diff --git a/.changeset/2009-load-failed-capability-fail-open.md b/.changeset/2009-load-failed-capability-fail-open.md
new file mode 100644
index 000000000..22ce740cf
--- /dev/null
+++ b/.changeset/2009-load-failed-capability-fail-open.md
@@ -0,0 +1,5 @@
+---
+type: Fixed
+pr: 2075
+---
+**Load-failed capability gates now fail open with a loud warning instead of blocking the whole project** — when an installed overlay (third-party) capability failed to load (e.g. an incompatible `engines.gsd` range) but had declared a `gate`-kind loop hook, the loop resolver injected a blocking synthetic gate (`blocking:true`, `onError:halt`) at every point where that capability declared a gate. A single incompatible capability therefore halted every `ship:pre` and `verify:post` in the project — unrelated to what the gate would have checked, and with no remediation surfaced. The resolver now injects no gate and instead emits a loud warning — to stderr and in the `loop render-hooks` envelope's `warnings` array — naming the load-failure reason and the exact `gsd capability remove <id>` remediation, and the loop proceeds (fail open). The capability id embedded in that remediation is validated against the canonical id shape first, so a malformed overlay directory name cannot inject shell metacharacters into the surfaced command. The loader still records `_overlay.blockedGates`; only the consequence changes from block to warn. `step`/`contribution` overlays were already skip-open. (#2009)
diff --git a/.changeset/2072-thread-model-into-routed-agent-spawns.md b/.changeset/2072-thread-model-into-routed-agent-spawns.md
new file mode 100644
index 000000000..a74b21ff9
--- /dev/null
+++ b/.changeset/2072-thread-model-into-routed-agent-spawns.md
@@ -0,0 +1,5 @@
+---
+type: Fixed
+pr: 2074
+---
+**`model_overrides` and per-phase-type models now actually apply to the assumptions-analyzer, code-reviewer, and code-fixer agents on Claude Code.** Previously `model_overrides["gsd-code-reviewer"]` / `["gsd-assumptions-analyzer"]` / `["gsd-code-fixer"]` (and `models.verification` / `models.discuss` / `models.execution`) were accepted and resolved but silently dropped — the workflows spawned these agents with no model, so they inherited the session model and the configured routing never took effect (no warning). Every spawn now threads its resolved model: `discuss-phase-assumptions`, `code-review`, and `code-review-fix` (both the re-review and the two fixer spawns) resolve it inline, and `quick`'s review step uses the code-reviewer's own resolved model instead of the executor's. The stale "`discuss` — reserved, no subagent" model-profile docs are corrected to list `gsd-assumptions-analyzer`, and the `verification` row now includes `gsd-code-reviewer`. (#2074)
diff --git a/docs/ARCHITECTURE.md b/docs/ARCHITECTURE.md
index 760409bcd..59ef61380 100644
--- a/docs/ARCHITECTURE.md
+++ b/docs/ARCHITECTURE.md
@@ -381,7 +381,7 @@ Node.js CLI utility (`gsd-tools.cjs`) with domain modules split across `gsd-core
 | `profile-pipeline.cjs` | User behavioral profiling data pipeline, session file scanning                                      |
 | `profile-output.cjs`       | Profile rendering, USER-PROFILE.md and dev-preferences.md generation                                |
 | `loop-host-contract.cjs`   | Generated Loop Host Contract — 12 loop points, per-step agent roles, and core artifacts; emitted by `scripts/gen-loop-host-contract.cjs` from workflow markers (ADR-894 §3); consumed by `gen-capability-registry.cjs` |
-| `capability-loader.cjs`    | Runtime registry overlay loader (ADR-1244 D2) — `loadRegistry({ includeInstalled })` composes the frozen first-party registry with a validated installed overlay of third-party capability manifests read from global `$GSD_HOME/.gsd/capabilities/` and project `<projectRoot>/.gsd/capabilities/`; first-party always wins; load-time `engines.gsd` re-gate skips incompatible overlays with a warning; gate-kind hooks on skipped capabilities fail CLOSED |
+| `capability-loader.cjs`    | Runtime registry overlay loader (ADR-1244 D2) — `loadRegistry({ includeInstalled })` composes the frozen first-party registry with a validated installed overlay of third-party capability manifests read from global `$GSD_HOME/.gsd/capabilities/` and project `<projectRoot>/.gsd/capabilities/`; first-party always wins; load-time `engines.gsd` re-gate skips incompatible overlays with a warning; gate-kind hooks on skipped capabilities fail OPEN — no gate is injected; a loud warning (stderr + envelope `warnings`) names the load failure and the `gsd capability remove <id>` remediation (#2009) |
 | `capability-registry.cjs`  | Generated central Capability Registry — role-partitioned index of all co-located capability declarations; emitted by `scripts/gen-capability-registry.cjs` (ADR-894 §5) |
 | `loop-resolver.cjs`        | Loop Extension Point resolver — ADR-857 phase 3c registry-consuming query; consumes resolved Capability State, filters `byLoopPoint` by capability enablement plus config activation, renders active hooks as markdown, emits `{ point, activeHooks, rendered }` envelope; `gsd-tools loop render-hooks <point> [--config-dir <path>]` |
 | `capability-state.cjs`     | Unified capability-state resolver — ADR-857 phase 4b/6; composes install profile, runtime surface, and config activation into one per-capability view consumed by workflow hook rendering; pure `resolveCapabilityState`, reusable `resolveCapabilityRuntimeState`, I/O `cmdCapabilityState`, and convenience predicate `isCapabilityActive(capId, cwd)`; `gsd-tools capability state [--config-dir <path>]` emits `{ runtimeConfigDir, capabilities[] }` where each entry carries `enabled` (installed && surfaced) and `active` (enabled && configActivation via the capability's `activationKey`; absent key → active===enabled) |
diff --git a/docs/CONFIGURATION.md b/docs/CONFIGURATION.md
index d754a4887..7505907e9 100644
--- a/docs/CONFIGURATION.md
+++ b/docs/CONFIGURATION.md
@@ -770,9 +770,9 @@ Installed overlay capabilities are merged via the same `buildRegistry` pipeline
 
 Each overlay manifest may declare an `engines.gsd` semver range. At load time GSD evaluates this range against the running GSD version. An overlay that does not satisfy the range is **skipped with a warning** — it is never loaded and never crashes the loop. Manifests without an `engines.gsd` field are accepted unconditionally.
 
-### Gate-kind fail-closed policy
+### Gate-kind fail-open policy (#2009)
 
-If a skipped overlay capability declared a `gate`-kind loop hook, the loop resolver **injects a blocking gate** at that hook point (fail CLOSED). Skipped capabilities whose hooks are `step` or `contribution` kind skip open — the loop proceeds without them.
+If a skipped or load-failed overlay capability (for example, one whose `engines.gsd` range is incompatible) declared a `gate`-kind loop hook, the loop resolver does **not** inject a gate at that hook point (fail OPEN): the loop proceeds. Instead it emits a loud warning — to stderr and in the `loop render-hooks` envelope's `warnings` array — naming the load-failure reason and the exact remediation, `gsd capability remove <id>`, so the operator is loudly told how to clear it. Skipped capabilities whose hooks are `step` or `contribution` kind skip open too, as before — the loop proceeds without them.
 
 ### Overlay config federation
 
@@ -1115,10 +1115,10 @@ for the change to take effect. See issue #2256.
 | Phase type | Agents |
 |---|---|
 | `planning` | `gsd-planner`, `gsd-roadmapper`, `gsd-pattern-mapper` |
-| `discuss` | (reserved — no subagent today) |
+| `discuss` | `gsd-assumptions-analyzer` |
 | `research` | `gsd-phase-researcher`, `gsd-project-researcher`, `gsd-research-synthesizer`, `gsd-codebase-mapper`, `gsd-ui-researcher` |
 | `execution` | `gsd-executor`, `gsd-debugger`, `gsd-doc-writer` |
-| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier` |
+| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier`, `gsd-code-reviewer` |
 | `completion` | (reserved — no subagent today) |
 
 `discuss` and `completion` are accepted by the schema for forward compatibility; setting them today is a no-op until a subagent maps to them.
diff --git a/docs/FEATURES.md b/docs/FEATURES.md
index 1a80bd7c3..2a3bcf584 100644
--- a/docs/FEATURES.md
+++ b/docs/FEATURES.md
@@ -2751,10 +2751,10 @@ Users who run a memory / knowledge-base MCP server (for example, ExoCortex-style
 | Slot | Agents assigned |
 |------|-----------------|
 | `planning` | `gsd-planner`, `gsd-roadmapper`, `gsd-pattern-mapper` |
-| `discuss` | (reserved for future subagent) |
+| `discuss` | `gsd-assumptions-analyzer` |
 | `research` | `gsd-phase-researcher`, `gsd-project-researcher`, `gsd-research-synthesizer`, `gsd-codebase-mapper`, `gsd-ui-researcher` |
 | `execution` | `gsd-executor`, `gsd-debugger`, `gsd-doc-writer` |
-| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier` |
+| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier`, `gsd-code-reviewer` |
 | `completion` | (reserved for future subagent) |
 
 **Accepted values:** `"opus"` / `"sonnet"` / `"haiku"` / `"inherit"`
diff --git a/docs/INVENTORY.md b/docs/INVENTORY.md
index be47f0f48..af1075362 100644
--- a/docs/INVENTORY.md
+++ b/docs/INVENTORY.md
@@ -407,7 +407,7 @@ Full listing: `gsd-core/bin/lib/*.cjs`.
 | `capability-lock.cjs` | Shared cross-process lock primitive (#1459 finding 4) — the SINGLE hardened lockfile protocol used by BOTH capability-lifecycle (`.gsd/capabilities/.lock`) and capability-consent (`.consent.lock`); exports `acquireLock(lockPath, opts?)`/`releaseLock(handle)` with pid + process-start-time liveness identity, a hard deadman, and token+inode owner-safe release — NEVER stale-steals a verified-live same-host holder, reclaims only a provably-dead/unverifiable holder, never deadlocks; `opts.maxAttempts`/`opts.waitForFresh` let the consent store serialize genuinely-contended writers; `_setLockProbes`/`_resetLockProbes` are test seams |
 | `capability-ledger.cjs` | Per-runtime install ledger (ADR-1244 D4) — atomic read/write of `.gsd-capabilities.json` recording `{ id, version, source, integrity, files[], sharedEdits[] }` per installed capability; exports `readLedger`/`writeLedger`/`recordInstall`/`removeEntry`/`reconcile` (orphan detection)/`readSmallRegularFile` (utf8) + `readSmallRegularFileBuffer` (raw bytes, the byte-exact consent-hash reader, #1459 finding 1); atomic commit point and reconciliation basis for Phase-4 upgrade/remove |
 | `capability-lifecycle.cjs` | Capability lifecycle orchestration (ADR-1244 Phase 4, D5+D6) — composes the source resolver + ledger + trust gate into `installCapability`/`upgradeCapability`/`removeCapability`/`reconcileCapabilities`; ledger write is the commit point; upgrade is atomic stage-then-swap (old set aside, new swapped in, ledger committed, backup dropped) with deterministic crash recovery (`reconcileCapabilities` rolls forward/back to a fully-old-or-fully-new state); remove surgically strips only marker-stamped (`_gsdCapability`) shared-config entries, preserving user hand-edits; never executes capability code |
-| `capability-loader.cjs` | Runtime Capability Registry overlay (ADR-1244 D2) — `loadRegistry({ includeInstalled })` composes the frozen first-party registry with a validated installed overlay read from `$GSD_HOME/.gsd/capabilities/<id>/` (global) and `<projectRoot>/.gsd/capabilities/<id>/` (project); first-party-wins on id/skill/agent/config collisions, reserved-namespace rejection, load-time `engines.gsd` re-gate (skip-with-warning), and gate-kind fail-closed via `_overlay.blockedGates`; composes through the canonical `buildRegistry` so derived views never drift |
+| `capability-loader.cjs` | Runtime Capability Registry overlay (ADR-1244 D2) — `loadRegistry({ includeInstalled })` composes the frozen first-party registry with a validated installed overlay read from `$GSD_HOME/.gsd/capabilities/<id>/` (global) and `<projectRoot>/.gsd/capabilities/<id>/` (project); first-party-wins on id/skill/agent/config collisions, reserved-namespace rejection, load-time `engines.gsd` re-gate (skip-with-warning), and gate-kind fail-open via `_overlay.blockedGates` — a loud warning (stderr + envelope `warnings`) naming the load failure and `gsd capability remove <id>` remediation; no gate injected (#2009); composes through the canonical `buildRegistry` so derived views never drift |
 | `capability-registry.cjs` | Generated central Capability Registry — role-partitioned index of all co-located capability declarations (`capabilities/<id>/capability.json`); emitted by `scripts/gen-capability-registry.cjs --write` (ADR-894 §5) |
 | `capability-source.cjs` | Capability source resolver (ADR-1244 D3) — `resolveCapabilitySource(spec, opts)` fetches and stages a capability from local path, git (https/ssh/git transports only), npm pack (no lifecycle scripts), tarball (sha512 integrity verify before extraction), or registry (stub); tar-slip/symlink rejection; atomic staging to `$GSD_HOME/.gsd/capabilities/<id>/`; no capability code executes during install |
 | `capability-state.cjs` | Unified capability-state resolver (ADR-857 phase 4b/6) — composes install profile, runtime surface, and config activation into one per-capability view consumed by workflow hook rendering; exports pure `resolveCapabilityState`, reusable `resolveCapabilityRuntimeState`, and I/O handler `cmdCapabilityState`; command surface: `gsd-tools capability state [--config-dir <path>]` emitting `{ runtimeConfigDir, capabilities[] }` |
diff --git a/docs/README.md b/docs/README.md
index f05fce2cd..c78509ffa 100644
--- a/docs/README.md
+++ b/docs/README.md
@@ -72,7 +72,7 @@ Language versions: [English](README.md) · [Português (pt-BR)](pt-BR/README.md)
 - [Multi-agent orchestration](explanation/multi-agent-orchestration.md) — how subagents are spawned, scoped, and coordinated
 - [Security model](explanation/security-model.md) — trust boundaries, permissions, and safe automation
 - [The capability trust model](explanation/capability-trust-model.md) — why third-party capabilities are gated by consent + integrity + reversibility, not a sandbox
-- [How overlay capabilities compose](explanation/capability-overlay-model.md) — why first-party always wins and how the loader resolves precedence, conflicts, and fail-closed gates
+- [How overlay capabilities compose](explanation/capability-overlay-model.md) — why first-party always wins and how the loader resolves precedence, conflicts, and fail-open load-failure warnings
 - [Architecture](ARCHITECTURE.md) — system architecture, agent model, and data flow
 - [Discuss modes](workflow-discuss-mode.md) — assumptions mode vs interview mode for `/gsd-discuss-phase`
 - [Context monitoring](context-monitor.md) — context window monitoring hook architecture
diff --git a/docs/explanation/capability-overlay-model.md b/docs/explanation/capability-overlay-model.md
index a39326644..b1d95f956 100644
--- a/docs/explanation/capability-overlay-model.md
+++ b/docs/explanation/capability-overlay-model.md
@@ -181,9 +181,10 @@ candidate is processed. A single broken overlay cannot poison the rest of the se
 
 ---
 
-## The one place where skipping is dangerous: gates
+## The one place where a skip must be loud: gates
 
-Skipping a broken overlay is the safe default for most surfaces — but not for *gates*.
+Skipping a broken overlay is the safe default for every surface — including gates, though
+gates get special treatment.
 
 A capability's loop hooks come in three kinds:
 
@@ -195,21 +196,28 @@ For steps and contributions, skipping a capability means the loop simply proceed
 **without** that addition. That is *fail-open*, and it is correct: the loop is missing an
 optional step, not doing something unsafe.
 
-A gate is the opposite. The whole purpose of a gate is to *stop* the loop when a
-condition is not met — a deploy gate, a house-style verification gate, a safety check. If
-GSD skipped a broken gate-declaring capability and proceeded, it would behave exactly as
-if the gate had *passed* — silently waving through the very thing the gate existed to
-block. That is a fail-open on a security-relevant control, and it is unacceptable.
+A gate looks different at first glance. The whole purpose of a gate is to *stop* the loop
+when a condition is not met — a deploy gate, a house-style verification gate, a safety
+check. Silently skipping a broken gate-declaring capability and proceeding as if the gate
+had *passed* would wave through the very thing the gate existed to block, with no signal
+to the operator at all.
 
-So composition treats gates asymmetrically from steps and contributions. When a
-capability that declares a gate is skipped, GSD records its gate points in
-`_overlay.incompatibleGateCapIds` and `_overlay.blockedGates`, and the loop resolver
-**injects a synthetic blocking gate** at each of those extension points. The loop
-**fails closed**: rather than proceed as if the gate passed, it halts with a message
-naming the skipped capability and why its gate could not be evaluated.
+So, per the maintainer decision on [#2009](https://github.com/open-gsd/gsd-core/issues/2009),
+composition treats gates like steps and contributions for control flow — the loop always
+proceeds — but never silently. When a capability that declares a gate is skipped, GSD
+records its gate points in `_overlay.incompatibleGateCapIds` and `_overlay.blockedGates`,
+and the loop resolver **injects no gate** at each of those extension points. The loop
+**fails open**, but loudly: it emits a warning through two channels — stderr (the channel
+host workflows/agents see when they run `gsd_run loop render-hooks <point>`) and the
+`loop render-hooks` JSON envelope's top-level `warnings` array. The warning names the
+skipped capability, why it could not be loaded (for example, an incompatible
+`engines.gsd` range), and the exact remediation — `gsd capability remove <id>` — so the
+operator sees the missing control on every pass through the loop until they act on it,
+instead of the loop halting project-wide over a single incompatible overlay.
 
 The discriminator is therefore *not* "is this overlay broken?" but "what does failing
-to load it mean?" — and for a gate, failing to load it means you must not proceed.
+to load it mean?" — and for a gate, failing to load it means the operator must be told,
+unmistakably, until they resolve it.
 
 ---
 
@@ -230,10 +238,12 @@ details make this safe rather than merely convenient:
   behind a path that a runtime dispatcher might `require()` a command module from.
 - Every dropped overlay's **gates are recorded as blocked** — using the same extraction
   as the per-candidate path — so a gate-declaring overlay that vanishes in the fallback
-  still **fails closed**, never open.
+  still **surfaces a loud warning** (stderr + envelope `warnings`) at its gate points
+  rather than vanishing silently (#2009).
 
 The principle is the same at every layer: when GSD cannot compose an overlay, it removes
-the overlay's *additions* but never weakens a *control*.
+the overlay's *additions* but never silences a *control* — a missing gate always
+surfaces, even though, per #2009, it no longer blocks the loop.
 
 ---
 
@@ -262,16 +272,20 @@ The overlay model rests on a few rules applied consistently:
 - **First-party always wins** every collision — id, skill/agent stem, config key,
   command family, reserved prefix. An overlay can only add, never override.
 - A bad overlay is **skipped, not crashed** — the loop always gets a usable registry.
-- Skipping **fails open** for steps and contributions (a missing optional addition) but
-  **fails closed** for gates (a missing control must block, not pass).
+- Skipping **fails open** for steps and contributions (a missing optional addition) and,
+  per [#2009](https://github.com/open-gsd/gsd-core/issues/2009), **fails open** for gates
+  too (a missing control, no gate injected) — but loudly, via a warning (stderr + the
+  envelope's `warnings` array) that names the load failure and its
+  `gsd capability remove <id>` remediation.
 - A whole-set compose failure **falls back to first-party**, clearing command roots and
-  still blocking dropped gates.
+  still surfacing dropped gates as loud warnings.
 - One canonical builder materialises both first-party and overlay views, so an accepted
   overlay has true parity with a shipped capability.
 
 Every one of these choices answers the same question — *what does it mean if this
-composition step fails?* — and resolves it in favour of first-party authority and a
-fail-closed security posture.
+composition step fails?* — and resolves it in favour of first-party authority and,
+per #2009, a loud fail-open posture: never silent, never a project-wide halt over a
+single incompatible overlay.
 
 ---
 
diff --git a/docs/how-to/configure-model-profiles.md b/docs/how-to/configure-model-profiles.md
index 153611526..8d575d2f5 100644
--- a/docs/how-to/configure-model-profiles.md
+++ b/docs/how-to/configure-model-profiles.md
@@ -90,8 +90,9 @@ Phase types and their agents:
 | `planning` | `gsd-planner`, `gsd-roadmapper`, `gsd-pattern-mapper` |
 | `research` | `gsd-phase-researcher`, `gsd-project-researcher`, `gsd-research-synthesizer`, `gsd-codebase-mapper`, `gsd-ui-researcher` |
 | `execution` | `gsd-executor`, `gsd-debugger`, `gsd-doc-writer` |
-| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier` |
-| `discuss`, `completion` | Reserved — no subagent today; accepted by schema for forward compatibility |
+| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier`, `gsd-code-reviewer` |
+| `discuss` | `gsd-assumptions-analyzer` |
+| `completion` | Reserved — no subagent today; accepted by schema for forward compatibility |
 
 The `models` block accepts tier aliases only (`opus`, `sonnet`, `haiku`, `inherit`). For a fully-qualified model ID, use `model_overrides` per agent instead.
 
diff --git a/docs/ja-JP/FEATURES.md b/docs/ja-JP/FEATURES.md
index 31c1da45c..0e65982f6 100644
--- a/docs/ja-JP/FEATURES.md
+++ b/docs/ja-JP/FEATURES.md
@@ -2676,10 +2676,10 @@ capture_thought({
 | スロット | 割り当てられたエージェント |
 |---------|----------------------|
 | `planning` | `gsd-planner`、`gsd-roadmapper`、`gsd-pattern-mapper` |
-| `discuss` | （将来のサブエージェント用に予約） |
+| `discuss` | `gsd-assumptions-analyzer` |
 | `research` | `gsd-phase-researcher`、`gsd-project-researcher`、`gsd-research-synthesizer`、`gsd-codebase-mapper`、`gsd-ui-researcher` |
 | `execution` | `gsd-executor`、`gsd-debugger`、`gsd-doc-writer` |
-| `verification` | `gsd-verifier`、`gsd-plan-checker`、`gsd-integration-checker`、`gsd-nyquist-auditor`、`gsd-ui-checker`、`gsd-ui-auditor`、`gsd-doc-verifier` |
+| `verification` | `gsd-verifier`、`gsd-plan-checker`、`gsd-integration-checker`、`gsd-nyquist-auditor`、`gsd-ui-checker`、`gsd-ui-auditor`、`gsd-doc-verifier`、`gsd-code-reviewer` |
 | `completion` | （将来のサブエージェント用に予約） |
 
 **受け入れられる値:** `"opus"` / `"sonnet"` / `"haiku"` / `"inherit"`
diff --git a/docs/ja-JP/how-to/configure-model-profiles.md b/docs/ja-JP/how-to/configure-model-profiles.md
index 2cb243c82..bd59d3f3b 100644
--- a/docs/ja-JP/how-to/configure-model-profiles.md
+++ b/docs/ja-JP/how-to/configure-model-profiles.md
@@ -88,8 +88,9 @@ npx @opengsd/gsd-core@latest --codex --global   # または --opencode、--kilo
 | `planning` | `gsd-planner`、`gsd-roadmapper`、`gsd-pattern-mapper` |
 | `research` | `gsd-phase-researcher`、`gsd-project-researcher`、`gsd-research-synthesizer`、`gsd-codebase-mapper`、`gsd-ui-researcher` |
 | `execution` | `gsd-executor`、`gsd-debugger`、`gsd-doc-writer` |
-| `verification` | `gsd-verifier`、`gsd-plan-checker`、`gsd-integration-checker`、`gsd-nyquist-auditor`、`gsd-ui-checker`、`gsd-ui-auditor`、`gsd-doc-verifier` |
-| `discuss`、`completion` | 予約済み — 現在はサブエージェントなし。スキーマの前方互換性のために受け入れられます |
+| `verification` | `gsd-verifier`、`gsd-plan-checker`、`gsd-integration-checker`、`gsd-nyquist-auditor`、`gsd-ui-checker`、`gsd-ui-auditor`、`gsd-doc-verifier`、`gsd-code-reviewer` |
+| `discuss` | `gsd-assumptions-analyzer` |
+| `completion` | 予約済み — 現在はサブエージェントなし。スキーマの前方互換性のために受け入れられます |
 
 `models` ブロックはティアエイリアス（`opus`、`sonnet`、`haiku`、`inherit`）のみを受け入れます。特定のエージェントに完全修飾のモデル ID を指定するには `model_overrides` を使用してください。
 
diff --git a/docs/ko-KR/how-to/configure-model-profiles.md b/docs/ko-KR/how-to/configure-model-profiles.md
index c87349c3f..e76d3758c 100644
--- a/docs/ko-KR/how-to/configure-model-profiles.md
+++ b/docs/ko-KR/how-to/configure-model-profiles.md
@@ -88,8 +88,9 @@ npx @opengsd/gsd-core@latest --codex --global   # 또는 --opencode, --kilo 등
 | `planning` | `gsd-planner`, `gsd-roadmapper`, `gsd-pattern-mapper` |
 | `research` | `gsd-phase-researcher`, `gsd-project-researcher`, `gsd-research-synthesizer`, `gsd-codebase-mapper`, `gsd-ui-researcher` |
 | `execution` | `gsd-executor`, `gsd-debugger`, `gsd-doc-writer` |
-| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier` |
-| `discuss`, `completion` | 예약됨 — 현재 서브에이전트 없음; 향후 호환성을 위해 스키마에서 허용 |
+| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier`, `gsd-code-reviewer` |
+| `discuss` | `gsd-assumptions-analyzer` |
+| `completion` | 예약됨 — 현재 서브에이전트 없음; 향후 호환성을 위해 스키마에서 허용 |
 
 `models` 블록은 티어 별칭만 허용합니다(`opus`, `sonnet`, `haiku`, `inherit`). 완전히 정규화된 모델 ID는 에이전트별 `model_overrides`를 사용하세요.
 
diff --git a/docs/pt-BR/CONFIGURATION.md b/docs/pt-BR/CONFIGURATION.md
index 9510927f6..fda6c8b64 100644
--- a/docs/pt-BR/CONFIGURATION.md
+++ b/docs/pt-BR/CONFIGURATION.md
@@ -836,10 +836,10 @@ para que a alteração entre em vigor. Consulte a issue #2256.
 | Tipo de fase | Agentes |
 |---|---|
 | `planning` | `gsd-planner`, `gsd-roadmapper`, `gsd-pattern-mapper` |
-| `discuss` | (reservado — sem subagente atualmente) |
+| `discuss` | `gsd-assumptions-analyzer` |
 | `research` | `gsd-phase-researcher`, `gsd-project-researcher`, `gsd-research-synthesizer`, `gsd-codebase-mapper`, `gsd-ui-researcher` |
 | `execution` | `gsd-executor`, `gsd-debugger`, `gsd-doc-writer` |
-| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier` |
+| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier`, `gsd-code-reviewer` |
 | `completion` | (reservado — sem subagente atualmente) |
 
 `discuss` e `completion` são aceitos pelo esquema para compatibilidade futura; defini-los hoje é um no-op até que um subagente seja mapeado para eles.
diff --git a/docs/pt-BR/how-to/configure-model-profiles.md b/docs/pt-BR/how-to/configure-model-profiles.md
index 66465a740..4f04d6b43 100644
--- a/docs/pt-BR/how-to/configure-model-profiles.md
+++ b/docs/pt-BR/how-to/configure-model-profiles.md
@@ -88,8 +88,9 @@ Tipos de fase e seus agentes:
 | `planning` | `gsd-planner`, `gsd-roadmapper`, `gsd-pattern-mapper` |
 | `research` | `gsd-phase-researcher`, `gsd-project-researcher`, `gsd-research-synthesizer`, `gsd-codebase-mapper`, `gsd-ui-researcher` |
 | `execution` | `gsd-executor`, `gsd-debugger`, `gsd-doc-writer` |
-| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier` |
-| `discuss`, `completion` | Reservado — nenhum subagente hoje; aceito pelo esquema para compatibilidade futura |
+| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier`, `gsd-code-reviewer` |
+| `discuss` | `gsd-assumptions-analyzer` |
+| `completion` | Reservado — nenhum subagente hoje; aceito pelo esquema para compatibilidade futura |
 
 O bloco `models` aceita apenas aliases de nível (`opus`, `sonnet`, `haiku`, `inherit`). Para um ID de modelo totalmente qualificado, use `model_overrides` por agente.
 
diff --git a/docs/zh-CN/CONFIGURATION.md b/docs/zh-CN/CONFIGURATION.md
index 2b49cf333..a43d6ba14 100644
--- a/docs/zh-CN/CONFIGURATION.md
+++ b/docs/zh-CN/CONFIGURATION.md
@@ -805,10 +805,10 @@ gsd-tools query config-set features.thinking_partner false
 | 阶段类型 | Agents |
 |---|---|
 | `planning` | `gsd-planner`, `gsd-roadmapper`, `gsd-pattern-mapper` |
-| `discuss` | （保留——当前无 subagent） |
+| `discuss` | `gsd-assumptions-analyzer` |
 | `research` | `gsd-phase-researcher`, `gsd-project-researcher`, `gsd-research-synthesizer`, `gsd-codebase-mapper`, `gsd-ui-researcher` |
 | `execution` | `gsd-executor`, `gsd-debugger`, `gsd-doc-writer` |
-| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier` |
+| `verification` | `gsd-verifier`, `gsd-plan-checker`, `gsd-integration-checker`, `gsd-nyquist-auditor`, `gsd-ui-checker`, `gsd-ui-auditor`, `gsd-doc-verifier`, `gsd-code-reviewer` |
 | `completion` | （保留——当前无 subagent） |
 
 `discuss` 和 `completion` 被 schema 接受以保持前向兼容性；今天设置它们是无操作，直到某个 subagent 映射到它们为止。
diff --git a/docs/zh-CN/FEATURES.md b/docs/zh-CN/FEATURES.md
index 80953d3af..3d9e87e08 100644
--- a/docs/zh-CN/FEATURES.md
+++ b/docs/zh-CN/FEATURES.md
@@ -2692,10 +2692,10 @@ capture_thought({
 | 槽位 | 分配的智能体 |
 |------|-----------------|
 | `planning` | `gsd-planner`、`gsd-roadmapper`、`gsd-pattern-mapper` |
-| `discuss` | （为未来子智能体保留） |
+| `discuss` | `gsd-assumptions-analyzer` |
 | `research` | `gsd-phase-researcher`、`gsd-project-researcher`、`gsd-research-synthesizer`、`gsd-codebase-mapper`、`gsd-ui-researcher` |
 | `execution` | `gsd-executor`、`gsd-debugger`、`gsd-doc-writer` |
-| `verification` | `gsd-verifier`、`gsd-plan-checker`、`gsd-integration-checker`、`gsd-nyquist-auditor`、`gsd-ui-checker`、`gsd-ui-auditor`、`gsd-doc-verifier` |
+| `verification` | `gsd-verifier`、`gsd-plan-checker`、`gsd-integration-checker`、`gsd-nyquist-auditor`、`gsd-ui-checker`、`gsd-ui-auditor`、`gsd-doc-verifier`、`gsd-code-reviewer` |
 | `completion` | （为未来子智能体保留） |
 
 **接受的值：** `"opus"` / `"sonnet"` / `"haiku"` / `"inherit"`
diff --git a/docs/zh-CN/how-to/configure-model-profiles.md b/docs/zh-CN/how-to/configure-model-profiles.md
index f3e790985..2bb89ae40 100644
--- a/docs/zh-CN/how-to/configure-model-profiles.md
+++ b/docs/zh-CN/how-to/configure-model-profiles.md
@@ -88,8 +88,9 @@ npx @opengsd/gsd-core@latest --codex --global   # or --opencode, --kilo, etc.
 | `planning` | `gsd-planner`、`gsd-roadmapper`、`gsd-pattern-mapper` |
 | `research` | `gsd-phase-researcher`、`gsd-project-researcher`、`gsd-research-synthesizer`、`gsd-codebase-mapper`、`gsd-ui-researcher` |
 | `execution` | `gsd-executor`、`gsd-debugger`、`gsd-doc-writer` |
-| `verification` | `gsd-verifier`、`gsd-plan-checker`、`gsd-integration-checker`、`gsd-nyquist-auditor`、`gsd-ui-checker`、`gsd-ui-auditor`、`gsd-doc-verifier` |
-| `discuss`、`completion` | 保留——目前无子代理；已被模式接受以备向后兼容 |
+| `verification` | `gsd-verifier`、`gsd-plan-checker`、`gsd-integration-checker`、`gsd-nyquist-auditor`、`gsd-ui-checker`、`gsd-ui-auditor`、`gsd-doc-verifier`、`gsd-code-reviewer` |
+| `discuss` | `gsd-assumptions-analyzer` |
+| `completion` | 保留——目前无子代理；已被模式接受以备向后兼容 |
 
 `models` 块仅接受层级别名（`opus`、`sonnet`、`haiku`、`inherit`）。如需使用完全限定的模型 ID，请改用按代理设置的 `model_overrides`。
 
diff --git a/gsd-core/references/model-profiles.md b/gsd-core/references/model-profiles.md
index 52e3f7a8d..7cdefdbc8 100644
--- a/gsd-core/references/model-profiles.md
+++ b/gsd-core/references/model-profiles.md
@@ -45,10 +45,10 @@ Model profiles control which Claude model each GSD agent uses. This allows balan
 | Phase type | Agents |
 |---|---|
 | `planning` | gsd-planner, gsd-roadmapper, gsd-pattern-mapper |
-| `discuss` | (reserved — no subagent today) |
+| `discuss` | `gsd-assumptions-analyzer` |
 | `research` | gsd-phase-researcher, gsd-project-researcher, gsd-research-synthesizer, gsd-codebase-mapper, gsd-ui-researcher |
 | `execution` | gsd-executor, gsd-debugger, gsd-doc-writer |
-| `verification` | gsd-verifier, gsd-plan-checker, gsd-integration-checker, gsd-nyquist-auditor, gsd-ui-checker, gsd-ui-auditor, gsd-doc-verifier |
+| `verification` | gsd-verifier, gsd-plan-checker, gsd-integration-checker, gsd-nyquist-auditor, gsd-ui-checker, gsd-ui-auditor, gsd-doc-verifier, gsd-code-reviewer |
 | `completion` | (reserved — no subagent today) |
 
 ### Resolution precedence (highest to lowest)
diff --git a/gsd-core/workflows/code-review-fix.md b/gsd-core/workflows/code-review-fix.md
index 9a14680b6..833be2013 100644
--- a/gsd-core/workflows/code-review-fix.md
+++ b/gsd-core/workflows/code-review-fix.md
@@ -23,6 +23,10 @@ INIT=$(gsd_run query init.phase-op "${PHASE_ARG}")
 if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
 AGENT_SKILLS_FIXER=$(gsd_run query agent-skills gsd-code-fixer)
 AGENT_SKILLS_REVIEWER=$(gsd_run query agent-skills gsd-code-reviewer)
+# #2072: resolve the routed models so model_overrides / models.<phaseType> are honored
+# (gsd-code-reviewer → "verification", gsd-code-fixer → "execution"); thread them below.
+REVIEWER_MODEL=$(gsd_run query resolve-model gsd-code-reviewer --raw)
+FIXER_MODEL=$(gsd_run query resolve-model gsd-code-fixer --raw)
 ```
 
 Parse from init JSON: `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `padded_phase`, `commit_docs`.
@@ -194,7 +198,7 @@ echo "Fix scope: ${FIX_SCOPE}"
 Use Agent() to spawn agent:
 
 ```text
-Agent(subagent_type="gsd-code-fixer", prompt="
+Agent(subagent_type="gsd-code-fixer", model="{FIXER_MODEL}", prompt="
 <files_to_read>
 ${REVIEW_PATH}
 </files_to_read>
@@ -277,7 +281,7 @@ if [ "$AUTO_MODE" = "true" ]; then
     
     # Spawn gsd-code-reviewer agent to re-review (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)
     # (This overwrites REVIEW_PATH with latest review state)
-    Agent(subagent_type="gsd-code-reviewer", prompt="
+    Agent(subagent_type="gsd-code-reviewer", model="{REVIEWER_MODEL}", prompt="
 <config>
 depth: ${REVIEW_DEPTH}
 phase_dir: ${PHASE_DIR}
@@ -311,7 +315,7 @@ ${AGENT_SKILLS_REVIEWER}")
     # Still has issues — spawn fixer again (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)
     echo "Issues remain. Applying fixes for iteration ${ITERATION}..."
     
-    Agent(subagent_type="gsd-code-fixer", prompt="
+    Agent(subagent_type="gsd-code-fixer", model="{FIXER_MODEL}", prompt="
 <files_to_read>
 ${REVIEW_PATH}
 </files_to_read>
diff --git a/gsd-core/workflows/code-review.md b/gsd-core/workflows/code-review.md
index 0a257473f..a559cd74a 100644
--- a/gsd-core/workflows/code-review.md
+++ b/gsd-core/workflows/code-review.md
@@ -22,6 +22,9 @@ PHASE_ARG="${1}"
 INIT=$(gsd_run query init.phase-op "${PHASE_ARG}")
 if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
 AGENT_SKILLS_REVIEWER=$(gsd_run query agent-skills gsd-code-reviewer)
+# #2072: resolve the routed model so model_overrides / models.verification are honored
+# (the resolver maps gsd-code-reviewer → phaseType "verification"); thread it below.
+REVIEWER_MODEL=$(gsd_run query resolve-model gsd-code-reviewer --raw)
 ```
 
 Parse from init JSON: `phase_found`, `phase_dir`, `phase_number`, `phase_name`, `padded_phase`, `commit_docs`.
@@ -482,7 +485,7 @@ Spawn the gsd-code-reviewer agent:
 Print: `◆ Spawning code reviewer... (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)`
 
 ```
-Agent(subagent_type="gsd-code-reviewer", prompt="
+Agent(subagent_type="gsd-code-reviewer", model="{REVIEWER_MODEL}", prompt="
 <files_to_read>
 ${FILES_TO_READ}
 </files_to_read>
diff --git a/gsd-core/workflows/discuss-phase-assumptions.md b/gsd-core/workflows/discuss-phase-assumptions.md
index 80c6666ae..6aa600c70 100644
--- a/gsd-core/workflows/discuss-phase-assumptions.md
+++ b/gsd-core/workflows/discuss-phase-assumptions.md
@@ -68,6 +68,9 @@ _GSD_SHIM_NAME="gsd-tools.cjs"; _GSD_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-pars
 INIT=$(gsd_run query init.phase-op "${PHASE}")
 if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
 AGENT_SKILLS_ANALYZER=$(gsd_run query agent-skills gsd-assumptions-analyzer)
+# #2072: resolve the routed model so model_overrides / models.discuss are honored
+# (the resolver maps gsd-assumptions-analyzer → phaseType "discuss"); thread it below.
+ANALYZER_MODEL=$(gsd_run query resolve-model gsd-assumptions-analyzer --raw)
 ```
 
 Parse JSON for: `commit_docs`, `phase_found`, `phase_dir`, `phase_number`, `phase_name`,
@@ -255,7 +258,7 @@ If no USER-PROFILE.md: calibration_tier = "standard"
 **Spawn Explore subagent** (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)**:**
 
 ```
-Agent(subagent_type="gsd-assumptions-analyzer", prompt="""
+Agent(subagent_type="gsd-assumptions-analyzer", model="{ANALYZER_MODEL}", prompt="""
 Analyze the codebase for Phase {PHASE}: {phase_name}.
 
 Phase goal: {roadmap_description}
diff --git a/gsd-core/workflows/quick.md b/gsd-core/workflows/quick.md
index fc9f98756..b3ec7b140 100644
--- a/gsd-core/workflows/quick.md
+++ b/gsd-core/workflows/quick.md
@@ -134,7 +134,7 @@ AGENT_SKILLS_CHECKER=$(gsd_run query agent-skills gsd-plan-checker)
 AGENT_SKILLS_VERIFIER=$(gsd_run query agent-skills gsd-verifier)
 ```
 
-Parse JSON for: `planner_model`, `executor_model`, `checker_model`, `verifier_model`, `commit_docs`, `branch_name`, `quick_id`, `slug`, `date`, `timestamp`, `quick_dir`, `task_dir`, `roadmap_exists`, `planning_exists`.
+Parse JSON for: `planner_model`, `executor_model`, `checker_model`, `verifier_model`, `reviewer_model`, `commit_docs`, `branch_name`, `quick_id`, `slug`, `date`, `timestamp`, `quick_dir`, `task_dir`, `roadmap_exists`, `planning_exists`.
 
 ```bash
 USE_WORKTREES=$(gsd_run query config-get workflow.use_worktrees --raw 2>/dev/null || echo "true")
@@ -868,7 +868,7 @@ Agent(
   Output: ${QUICK_DIR}/${quick_id}-REVIEW.md
   Depth: quick",
   subagent_type="gsd-code-reviewer",
-  model="{executor_model}"
+  model="{reviewer_model}"
 )
 ```
 
diff --git a/src/capability-loader.cts b/src/capability-loader.cts
index 673570770..2ba118ccc 100644
--- a/src/capability-loader.cts
+++ b/src/capability-loader.cts
@@ -17,10 +17,12 @@
  *     `gsd-core-` / `anthropic-` id prefix) is rejected.
  *   - Load-time re-gate (default-resilient): an overlay that fails validation or
  *     whose `engines.gsd` does not satisfy the running GSD version is SKIPPED
- *     with a warning — it never crashes the loop. EXCEPTION (per-hook-kind
- *     policy): a skipped capability that declares a `gate` is recorded in
- *     `_overlay.incompatibleGateCapIds` so the loop resolver can fail CLOSED for
- *     that gate rather than silently proceeding as if it had passed.
+ *     with a warning — it never crashes the loop. A skipped capability that
+ *     declares a `gate` is additionally recorded in
+ *     `_overlay.incompatibleGateCapIds` / `_overlay.blockedGates` so the loop
+ *     resolver can surface a loud fail-OPEN advisory for that gate (#2009): the
+ *     un-evaluable gate is skipped (not enforced) with a remediation message,
+ *     rather than silently vanishing.
  *
  * The merged registry is materialized by the canonical `buildRegistry`
  * (re-exported from the generator, which ships) over a cap-map reconstructed
@@ -845,12 +847,12 @@ export function loadRegistry(options: LoadRegistryOptions = {}): Registry {
     // to load. Clear the map (the first-party base never lists overlay commandRoots — first-party
     // command modules ship in bin/lib/, not via _overlay.commandRoots).
     meta.commandRoots = {};
-    // #1461 OVL-2 fail-CLOSED on compose failure (HIGH): the fallback DROPS every accepted overlay,
-    // so any accepted overlay that DECLARED a gate would have its gate silently vanish → a blocking
-    // gate FAILS OPEN, violating ADR-1244 (a skipped capability declaring a gate must FAIL CLOSED).
+    // #1461 OVL-2 (HIGH): on compose failure the fallback DROPS every accepted overlay, so any
+    // accepted overlay that DECLARED a gate would have its gate silently vanish with no trace.
     // Record each dropped gate-declaring overlay's gate as blocked using the SAME extraction the
-    // per-candidate `skip()` closure uses (gatePointsOf), so loop-resolver injects the synthetic
-    // blocking gate at each declared point exactly as it would for a per-candidate skip.
+    // per-candidate `skip()` closure uses (gatePointsOf), so loop-resolver surfaces the loud
+    // fail-OPEN advisory (#2009) at each declared point exactly as it would for a per-candidate
+    // skip — the gate does not silently disappear.
     for (const cap of overlayCaps) {
       const gatePoints = gatePointsOf(cap);
       if (gatePoints.length === 0) continue;
diff --git a/src/init.cts b/src/init.cts
index 8ac092f2c..196b266e2 100644
--- a/src/init.cts
+++ b/src/init.cts
@@ -759,6 +759,9 @@ function cmdInitQuick(cwd: string, description: string | undefined, raw: boolean
     executor_model: resolveModelInternal(cwd, 'gsd-executor'),
     checker_model: resolveModelInternal(cwd, 'gsd-plan-checker'),
     verifier_model: resolveModelInternal(cwd, 'gsd-verifier'),
+    // #2072: the quick review step spawns gsd-code-reviewer; resolve its own model
+    // so model_overrides / models.verification apply (was reusing executor_model).
+    reviewer_model: resolveModelInternal(cwd, 'gsd-code-reviewer'),
 
     commit_docs: config.commit_docs,
     branch_name: quickBranchName,
diff --git a/src/loop-resolver.cts b/src/loop-resolver.cts
index 1b0d3b1aa..ff86175a7 100644
--- a/src/loop-resolver.cts
+++ b/src/loop-resolver.cts
@@ -454,6 +454,27 @@ function renderLoopHooks(resolved: ResolveLoopHooksResult): string {
  * Missing <capId> value → coreError + non-zero exit.
  * Unknown/inactive capId → `false` (not an error).
  */
+// #2009: a capability id surfaced inside the runnable `gsd capability remove <id>`
+// remediation must match the canonical kebab-case id shape (identical to
+// capability-consent.cts / capability-ledger.cts) before it is embedded — a raw
+// overlay directory name is attacker-controlled and can carry shell/markdown
+// metacharacters (backticks, ';', '|', '$()'). An id that fails this check is
+// withheld and no runnable command is rendered for it.
+const LOAD_FAIL_CAP_ID_RE = /^[a-z][a-z0-9-]*$/;
+
+// #2009: neutralize control chars, newlines, and backticks from a third-party
+// load-failure reason so a malicious manifest cannot break out of the warning
+// line or inject markdown / prompt content into the surfaced message.
+function sanitizeLoadFailReason(reason: unknown): string {
+  const cleaned = String(reason)
+    // Strip C0 control chars, DEL, and backticks; collapse remaining whitespace.
+    .replace(/[\x00-\x1F\x7F`]/g, ' ')
+    .replace(/\s+/g, " ")
+    .trim()
+    .slice(0, 300);
+  return cleaned || '(no reason given)';
+}
+
 function cmdLoopRenderHooks(
   cwd: string,
   point: string,
@@ -519,26 +540,55 @@ function cmdLoopRenderHooks(
     return;
   }
 
-  // ── ADR-1244 D2 fail-closed gate injection ────────────────────────────────────
-  // For every skipped overlay capability that declared a gate at this point,
-  // inject a synthetic BLOCKING gate into the resolved output so the loop HALTS
-  // rather than silently proceeding as if the gate had passed. step/contribution
-  // overlays that were skipped are left open (skip-open is correct for them).
+  // ── ADR-1244 D2: load-failed capability gates FAIL OPEN with a loud warning ────
+  // Decision (#2009): a capability that failed to LOAD must not block the loop.
+  // The prior behavior injected a BLOCKING synthetic gate (blocking:true,
+  // onError:'halt') at every point where the skipped cap declared a gate, so a
+  // single incompatible capability halted every ship:pre / verify:post
+  // project-wide for a load error unrelated to what the gate checked — with no
+  // remediation surfaced. We now fail OPEN: no gate is injected (the loop proceeds
+  // and `--active-cap <failed-cap>` correctly reports it inactive), and a loud
+  // warning is emitted instead — to STDERR (which the operator, or the agent
+  // running the command, actually sees regardless of how the host workflow
+  // consumes stdout) AND in the envelope's `warnings` channel for structured
+  // consumers. The warning names the load reason and the exact
+  // `gsd capability remove <id>` remediation so the operator can clear the broken
+  // capability. blockedGates is still recorded by the loader; only the consequence
+  // changes from block to warn. step/contribution overlays were already skip-open.
+  //
+  // The gate injection was dropped rather than made non-blocking because no host
+  // workflow generically surfaces an arbitrary gate's message at ship:pre /
+  // verify:post (consumers dispatch on specific capIds / ref.skills), and the
+  // generic gate consumers expect an object-shaped `check`, not a prose string —
+  // so an injected advisory gate would be silently dropped or mis-dispatched. A
+  // stderr warning is the channel that is actually surfaced. (See #2009 review.)
   const overlayMeta = (registry as { _overlay?: { blockedGates?: Array<{ point: string; capId: string; reason: string }> } })['_overlay'];
+  const loadFailWarnings: string[] = [];
   if (overlayMeta && Array.isArray(overlayMeta.blockedGates)) {
     for (const blocked of overlayMeta.blockedGates) {
-      if (blocked.point === point) {
-        const syntheticGate: ActiveHook = {
-          capId: blocked.capId,
-          kind: 'gate',
-          blocking: true,
-          onError: 'halt',
-          check: `capability "${blocked.capId}" was skipped at load (${blocked.reason}); its gate at ${point} cannot be evaluated — failing closed`,
-        };
-        resolved.activeHooks.push(syntheticGate);
-      }
+      if (blocked.point !== point) continue;
+      // Security (#2009 review): capId/reason come from a third-party manifest or
+      // directory name. Validate capId before embedding it in the runnable
+      // remediation command; withhold it (no runnable command) if it is not a
+      // canonical id. Strip control chars/backticks from reason.
+      const idValid = LOAD_FAIL_CAP_ID_RE.test(String(blocked.capId));
+      const capLabel = idValid
+        ? `"${blocked.capId}"`
+        : 'with an invalid id (withheld) under .gsd/capabilities/';
+      const remediation = idValid
+        ? `Run \`gsd capability remove ${blocked.capId}\` to remove it, or fix the load error.`
+        : 'Remove the offending capability directory under .gsd/capabilities/, or fix the load error.';
+      loadFailWarnings.push(
+        `capability ${capLabel} failed to load (${sanitizeLoadFailReason(blocked.reason)}); ` +
+        `its gate at ${point} is SKIPPED and NOT enforced (failing open). ${remediation}`,
+      );
     }
   }
+  // Emit loudly to stderr in EVERY output mode (including --active-cap), so a
+  // skipped gate is never silently invisible to the operator/agent.
+  for (const w of loadFailWarnings) {
+    process.stderr.write(`gsd: warning — ${w}\n`);
+  }
 
   // --active-cap mode: print exactly 'true' or 'false' with no envelope
   if (activeCapId !== undefined) {
@@ -558,8 +608,12 @@ function cmdLoopRenderHooks(
     activeHooks: resolved.activeHooks,
     rendered,
   };
-  if (state.warnings && state.warnings.length > 0) {
-    envelope.warnings = state.warnings;
+  // Surface capability-state warnings and the #2009 load-failure fail-open
+  // warnings together in the structured `warnings` channel (in addition to the
+  // stderr emission above, which is the channel host workflows actually see).
+  const combinedWarnings = [...(state.warnings || []), ...loadFailWarnings];
+  if (combinedWarnings.length > 0) {
+    envelope.warnings = combinedWarnings;
   }
 
   coreOutput(envelope, raw);
diff --git a/tests/fixtures/golden-install-parity/antigravity.json b/tests/fixtures/golden-install-parity/antigravity.json
index e6c8252c3..e7e4e189d 100644
--- a/tests/fixtures/golden-install-parity/antigravity.json
+++ b/tests/fixtures/golden-install-parity/antigravity.json
@@ -94,7 +94,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "de81380316d8a37f",
-  "gsd-core/references/model-profiles.md": "d6ed560db6357ad2",
+  "gsd-core/references/model-profiles.md": "6568ca29b6ee00d8",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "2459c40bfc8a0ea8",
@@ -207,13 +207,13 @@
   "gsd-core/workflows/autonomous.md": "603ce2019835f00e",
   "gsd-core/workflows/check-todos.md": "5a62092df800ad7c",
   "gsd-core/workflows/cleanup.md": "12c8fd85d3010fe6",
-  "gsd-core/workflows/code-review-fix.md": "5738cb929c995008",
-  "gsd-core/workflows/code-review.md": "d454365f1704d0bc",
+  "gsd-core/workflows/code-review-fix.md": "60640e633b0a124b",
+  "gsd-core/workflows/code-review.md": "5c40505c01871153",
   "gsd-core/workflows/complete-milestone.md": "aaf272074acec69d",
   "gsd-core/workflows/debug.md": "68f1ddc74886ebe5",
   "gsd-core/workflows/diagnose-issues.md": "c8c41993c277363c",
   "gsd-core/workflows/discovery-phase.md": "3de990caffdde4f8",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "42210a0cbe1bac70",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "8581fd77def7ce84",
   "gsd-core/workflows/discuss-phase-power.md": "5c0d1ca6abda0383",
   "gsd-core/workflows/discuss-phase.md": "c0a977154470b7f5",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "ab0c68941386998b",
@@ -279,7 +279,7 @@
   "gsd-core/workflows/pr-branch.md": "dc5598ae8accdecd",
   "gsd-core/workflows/profile-user.md": "355af92ac285567f",
   "gsd-core/workflows/progress.md": "79a11ce798082054",
-  "gsd-core/workflows/quick.md": "35582887917ef938",
+  "gsd-core/workflows/quick.md": "7108075f69e88e7c",
   "gsd-core/workflows/reapply-patches.md": "4dcd6117d0a507ca",
   "gsd-core/workflows/remove-phase.md": "23b9eb0858a2535e",
   "gsd-core/workflows/remove-workspace.md": "d0bd7e0601138798",
diff --git a/tests/fixtures/golden-install-parity/augment.json b/tests/fixtures/golden-install-parity/augment.json
index 7785d1737..9ced83650 100644
--- a/tests/fixtures/golden-install-parity/augment.json
+++ b/tests/fixtures/golden-install-parity/augment.json
@@ -165,7 +165,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "8484ad9799b7f680",
+  "gsd-core/references/model-profiles.md": "e067ad3df6770db1",
   "gsd-core/references/mvp-concepts.md": "72f7e8b1f8ae7118",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -278,13 +278,13 @@
   "gsd-core/workflows/autonomous.md": "7e5683728ef33707",
   "gsd-core/workflows/check-todos.md": "bdeaf43f9c61e0cc",
   "gsd-core/workflows/cleanup.md": "0daa2f2720c111f1",
-  "gsd-core/workflows/code-review-fix.md": "c323f7098b671bd6",
-  "gsd-core/workflows/code-review.md": "ad450c6ef8459dad",
+  "gsd-core/workflows/code-review-fix.md": "2e113d1f4350a075",
+  "gsd-core/workflows/code-review.md": "334c90c401f291f8",
   "gsd-core/workflows/complete-milestone.md": "c1f91b77f4ace7f2",
   "gsd-core/workflows/debug.md": "849d7e5b9c12dcae",
   "gsd-core/workflows/diagnose-issues.md": "6cc3900891dfb927",
   "gsd-core/workflows/discovery-phase.md": "3ba7cfb89fb1e761",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "1e229f6d21831d60",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "f5b765d33eba4f88",
   "gsd-core/workflows/discuss-phase-power.md": "0841f7dc6e9a054a",
   "gsd-core/workflows/discuss-phase.md": "5c5e8d8c2c9d95aa",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "db488d74d080c653",
@@ -350,7 +350,7 @@
   "gsd-core/workflows/pr-branch.md": "c87db7ac8c28be1b",
   "gsd-core/workflows/profile-user.md": "14263db831230142",
   "gsd-core/workflows/progress.md": "893aa3c36983f74b",
-  "gsd-core/workflows/quick.md": "5790ceb09aa685be",
+  "gsd-core/workflows/quick.md": "069fe37d083a94a3",
   "gsd-core/workflows/reapply-patches.md": "39050f72601aec89",
   "gsd-core/workflows/remove-phase.md": "df9a45f0b1880999",
   "gsd-core/workflows/remove-workspace.md": "a7ca66db6b7c132c",
diff --git a/tests/fixtures/golden-install-parity/claude.json b/tests/fixtures/golden-install-parity/claude.json
index 2be2052f2..2fb838fa0 100644
--- a/tests/fixtures/golden-install-parity/claude.json
+++ b/tests/fixtures/golden-install-parity/claude.json
@@ -93,7 +93,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "90e2c9bc577278fd",
+  "gsd-core/references/model-profiles.md": "c249163663bbea53",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -206,13 +206,13 @@
   "gsd-core/workflows/autonomous.md": "722397c04272dfaa",
   "gsd-core/workflows/check-todos.md": "6c2a43d1d3e86589",
   "gsd-core/workflows/cleanup.md": "0daa2f2720c111f1",
-  "gsd-core/workflows/code-review-fix.md": "adb62c695b39ef61",
-  "gsd-core/workflows/code-review.md": "6c40b95e799907d0",
+  "gsd-core/workflows/code-review-fix.md": "722416b71b31c5fc",
+  "gsd-core/workflows/code-review.md": "506412604f767adc",
   "gsd-core/workflows/complete-milestone.md": "dcf1182398efb1ca",
   "gsd-core/workflows/debug.md": "a9397fd35cca2240",
   "gsd-core/workflows/diagnose-issues.md": "75ffc381ac3059ff",
   "gsd-core/workflows/discovery-phase.md": "6161c60d752d0058",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "46876f83547db40a",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "a8cd1db094fefd35",
   "gsd-core/workflows/discuss-phase-power.md": "290c0d83d783f9f6",
   "gsd-core/workflows/discuss-phase.md": "df56c8cd170b2150",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "db488d74d080c653",
@@ -278,7 +278,7 @@
   "gsd-core/workflows/pr-branch.md": "ab157cd8e49621dd",
   "gsd-core/workflows/profile-user.md": "ff3820a27731ceb8",
   "gsd-core/workflows/progress.md": "bd1ecf9207331bda",
-  "gsd-core/workflows/quick.md": "da83b1a15b7f1bf7",
+  "gsd-core/workflows/quick.md": "3363bdfefd403686",
   "gsd-core/workflows/reapply-patches.md": "ba9406b60f2c4041",
   "gsd-core/workflows/remove-phase.md": "ada8a0546c686483",
   "gsd-core/workflows/remove-workspace.md": "f3ab3a88a7e9e1ed",
diff --git a/tests/fixtures/golden-install-parity/cline.json b/tests/fixtures/golden-install-parity/cline.json
index f3841bb20..2851df9ba 100644
--- a/tests/fixtures/golden-install-parity/cline.json
+++ b/tests/fixtures/golden-install-parity/cline.json
@@ -97,7 +97,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "eb144b83e31196b8",
+  "gsd-core/references/model-profiles.md": "1794ad3d9854129e",
   "gsd-core/references/mvp-concepts.md": "72f7e8b1f8ae7118",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -210,13 +210,13 @@
   "gsd-core/workflows/autonomous.md": "cc5217b1b2238a4c",
   "gsd-core/workflows/check-todos.md": "32fdf33f5dc8bdde",
   "gsd-core/workflows/cleanup.md": "b0ebfc48792b407b",
-  "gsd-core/workflows/code-review-fix.md": "b946fe7bcb303852",
-  "gsd-core/workflows/code-review.md": "0b24efcfa71a2ed2",
+  "gsd-core/workflows/code-review-fix.md": "e4549af672e74e6f",
+  "gsd-core/workflows/code-review.md": "a65e3e869508f89e",
   "gsd-core/workflows/complete-milestone.md": "c0808127038a8f86",
   "gsd-core/workflows/debug.md": "f42e8e3cbc298694",
   "gsd-core/workflows/diagnose-issues.md": "e616d0d730328d68",
   "gsd-core/workflows/discovery-phase.md": "3ba7cfb89fb1e761",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "89987fd183e0d552",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "9efcb2ef6a9245b3",
   "gsd-core/workflows/discuss-phase-power.md": "0841f7dc6e9a054a",
   "gsd-core/workflows/discuss-phase.md": "a290d5ee19607bb7",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "250de9aae90daebc",
@@ -282,7 +282,7 @@
   "gsd-core/workflows/pr-branch.md": "9923878a4f6a2d91",
   "gsd-core/workflows/profile-user.md": "26f74db0a7fcd268",
   "gsd-core/workflows/progress.md": "9f326d63afb4b76b",
-  "gsd-core/workflows/quick.md": "68a9dfcd53f0859f",
+  "gsd-core/workflows/quick.md": "2afc046e94daad0a",
   "gsd-core/workflows/reapply-patches.md": "eb4272145a117904",
   "gsd-core/workflows/remove-phase.md": "e336350f8113a328",
   "gsd-core/workflows/remove-workspace.md": "e685dfbd736dfd90",
diff --git a/tests/fixtures/golden-install-parity/codebuddy.json b/tests/fixtures/golden-install-parity/codebuddy.json
index df78da0b6..5ea53f832 100644
--- a/tests/fixtures/golden-install-parity/codebuddy.json
+++ b/tests/fixtures/golden-install-parity/codebuddy.json
@@ -165,7 +165,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "8484ad9799b7f680",
+  "gsd-core/references/model-profiles.md": "e067ad3df6770db1",
   "gsd-core/references/mvp-concepts.md": "72f7e8b1f8ae7118",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -278,13 +278,13 @@
   "gsd-core/workflows/autonomous.md": "7e5683728ef33707",
   "gsd-core/workflows/check-todos.md": "bdeaf43f9c61e0cc",
   "gsd-core/workflows/cleanup.md": "0daa2f2720c111f1",
-  "gsd-core/workflows/code-review-fix.md": "c323f7098b671bd6",
-  "gsd-core/workflows/code-review.md": "ad450c6ef8459dad",
+  "gsd-core/workflows/code-review-fix.md": "2e113d1f4350a075",
+  "gsd-core/workflows/code-review.md": "334c90c401f291f8",
   "gsd-core/workflows/complete-milestone.md": "c1f91b77f4ace7f2",
   "gsd-core/workflows/debug.md": "849d7e5b9c12dcae",
   "gsd-core/workflows/diagnose-issues.md": "77d98ac07c4a26ff",
   "gsd-core/workflows/discovery-phase.md": "3ba7cfb89fb1e761",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "1e229f6d21831d60",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "f5b765d33eba4f88",
   "gsd-core/workflows/discuss-phase-power.md": "0841f7dc6e9a054a",
   "gsd-core/workflows/discuss-phase.md": "02a5381c9a2173be",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "db488d74d080c653",
@@ -350,7 +350,7 @@
   "gsd-core/workflows/pr-branch.md": "c87db7ac8c28be1b",
   "gsd-core/workflows/profile-user.md": "4fa910d15dea5695",
   "gsd-core/workflows/progress.md": "893aa3c36983f74b",
-  "gsd-core/workflows/quick.md": "9033dbe58443af36",
+  "gsd-core/workflows/quick.md": "cc530299ba461539",
   "gsd-core/workflows/reapply-patches.md": "39050f72601aec89",
   "gsd-core/workflows/remove-phase.md": "df9a45f0b1880999",
   "gsd-core/workflows/remove-workspace.md": "a7ca66db6b7c132c",
diff --git a/tests/fixtures/golden-install-parity/codex.json b/tests/fixtures/golden-install-parity/codex.json
index a6e01217e..4d07225df 100644
--- a/tests/fixtures/golden-install-parity/codex.json
+++ b/tests/fixtures/golden-install-parity/codex.json
@@ -129,7 +129,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "86e81f17c2f23fff",
+  "gsd-core/references/model-profiles.md": "bd90862f68007f2e",
   "gsd-core/references/mvp-concepts.md": "23201c8118fb074a",
   "gsd-core/references/phase-argument-parsing.md": "531176f66da49c98",
   "gsd-core/references/planner-antipatterns.md": "2459c40bfc8a0ea8",
@@ -242,13 +242,13 @@
   "gsd-core/workflows/autonomous.md": "92f08626d4aea668",
   "gsd-core/workflows/check-todos.md": "b2b103e8638e760a",
   "gsd-core/workflows/cleanup.md": "5d48d64664222a3e",
-  "gsd-core/workflows/code-review-fix.md": "3ff5f7eac2269ca3",
-  "gsd-core/workflows/code-review.md": "82858ab037b9176e",
+  "gsd-core/workflows/code-review-fix.md": "ae7f9c6b39a23c12",
+  "gsd-core/workflows/code-review.md": "eadada9e0a89adf2",
   "gsd-core/workflows/complete-milestone.md": "017df7443bd08da5",
   "gsd-core/workflows/debug.md": "cc7b2d2fd4307a78",
   "gsd-core/workflows/diagnose-issues.md": "e38bb21d06dff077",
   "gsd-core/workflows/discovery-phase.md": "71a4b78ff876a854",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "f23abfe76623ed63",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "0d936ec25299917c",
   "gsd-core/workflows/discuss-phase-power.md": "3f8b83dc6be2e9d5",
   "gsd-core/workflows/discuss-phase.md": "7c9df6656b81fda9",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "db488d74d080c653",
@@ -314,7 +314,7 @@
   "gsd-core/workflows/pr-branch.md": "d13e1cc81de40896",
   "gsd-core/workflows/profile-user.md": "05828c8cc61ef384",
   "gsd-core/workflows/progress.md": "7bedc431bb55edb8",
-  "gsd-core/workflows/quick.md": "3e7686705da2af19",
+  "gsd-core/workflows/quick.md": "62b9e138dc70b479",
   "gsd-core/workflows/reapply-patches.md": "26297b84736e66a4",
   "gsd-core/workflows/remove-phase.md": "9ee0fddd11a0d9d4",
   "gsd-core/workflows/remove-workspace.md": "19d7465aaa50cb62",
diff --git a/tests/fixtures/golden-install-parity/copilot.json b/tests/fixtures/golden-install-parity/copilot.json
index 060f81cd9..68c1c364d 100644
--- a/tests/fixtures/golden-install-parity/copilot.json
+++ b/tests/fixtures/golden-install-parity/copilot.json
@@ -95,7 +95,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "1d392e37a746742a",
-  "gsd-core/references/model-profiles.md": "d6ed560db6357ad2",
+  "gsd-core/references/model-profiles.md": "6568ca29b6ee00d8",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "2459c40bfc8a0ea8",
@@ -208,13 +208,13 @@
   "gsd-core/workflows/autonomous.md": "dd972ddde9663295",
   "gsd-core/workflows/check-todos.md": "be9b50b5f28d7504",
   "gsd-core/workflows/cleanup.md": "8233b05ebf011bec",
-  "gsd-core/workflows/code-review-fix.md": "ab2b467b41522c10",
-  "gsd-core/workflows/code-review.md": "1bbbe61f45fccf4c",
+  "gsd-core/workflows/code-review-fix.md": "fda53892ae4b17fc",
+  "gsd-core/workflows/code-review.md": "f1c045ec4d33abc8",
   "gsd-core/workflows/complete-milestone.md": "470cf39261400ee2",
   "gsd-core/workflows/debug.md": "36cb536be452d79e",
   "gsd-core/workflows/diagnose-issues.md": "42acbe2a43fc886e",
   "gsd-core/workflows/discovery-phase.md": "8e99da61fb2b7074",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "ab2d26b194805ac1",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "ab0c432b84038681",
   "gsd-core/workflows/discuss-phase-power.md": "5c0d1ca6abda0383",
   "gsd-core/workflows/discuss-phase.md": "31a79ea11c1cdd5f",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "654cdaf1138d5e27",
@@ -280,7 +280,7 @@
   "gsd-core/workflows/pr-branch.md": "2833905f119b5722",
   "gsd-core/workflows/profile-user.md": "5cc032206c99ef71",
   "gsd-core/workflows/progress.md": "6b9a84a43dc55af5",
-  "gsd-core/workflows/quick.md": "7ddfe17f048541ec",
+  "gsd-core/workflows/quick.md": "eb68ea8748546331",
   "gsd-core/workflows/reapply-patches.md": "8fd59e24b486f180",
   "gsd-core/workflows/remove-phase.md": "e262654e319d1bc4",
   "gsd-core/workflows/remove-workspace.md": "ceddfeef5f2d6754",
diff --git a/tests/fixtures/golden-install-parity/cursor.json b/tests/fixtures/golden-install-parity/cursor.json
index c618c1846..4ed920084 100644
--- a/tests/fixtures/golden-install-parity/cursor.json
+++ b/tests/fixtures/golden-install-parity/cursor.json
@@ -165,7 +165,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "f4c013e700c52b08",
+  "gsd-core/references/model-profiles.md": "5452b2e19e19f77e",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e562947d1bf5c5a4",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -278,13 +278,13 @@
   "gsd-core/workflows/autonomous.md": "4b20eda9a0b587ce",
   "gsd-core/workflows/check-todos.md": "1a67337d1630848f",
   "gsd-core/workflows/cleanup.md": "db47963f103c2748",
-  "gsd-core/workflows/code-review-fix.md": "49e7f024c551b3a5",
-  "gsd-core/workflows/code-review.md": "6a9fd2996a6b600e",
+  "gsd-core/workflows/code-review-fix.md": "c57af378033b1b58",
+  "gsd-core/workflows/code-review.md": "32c37bcbec8b8698",
   "gsd-core/workflows/complete-milestone.md": "1400a4856f592f3e",
   "gsd-core/workflows/debug.md": "a73d8018986131ba",
   "gsd-core/workflows/diagnose-issues.md": "cd582747131726e3",
   "gsd-core/workflows/discovery-phase.md": "7dcf150998559c11",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "373788c6b7eab272",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "c25c6a6c633d71b6",
   "gsd-core/workflows/discuss-phase-power.md": "290c0d83d783f9f6",
   "gsd-core/workflows/discuss-phase.md": "14688ff19ce2184c",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "30612a2de153cb5b",
@@ -350,7 +350,7 @@
   "gsd-core/workflows/pr-branch.md": "c67d90c65da47168",
   "gsd-core/workflows/profile-user.md": "8c943983241260b5",
   "gsd-core/workflows/progress.md": "65aabee5e8a6dd82",
-  "gsd-core/workflows/quick.md": "762256cf6d177c06",
+  "gsd-core/workflows/quick.md": "32a71f62041c8510",
   "gsd-core/workflows/reapply-patches.md": "ba9406b60f2c4041",
   "gsd-core/workflows/remove-phase.md": "ada8a0546c686483",
   "gsd-core/workflows/remove-workspace.md": "433affcd1a200826",
diff --git a/tests/fixtures/golden-install-parity/hermes.json b/tests/fixtures/golden-install-parity/hermes.json
index f8013837a..dd711e18b 100644
--- a/tests/fixtures/golden-install-parity/hermes.json
+++ b/tests/fixtures/golden-install-parity/hermes.json
@@ -94,7 +94,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "8472d453a325cc1b",
+  "gsd-core/references/model-profiles.md": "6012c3b53473f04f",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -207,13 +207,13 @@
   "gsd-core/workflows/autonomous.md": "dd572ca89862e5ec",
   "gsd-core/workflows/check-todos.md": "ea9a303c48a5d752",
   "gsd-core/workflows/cleanup.md": "6c488059fc152a49",
-  "gsd-core/workflows/code-review-fix.md": "04b143a963067236",
-  "gsd-core/workflows/code-review.md": "ff28724fc216972c",
+  "gsd-core/workflows/code-review-fix.md": "e829d3baf9901b54",
+  "gsd-core/workflows/code-review.md": "50a05ab8957bd05f",
   "gsd-core/workflows/complete-milestone.md": "f1866541148dc291",
   "gsd-core/workflows/debug.md": "15cf6999e85dcc8c",
   "gsd-core/workflows/diagnose-issues.md": "16f2d2a85335641f",
   "gsd-core/workflows/discovery-phase.md": "6161c60d752d0058",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "db60ec68b59a40eb",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "3a1e215890d2b3f4",
   "gsd-core/workflows/discuss-phase-power.md": "290c0d83d783f9f6",
   "gsd-core/workflows/discuss-phase.md": "0aa052ae4ee70bf6",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "536e2fa842f1bc95",
@@ -279,7 +279,7 @@
   "gsd-core/workflows/pr-branch.md": "ecabd55e4eabf229",
   "gsd-core/workflows/profile-user.md": "de5030437226cf2c",
   "gsd-core/workflows/progress.md": "f18db000584d9cb1",
-  "gsd-core/workflows/quick.md": "5044ce4e7512e174",
+  "gsd-core/workflows/quick.md": "e7a395b9e7786b56",
   "gsd-core/workflows/reapply-patches.md": "158083a310859594",
   "gsd-core/workflows/remove-phase.md": "fce799aae3ab2715",
   "gsd-core/workflows/remove-workspace.md": "8facde381657dd71",
diff --git a/tests/fixtures/golden-install-parity/kilo.json b/tests/fixtures/golden-install-parity/kilo.json
index f3596be07..501c826ac 100644
--- a/tests/fixtures/golden-install-parity/kilo.json
+++ b/tests/fixtures/golden-install-parity/kilo.json
@@ -165,7 +165,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "d6ed560db6357ad2",
+  "gsd-core/references/model-profiles.md": "6568ca29b6ee00d8",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "2459c40bfc8a0ea8",
@@ -278,13 +278,13 @@
   "gsd-core/workflows/autonomous.md": "73f429f7472c9949",
   "gsd-core/workflows/check-todos.md": "ed4b4eb12be222d7",
   "gsd-core/workflows/cleanup.md": "c5f1bf186395d67d",
-  "gsd-core/workflows/code-review-fix.md": "adb62c695b39ef61",
-  "gsd-core/workflows/code-review.md": "6c40b95e799907d0",
+  "gsd-core/workflows/code-review-fix.md": "722416b71b31c5fc",
+  "gsd-core/workflows/code-review.md": "506412604f767adc",
   "gsd-core/workflows/complete-milestone.md": "59753bf44d4300da",
   "gsd-core/workflows/debug.md": "a72d830ac3df74aa",
   "gsd-core/workflows/diagnose-issues.md": "210b5b313e8a559a",
   "gsd-core/workflows/discovery-phase.md": "ca7b2be46e59e862",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "36f7edcb666745f2",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "3ef1df313e715387",
   "gsd-core/workflows/discuss-phase-power.md": "5c0d1ca6abda0383",
   "gsd-core/workflows/discuss-phase.md": "bd4b26ba168bb51f",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "f8ae26ba4e07672b",
@@ -350,7 +350,7 @@
   "gsd-core/workflows/pr-branch.md": "ab157cd8e49621dd",
   "gsd-core/workflows/profile-user.md": "203ebe3f8f3876a8",
   "gsd-core/workflows/progress.md": "9381c59676ccb937",
-  "gsd-core/workflows/quick.md": "fd7461e5a92fe450",
+  "gsd-core/workflows/quick.md": "e71c92cf0463a461",
   "gsd-core/workflows/reapply-patches.md": "becf9728cdb124c4",
   "gsd-core/workflows/remove-phase.md": "ada8a0546c686483",
   "gsd-core/workflows/remove-workspace.md": "fc83f362a2d0a1b7",
diff --git a/tests/fixtures/golden-install-parity/kimi.json b/tests/fixtures/golden-install-parity/kimi.json
index 2b3f8fa6b..65d63af8a 100644
--- a/tests/fixtures/golden-install-parity/kimi.json
+++ b/tests/fixtures/golden-install-parity/kimi.json
@@ -130,7 +130,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "8484ad9799b7f680",
+  "gsd-core/references/model-profiles.md": "e067ad3df6770db1",
   "gsd-core/references/mvp-concepts.md": "72f7e8b1f8ae7118",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -243,13 +243,13 @@
   "gsd-core/workflows/autonomous.md": "7e5683728ef33707",
   "gsd-core/workflows/check-todos.md": "bdeaf43f9c61e0cc",
   "gsd-core/workflows/cleanup.md": "0daa2f2720c111f1",
-  "gsd-core/workflows/code-review-fix.md": "c323f7098b671bd6",
-  "gsd-core/workflows/code-review.md": "ad450c6ef8459dad",
+  "gsd-core/workflows/code-review-fix.md": "2e113d1f4350a075",
+  "gsd-core/workflows/code-review.md": "334c90c401f291f8",
   "gsd-core/workflows/complete-milestone.md": "c1f91b77f4ace7f2",
   "gsd-core/workflows/debug.md": "849d7e5b9c12dcae",
   "gsd-core/workflows/diagnose-issues.md": "67c058fc7ae6026b",
   "gsd-core/workflows/discovery-phase.md": "3ba7cfb89fb1e761",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "1e229f6d21831d60",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "f5b765d33eba4f88",
   "gsd-core/workflows/discuss-phase-power.md": "0841f7dc6e9a054a",
   "gsd-core/workflows/discuss-phase.md": "0c0465ba668adb33",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "db488d74d080c653",
@@ -315,7 +315,7 @@
   "gsd-core/workflows/pr-branch.md": "c87db7ac8c28be1b",
   "gsd-core/workflows/profile-user.md": "5abfae83739fa978",
   "gsd-core/workflows/progress.md": "893aa3c36983f74b",
-  "gsd-core/workflows/quick.md": "e265e01cfe117215",
+  "gsd-core/workflows/quick.md": "09d88dd1c0b3e03a",
   "gsd-core/workflows/reapply-patches.md": "39050f72601aec89",
   "gsd-core/workflows/remove-phase.md": "df9a45f0b1880999",
   "gsd-core/workflows/remove-workspace.md": "a7ca66db6b7c132c",
diff --git a/tests/fixtures/golden-install-parity/opencode.json b/tests/fixtures/golden-install-parity/opencode.json
index ed0c3e395..83a7124d5 100644
--- a/tests/fixtures/golden-install-parity/opencode.json
+++ b/tests/fixtures/golden-install-parity/opencode.json
@@ -165,7 +165,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "858c16730df68ac2",
-  "gsd-core/references/model-profiles.md": "d6ed560db6357ad2",
+  "gsd-core/references/model-profiles.md": "6568ca29b6ee00d8",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "2459c40bfc8a0ea8",
@@ -278,13 +278,13 @@
   "gsd-core/workflows/autonomous.md": "6cb0c014f5f56965",
   "gsd-core/workflows/check-todos.md": "6526b64ee88c7d2e",
   "gsd-core/workflows/cleanup.md": "94d771d26f62dc86",
-  "gsd-core/workflows/code-review-fix.md": "5d97b960da4fef73",
-  "gsd-core/workflows/code-review.md": "aec8ef4de1829607",
+  "gsd-core/workflows/code-review-fix.md": "adb9388bb157610c",
+  "gsd-core/workflows/code-review.md": "ae6bcbd1575aeec4",
   "gsd-core/workflows/complete-milestone.md": "614299b2c08e66c3",
   "gsd-core/workflows/debug.md": "9d4a8afc8d36be93",
   "gsd-core/workflows/diagnose-issues.md": "2971c699d52f1b85",
   "gsd-core/workflows/discovery-phase.md": "724408336596c50c",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "310b08dc31710cbc",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "92e43cd12200c610",
   "gsd-core/workflows/discuss-phase-power.md": "5c0d1ca6abda0383",
   "gsd-core/workflows/discuss-phase.md": "3a62a8d4c374c69f",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "83ca3ea4fac785af",
@@ -350,7 +350,7 @@
   "gsd-core/workflows/pr-branch.md": "929b7cb0c99c7b9e",
   "gsd-core/workflows/profile-user.md": "248d59a31948e0ed",
   "gsd-core/workflows/progress.md": "8fc3404087f50b95",
-  "gsd-core/workflows/quick.md": "10cc8ddd4bc3f0ee",
+  "gsd-core/workflows/quick.md": "9bdccb7c6a5530c9",
   "gsd-core/workflows/reapply-patches.md": "a0e9b53f90abceb2",
   "gsd-core/workflows/remove-phase.md": "dea4661e8f89596f",
   "gsd-core/workflows/remove-workspace.md": "446847e71aa52504",
diff --git a/tests/fixtures/golden-install-parity/qwen.json b/tests/fixtures/golden-install-parity/qwen.json
index 6f24ee22f..71a9ad563 100644
--- a/tests/fixtures/golden-install-parity/qwen.json
+++ b/tests/fixtures/golden-install-parity/qwen.json
@@ -94,7 +94,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "cc1efc2942164744",
+  "gsd-core/references/model-profiles.md": "0b7e06ed2e4abac8",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -207,13 +207,13 @@
   "gsd-core/workflows/autonomous.md": "3014ff90115f0daf",
   "gsd-core/workflows/check-todos.md": "ec8c22920f6b2df1",
   "gsd-core/workflows/cleanup.md": "6a18b165752e3087",
-  "gsd-core/workflows/code-review-fix.md": "e14afce87cf0d420",
-  "gsd-core/workflows/code-review.md": "d6d385b6dadae5a0",
+  "gsd-core/workflows/code-review-fix.md": "f3725ae9d685bed2",
+  "gsd-core/workflows/code-review.md": "29125604bed2c467",
   "gsd-core/workflows/complete-milestone.md": "40085d32b15805c8",
   "gsd-core/workflows/debug.md": "c23d067580b09f63",
   "gsd-core/workflows/diagnose-issues.md": "652ae26975f82242",
   "gsd-core/workflows/discovery-phase.md": "6161c60d752d0058",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "3865afc23e9cd46a",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "18712f78bb960ec8",
   "gsd-core/workflows/discuss-phase-power.md": "290c0d83d783f9f6",
   "gsd-core/workflows/discuss-phase.md": "8644b72386a51241",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "3102430dfad9c012",
@@ -279,7 +279,7 @@
   "gsd-core/workflows/pr-branch.md": "cef0f65b16d500b4",
   "gsd-core/workflows/profile-user.md": "263c0693563d98da",
   "gsd-core/workflows/progress.md": "3b1b2142a74af85c",
-  "gsd-core/workflows/quick.md": "0a9a7dacc73f8e53",
+  "gsd-core/workflows/quick.md": "bb9a4a145a7edc36",
   "gsd-core/workflows/reapply-patches.md": "de0ee8acfe7245b2",
   "gsd-core/workflows/remove-phase.md": "e8ae4fbbfac700f0",
   "gsd-core/workflows/remove-workspace.md": "4ac64de862dc650e",
diff --git a/tests/fixtures/golden-install-parity/trae.json b/tests/fixtures/golden-install-parity/trae.json
index 7c07b71ab..8342ab964 100644
--- a/tests/fixtures/golden-install-parity/trae.json
+++ b/tests/fixtures/golden-install-parity/trae.json
@@ -94,7 +94,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "41b0af6f5f77af81",
+  "gsd-core/references/model-profiles.md": "b4527b0f255d193f",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e562947d1bf5c5a4",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -207,13 +207,13 @@
   "gsd-core/workflows/autonomous.md": "c482645c5d1ead46",
   "gsd-core/workflows/check-todos.md": "0dda8236355e8c9c",
   "gsd-core/workflows/cleanup.md": "82f65f5214ecd748",
-  "gsd-core/workflows/code-review-fix.md": "959a65773b325ed2",
-  "gsd-core/workflows/code-review.md": "b31bbd7dbe5ed303",
+  "gsd-core/workflows/code-review-fix.md": "f2761f7f8c4a5674",
+  "gsd-core/workflows/code-review.md": "47663a2922756c5e",
   "gsd-core/workflows/complete-milestone.md": "6e918b72bd885426",
   "gsd-core/workflows/debug.md": "197d3642a6704de5",
   "gsd-core/workflows/diagnose-issues.md": "9274b11a3db98c65",
   "gsd-core/workflows/discovery-phase.md": "b32b6197b66c9a13",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "3d05b08eae75c7bd",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "e376b1cf29379df4",
   "gsd-core/workflows/discuss-phase-power.md": "290c0d83d783f9f6",
   "gsd-core/workflows/discuss-phase.md": "4509657816c5566a",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "c9cd7db62e76ebcb",
@@ -279,7 +279,7 @@
   "gsd-core/workflows/pr-branch.md": "79fd55b88ea2db9c",
   "gsd-core/workflows/profile-user.md": "672821e6b1266645",
   "gsd-core/workflows/progress.md": "94768f835b0b8908",
-  "gsd-core/workflows/quick.md": "9bbf907e39688638",
+  "gsd-core/workflows/quick.md": "a568015cccb53615",
   "gsd-core/workflows/reapply-patches.md": "21b38c374f19fd78",
   "gsd-core/workflows/remove-phase.md": "a46c2fe853bf4e86",
   "gsd-core/workflows/remove-workspace.md": "ae0e1c6d4438d663",
diff --git a/tests/fixtures/golden-install-parity/windsurf.json b/tests/fixtures/golden-install-parity/windsurf.json
index 4993ab62d..a2d03a845 100644
--- a/tests/fixtures/golden-install-parity/windsurf.json
+++ b/tests/fixtures/golden-install-parity/windsurf.json
@@ -94,7 +94,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "b3ac5dc094bce1dc",
+  "gsd-core/references/model-profiles.md": "09aa53e3f1764a41",
   "gsd-core/references/mvp-concepts.md": "3464783eaaef5c10",
   "gsd-core/references/phase-argument-parsing.md": "e562947d1bf5c5a4",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -207,13 +207,13 @@
   "gsd-core/workflows/autonomous.md": "fe7bb7c978f305a2",
   "gsd-core/workflows/check-todos.md": "afc840fceb07bf99",
   "gsd-core/workflows/cleanup.md": "93c14107979a4428",
-  "gsd-core/workflows/code-review-fix.md": "9b2de93a6087774d",
-  "gsd-core/workflows/code-review.md": "2f0ebfb7a2e33764",
+  "gsd-core/workflows/code-review-fix.md": "b99b1f20bb27c291",
+  "gsd-core/workflows/code-review.md": "faa87faf07ae765a",
   "gsd-core/workflows/complete-milestone.md": "f463bf4e86ac26f6",
   "gsd-core/workflows/debug.md": "52243eb936a43150",
   "gsd-core/workflows/diagnose-issues.md": "447072aa72385271",
   "gsd-core/workflows/discovery-phase.md": "7dcf150998559c11",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "f57000d5c5fb178a",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "b091b3d3e580dd29",
   "gsd-core/workflows/discuss-phase-power.md": "290c0d83d783f9f6",
   "gsd-core/workflows/discuss-phase.md": "ce4e6abce9cb2d4e",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "cb49f485c4a1f09e",
@@ -279,7 +279,7 @@
   "gsd-core/workflows/pr-branch.md": "acd59f915d018ad4",
   "gsd-core/workflows/profile-user.md": "c4313672b81b5bcd",
   "gsd-core/workflows/progress.md": "18813a345bd2343a",
-  "gsd-core/workflows/quick.md": "3acd391cc0c3813a",
+  "gsd-core/workflows/quick.md": "b7813e1810c683e1",
   "gsd-core/workflows/reapply-patches.md": "d449a23d3acf6379",
   "gsd-core/workflows/remove-phase.md": "e7a6af429b36e77b",
   "gsd-core/workflows/remove-workspace.md": "b5e60fbb33b3e33a",
diff --git a/tests/fixtures/golden-install-parity/zcode.json b/tests/fixtures/golden-install-parity/zcode.json
index 5c044e9eb..ed40c52c3 100644
--- a/tests/fixtures/golden-install-parity/zcode.json
+++ b/tests/fixtures/golden-install-parity/zcode.json
@@ -165,7 +165,7 @@
   "gsd-core/references/loop-hook-dispatch.md": "32e5dfb4dba76987",
   "gsd-core/references/mandatory-initial-read.md": "fe59abce693717cf",
   "gsd-core/references/model-profile-resolution.md": "f32bb05102839767",
-  "gsd-core/references/model-profiles.md": "8484ad9799b7f680",
+  "gsd-core/references/model-profiles.md": "e067ad3df6770db1",
   "gsd-core/references/mvp-concepts.md": "72f7e8b1f8ae7118",
   "gsd-core/references/phase-argument-parsing.md": "e5bbb985f3bc3e34",
   "gsd-core/references/planner-antipatterns.md": "7ed54ec1e2cc54ac",
@@ -278,13 +278,13 @@
   "gsd-core/workflows/autonomous.md": "7e5683728ef33707",
   "gsd-core/workflows/check-todos.md": "bdeaf43f9c61e0cc",
   "gsd-core/workflows/cleanup.md": "0daa2f2720c111f1",
-  "gsd-core/workflows/code-review-fix.md": "c323f7098b671bd6",
-  "gsd-core/workflows/code-review.md": "ad450c6ef8459dad",
+  "gsd-core/workflows/code-review-fix.md": "2e113d1f4350a075",
+  "gsd-core/workflows/code-review.md": "334c90c401f291f8",
   "gsd-core/workflows/complete-milestone.md": "c1f91b77f4ace7f2",
   "gsd-core/workflows/debug.md": "849d7e5b9c12dcae",
   "gsd-core/workflows/diagnose-issues.md": "aa8d787db8f3c46c",
   "gsd-core/workflows/discovery-phase.md": "3ba7cfb89fb1e761",
-  "gsd-core/workflows/discuss-phase-assumptions.md": "1e229f6d21831d60",
+  "gsd-core/workflows/discuss-phase-assumptions.md": "f5b765d33eba4f88",
   "gsd-core/workflows/discuss-phase-power.md": "0841f7dc6e9a054a",
   "gsd-core/workflows/discuss-phase.md": "d0a67b6f77b4d339",
   "gsd-core/workflows/discuss-phase/modes/advisor.md": "db488d74d080c653",
@@ -350,7 +350,7 @@
   "gsd-core/workflows/pr-branch.md": "c87db7ac8c28be1b",
   "gsd-core/workflows/profile-user.md": "e23bea0a69c0bb4b",
   "gsd-core/workflows/progress.md": "893aa3c36983f74b",
-  "gsd-core/workflows/quick.md": "5747c2d8a37affbb",
+  "gsd-core/workflows/quick.md": "12917fdc9a624a0c",
   "gsd-core/workflows/reapply-patches.md": "39050f72601aec89",
   "gsd-core/workflows/remove-phase.md": "df9a45f0b1880999",
   "gsd-core/workflows/remove-workspace.md": "a7ca66db6b7c132c",
diff --git a/tests/loop-render-hooks.test.cjs b/tests/loop-render-hooks.test.cjs
index dc82b982a..ef91f7313 100644
--- a/tests/loop-render-hooks.test.cjs
+++ b/tests/loop-render-hooks.test.cjs
@@ -1039,79 +1039,136 @@ describe('Phase 4 regression: capabilityStatesById gates on active (not enabled)
   });
 });
 
-// ─── ADR-1244 D2 fail-closed gate injection ────────────────────────────────────
+// ─── ADR-1244 D2: load-failed capability gates FAIL OPEN with a loud warning (#2009) ──
 
-describe('ADR-1244 D2: fail-closed gate injection for skipped overlay caps with gates', () => {
-  // Verifies that cmdLoopRenderHooks injects a BLOCKING synthetic gate at the
-  // declared point when an overlay capability that declares a gate is skipped at
-  // load time due to an incompatible engines.gsd version constraint.
-  //
-  // Fixture: overlay cap declares a gate at execute:wave:post with engines.gsd: ">=99.0.0"
-  // → loadRegistry skips it → records it in _overlay.blockedGates
-  // → cmdLoopRenderHooks injects a blocking=true, onError=halt gate at execute:wave:post
+describe('ADR-1244 D2: load-failed capability gates fail OPEN with a loud warning (#2009)', () => {
+  // Decision (#2009): a capability that fails to LOAD must not block the loop.
+  // cmdLoopRenderHooks injects NO gate (the loop proceeds — fail open) and emits a
+  // loud warning naming the load reason and the exact `gsd capability remove <id>`
+  // remediation, both to STDERR (the channel host workflows actually surface) and
+  // in the envelope's `warnings` array. Previously it injected a blocking=true,
+  // onError=halt gate that halted every declared point project-wide.
 
-  test('skipped gate-kind overlay cap → BLOCKING synthetic gate at its declared point', (t) => {
-    const overlayHome = fs.mkdtempSync(path.join(os.tmpdir(), 'loop-fail-closed-'));
-    t.after(() => cleanup(overlayHome));
-
-    // Write an overlay capability that:
-    // - declares a gate at execute:wave:post
-    // - has engines.gsd: ">=99.0.0" (incompatible → will be skipped at load)
-    const capId = 'fail-closed-gate-cap';
+  // Helper: write an overlay cap with an incompatible engines.gsd (→ skipped at load)
+  // that declares gate(s) at the given point(s). `capId` may be an invalid id to
+  // exercise the sanitization path.
+  function writeSkippedGateCap(overlayHome, capId, gatePoints) {
     const capDir = path.join(overlayHome, '.gsd', 'capabilities', capId);
     fs.mkdirSync(capDir, { recursive: true });
     const capManifest = {
       id: capId,
       role: 'feature',
       version: '1.0.0',
-      title: 'Fail Closed Gate Cap',
-      description: 'ADR-1244 D2 fail-closed wiring test',
+      title: 'Load-Failed Gate Cap',
+      description: 'ADR-1244 D2 fail-open wiring test',
       tier: 'standard',
       requires: [],
-      engines: { gsd: '>=99.0.0' },  // intentionally incompatible → always skipped
+      engines: { gsd: '>=99.0.0' },  // intentionally incompatible → always skipped at load
       runtimeCompat: { supported: ['*'], unsupported: [] },
       skills: [], agents: [], hooks: [], config: {}, steps: [], contributions: [],
-      gates: [{ point: 'execute:wave:post', check: 'always-pass', blocking: true, onError: 'halt' }],
+      gates: gatePoints.map((point) => ({ point, check: { query: 'always-pass' }, blocking: true, onError: 'halt' })),
     };
     fs.writeFileSync(path.join(capDir, 'capability.json'), JSON.stringify(capManifest), 'utf8');
+  }
 
-    // Invoke gsd-tools via subprocess so stdout is the real fd-1 (io.cjs writes via writeSync).
-    // Set GSD_HOME to the overlay home so loadRegistry picks up the incompatible cap.
+  function renderHooks(overlayHome, point, extraArgs = []) {
     const result = spawnSync(
       process.execPath,
-      [GSD_TOOLS, 'loop', 'render-hooks', 'execute:wave:post', '--cwd', overlayHome],
-      {
-        cwd: ROOT,
-        encoding: 'utf8',
-        env: { ...process.env, GSD_HOME: overlayHome },
-      },
+      [GSD_TOOLS, 'loop', 'render-hooks', point, '--cwd', overlayHome, ...extraArgs],
+      { cwd: ROOT, encoding: 'utf8', env: { ...process.env, GSD_HOME: overlayHome } },
     );
+    assert.strictEqual(result.status, 0, `Expected exit 0 at ${point}. stderr: ` + (result.stderr || ''));
+    return result;
+  }
 
-    assert.strictEqual(result.status, 0, 'Expected exit 0. stderr: ' + (result.stderr || ''));
-
-    let envelope;
+  function parseEnvelope(result) {
     try {
-      envelope = JSON.parse(result.stdout.trim());
+      return JSON.parse(result.stdout.trim());
     } catch {
       assert.fail('loop render-hooks output must be valid JSON; got: ' + result.stdout.slice(0, 300));
     }
+  }
 
-    // The synthetic blocking gate must be present in activeHooks
-    const syntheticGate = Array.isArray(envelope.activeHooks)
-      ? envelope.activeHooks.find((h) => h.capId === capId && h.kind === 'gate')
+  test('load-failed gate-kind overlay cap → NO gate injected (fail open) + loud warning on stderr and in envelope', (t) => {
+    const overlayHome = fs.mkdtempSync(path.join(os.tmpdir(), 'loop-fail-open-'));
+    t.after(() => cleanup(overlayHome));
+
+    const capId = 'load-failed-gate-cap';
+    writeSkippedGateCap(overlayHome, capId, ['execute:wave:post']);
+
+    const result = renderHooks(overlayHome, 'execute:wave:post');
+    const envelope = parseEnvelope(result);
+
+    // AC2 / AC-a: fail OPEN — NO gate (blocking or otherwise) is injected for the
+    // load-failed cap, so the loop proceeds.
+    const anyGate = Array.isArray(envelope.activeHooks)
+      ? envelope.activeHooks.find((h) => h.capId === capId)
       : undefined;
-    assert.ok(
-      syntheticGate !== undefined,
-      `activeHooks must contain a synthetic gate attributed to ${capId} (fail-closed injection). ` +
-      'Got: ' + JSON.stringify(envelope.activeHooks),
+    assert.strictEqual(
+      anyGate, undefined,
+      'no hook must be injected for a load-failed cap (fail open). Got: ' + JSON.stringify(envelope.activeHooks),
     );
-    assert.strictEqual(syntheticGate.blocking, true, 'synthetic gate must be blocking=true');
-    assert.strictEqual(syntheticGate.onError, 'halt', 'synthetic gate must have onError=halt');
 
-    // The rendered markdown must also reference the gate cap
+    // AC-b: a loud warning is surfaced in the envelope `warnings` channel...
+    const warnEnv = (envelope.warnings || []).find((w) => w.includes(capId));
+    assert.ok(warnEnv, 'envelope.warnings must name the load-failed cap. Got: ' + JSON.stringify(envelope.warnings));
+    // AC1: ...carrying the exact remediation, and making clear the gate is not enforced.
     assert.ok(
-      typeof envelope.rendered === 'string' && envelope.rendered.includes(capId),
-      'rendered output must reference the fail-closed gate cap. Got: ' + envelope.rendered,
+      warnEnv.includes(`gsd capability remove ${capId}`),
+      'warning must include the `gsd capability remove <id>` remediation. Got: ' + warnEnv,
+    );
+    assert.match(warnEnv, /skipped|not enforced|failing open/i, 'warning must say the gate is not enforced. Got: ' + warnEnv);
+
+    // ...and ALSO to stderr (the channel host workflows actually see).
+    assert.ok(
+      result.stderr.includes(`gsd capability remove ${capId}`),
+      'stderr must carry the loud fail-open warning with remediation. Got: ' + result.stderr,
+    );
+  });
+
+  test('load-failed cap declaring gates at ship:pre AND verify:post → neither point blocks (project can ship & verify)', (t) => {
+    const overlayHome = fs.mkdtempSync(path.join(os.tmpdir(), 'loop-fail-open-2pt-'));
+    t.after(() => cleanup(overlayHome));
+
+    const capId = 'load-failed-two-point-cap';
+    writeSkippedGateCap(overlayHome, capId, ['ship:pre', 'verify:post']);
+
+    for (const point of ['ship:pre', 'verify:post']) {
+      const result = renderHooks(overlayHome, point);
+      const envelope = parseEnvelope(result);
+      const injected = envelope.activeHooks.find((h) => h.capId === capId);
+      assert.strictEqual(
+        injected, undefined,
+        `${point} must NOT inject any hook for a load-failed cap (fail open). Got: ` + JSON.stringify(envelope.activeHooks),
+      );
+      const warn = (envelope.warnings || []).find((w) => w.includes(`gsd capability remove ${capId}`));
+      assert.ok(warn, `${point} must surface a fail-open warning with remediation. Got: ` + JSON.stringify(envelope.warnings));
+    }
+  });
+
+  test('security: an invalid (non-kebab) capability id is withheld — no runnable remove command is rendered (#2009 review)', (t) => {
+    const overlayHome = fs.mkdtempSync(path.join(os.tmpdir(), 'loop-fail-open-evil-'));
+    t.after(() => cleanup(overlayHome));
+
+    // A directory name that is a valid POSIX filename but NOT a valid capability
+    // id, and contains a shell metacharacter. It must never appear inside a
+    // runnable `gsd capability remove <id>` command in the surfaced warning.
+    const evilId = 'Bad;Cap';
+    writeSkippedGateCap(overlayHome, evilId, ['ship:pre']);
+
+    const result = renderHooks(overlayHome, 'ship:pre');
+    const envelope = parseEnvelope(result);
+
+    const combined = (envelope.warnings || []).join('\n') + '\n' + result.stderr;
+    // The raw metacharacter id must not be embedded in a runnable remove command.
+    assert.ok(
+      !combined.includes(`gsd capability remove ${evilId}`),
+      'invalid capability id must NOT be placed in a runnable remove command. Got: ' + combined,
+    );
+    // A warning is still surfaced (fail-open is loud), using the withheld-id form.
+    assert.match(
+      combined, /invalid id \(withheld\)/,
+      'an invalid id must be reported via the withheld-id placeholder. Got: ' + combined,
     );
   });
 });
diff --git a/tests/model-resolver.test.cjs b/tests/model-resolver.test.cjs
index 3e2d06ddf..b902d5149 100644
--- a/tests/model-resolver.test.cjs
+++ b/tests/model-resolver.test.cjs
@@ -120,6 +120,36 @@ describe('resolveModelInternal', () => {
     assert.ok(typeof model === 'string' && model.length > 0);
   });
 
+  // #2072 acceptance: these two catalog agents' config MUST resolve — the bug was
+  // that the workflows never threaded the resolved value, not that the resolver
+  // ignored it. These assert the value the (now-threaded) spawns receive.
+  test('#2072: model_overrides applies to gsd-code-reviewer', () => {
+    writeConfig(tmpDir, { model_overrides: { 'gsd-code-reviewer': 'my-custom-model' } });
+    assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-code-reviewer'), 'my-custom-model');
+  });
+
+  test('#2072: model_overrides applies to gsd-assumptions-analyzer', () => {
+    writeConfig(tmpDir, { model_overrides: { 'gsd-assumptions-analyzer': 'my-custom-model' } });
+    assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-assumptions-analyzer'), 'my-custom-model');
+  });
+
+  test('#2072: models.verification tier applies to gsd-code-reviewer', () => {
+    writeConfig(tmpDir, { models: { verification: 'opus' } });
+    assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-code-reviewer'), 'opus');
+  });
+
+  test('#2072: models.discuss tier applies to gsd-assumptions-analyzer', () => {
+    writeConfig(tmpDir, { models: { discuss: 'opus' } });
+    assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-assumptions-analyzer'), 'opus');
+  });
+
+  test('#2072: model_overrides + models.execution apply to gsd-code-fixer', () => {
+    writeConfig(tmpDir, { model_overrides: { 'gsd-code-fixer': 'my-custom-model' } });
+    assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-code-fixer'), 'my-custom-model');
+    writeConfig(tmpDir, { models: { execution: 'opus' } });
+    assert.strictEqual(resolveModelInternal(tmpDir, 'gsd-code-fixer'), 'opus');
+  });
+
   test('runtime non-claude + model_profile_overrides for runtime tier', () => {
     writeConfig(tmpDir, {
       runtime: 'codex',
diff --git a/tests/model-routing-spawn-threading.test.cjs b/tests/model-routing-spawn-threading.test.cjs
new file mode 100644
index 000000000..bfa6a2ebc
--- /dev/null
+++ b/tests/model-routing-spawn-threading.test.cjs
@@ -0,0 +1,150 @@
+// allow-test-rule: source-text-is-the-product #2072
+// Workflow .md files ARE the deployed orchestration contract the runtime executes;
+// asserting that a spawn threads a resolved model= is asserting the deployed contract.
+
+'use strict';
+
+/**
+ * #2072 — model_overrides / models.<phaseType> were silently inert for
+ * gsd-assumptions-analyzer and gsd-code-reviewer on Claude: the resolver honored
+ * them, but the workflows spawned the agents with NO model= param, so the resolved
+ * value never reached the Agent tool and the agents inherited the session model.
+ *
+ * Fix contract: every spawn of these two catalog agents must thread a resolved
+ * model=, and the workflow must obtain that model (inline `resolve-model` for the
+ * single-agent workflows, or the `reviewer_model` field of the init.quick bundle).
+ */
+
+const { test, describe } = require('node:test');
+const assert = require('node:assert/strict');
+const fs = require('node:fs');
+const path = require('node:path');
+
+const WF = path.join(__dirname, '..', 'gsd-core', 'workflows');
+const read = (rel) => fs.readFileSync(path.join(WF, rel), 'utf-8');
+
+// Every .md under gsd-core/workflows (incl. nested steps/ and modes/).
+function allWorkflowMd() {
+  const out = [];
+  (function walk(dir, rel) {
+    for (const e of fs.readdirSync(dir, { withFileTypes: true })) {
+      if (e.isDirectory()) walk(path.join(dir, e.name), path.join(rel, e.name));
+      else if (e.name.endsWith('.md')) out.push(path.join(rel, e.name));
+    }
+  })(WF, '');
+  return out;
+}
+
+// Return the full text of every `Agent( … )` call in `content`, tracking string
+// state (triple- and single-double-quoted) and paren depth so a prompt body's own
+// parens/quotes don't end the call early. Order-independent: a call's params are
+// captured whether subagent_type= appears before or after the prompt.
+function agentCalls(content) {
+  const calls = [];
+  const re = /Agent\(/g;
+  let m;
+  while ((m = re.exec(content)) !== null) {
+    let i = m.index + m[0].length;
+    let depth = 1;
+    let tq = false; // inside """ … """
+    let sq = false; // inside " … "
+    while (i < content.length && depth > 0) {
+      if (tq) {
+        if (content.startsWith('"""', i)) { tq = false; i += 3; continue; }
+        i++; continue;
+      }
+      if (sq) {
+        if (content[i] === '\\') { i += 2; continue; }
+        if (content[i] === '"') { sq = false; }
+        i++; continue;
+      }
+      if (content.startsWith('"""', i)) { tq = true; i += 3; continue; }
+      if (content[i] === '"') { sq = true; i++; continue; }
+      if (content[i] === '(') { depth++; }
+      else if (content[i] === ')') { depth--; }
+      i++;
+    }
+    calls.push(content.slice(m.index, i));
+    re.lastIndex = i; // don't re-scan inside this call
+  }
+  return calls;
+}
+
+describe('#2072: routed-agent spawns thread the resolved model', () => {
+  test('discuss-phase-assumptions.md resolves + threads gsd-assumptions-analyzer model', () => {
+    const c = read('discuss-phase-assumptions.md');
+    assert.match(c, /resolve-model gsd-assumptions-analyzer/, 'must resolve the routed model');
+    assert.match(
+      c,
+      /subagent_type="gsd-assumptions-analyzer",\s*model="\{ANALYZER_MODEL\}"/,
+      'spawn must thread the resolved model=',
+    );
+  });
+
+  test('code-review.md resolves + threads gsd-code-reviewer model', () => {
+    const c = read('code-review.md');
+    assert.match(c, /resolve-model gsd-code-reviewer/);
+    assert.match(c, /subagent_type="gsd-code-reviewer",\s*model="\{REVIEWER_MODEL\}"/);
+  });
+
+  test('code-review-fix.md re-review resolves + threads gsd-code-reviewer model', () => {
+    const c = read('code-review-fix.md');
+    assert.match(c, /resolve-model gsd-code-reviewer/);
+    assert.match(c, /subagent_type="gsd-code-reviewer",\s*model="\{REVIEWER_MODEL\}"/);
+  });
+
+  test('quick.md review step threads gsd-code-reviewer own model (not executor_model)', () => {
+    const c = read('quick.md');
+    // reviewer_model comes from the init.quick bundle; the spawn must use it.
+    assert.match(c, /subagent_type="gsd-code-reviewer",\s*\n\s*model="\{reviewer_model\}"/);
+    assert.doesNotMatch(
+      c,
+      /subagent_type="gsd-code-reviewer",\s*\n\s*model="\{executor_model\}"/,
+      'reviewer must not reuse the executor model (own model_overrides would be ignored)',
+    );
+  });
+
+  test('code-review-fix.md threads gsd-code-fixer model at both fixer spawns', () => {
+    const c = read('code-review-fix.md');
+    assert.match(c, /resolve-model gsd-code-fixer/, 'must resolve the fixer model');
+    const fixerSpawns = c.match(/subagent_type="gsd-code-fixer", model="\{FIXER_MODEL\}"/g) || [];
+    assert.strictEqual(fixerSpawns.length, 2, 'both gsd-code-fixer spawns must thread FIXER_MODEL');
+  });
+
+  // Parity guard: EVERY spawn of the fixed routed agents across ALL workflows must
+  // carry a model= in its Agent(...) call, so a new silently-inert spawn cannot
+  // regress. Uses a quote/paren-aware scan of the WHOLE Agent(...) call, so it holds
+  // for single-line and multi-line calls, multiple spawns per file, and either param
+  // ordering (subagent_type= before OR after the prompt body).
+  test('no spawn of the fixed routed agents is missing a model= (parity guard)', () => {
+    const ROUTED = /subagent_type="(gsd-code-reviewer|gsd-assumptions-analyzer|gsd-code-fixer)"/;
+    const offenders = [];
+    for (const rel of allWorkflowMd()) {
+      for (const call of agentCalls(read(rel))) {
+        const routed = call.match(ROUTED);
+        if (routed && !/\bmodel\s*=/.test(call)) {
+          offenders.push(`${rel}: ${routed[1]} spawn missing model=`);
+        }
+      }
+    }
+    assert.deepEqual(offenders, [], `routed-agent spawn(s) missing model=:\n${offenders.join('\n')}`);
+  });
+
+  // The scanner itself must catch a prompt-first, un-threaded spawn (the exact blind
+  // spot a naive "params before prompt=" heuristic misses) — otherwise the guard
+  // above could pass vacuously.
+  test('parity guard detects a prompt-first spawn that omits model=', () => {
+    const synthetic = [
+      'Agent(',
+      '  prompt="""do the thing (with parens) and a " quote""",',
+      '  subagent_type="gsd-code-reviewer"',
+      ')',
+    ].join('\n');
+    const [call] = agentCalls(synthetic);
+    assert.ok(/subagent_type="gsd-code-reviewer"/.test(call), 'scanner must capture the prompt-first subagent_type');
+    assert.ok(!/\bmodel\s*=/.test(call), 'and correctly see that model= is absent');
+    // A well-formed prompt-first spawn WITH model= must be accepted.
+    const ok = agentCalls(synthetic.replace(')', '  model="{reviewer_model}"\n)'))[0];
+    assert.ok(/\bmodel\s*=/.test(ok));
+  });
+});
diff --git a/tests/perf-316-state-lock-buffer-alloc.test.cjs b/tests/perf-316-state-lock-buffer-alloc.test.cjs
index 3924cc5ef..4e0e04328 100644
--- a/tests/perf-316-state-lock-buffer-alloc.test.cjs
+++ b/tests/perf-316-state-lock-buffer-alloc.test.cjs
@@ -57,9 +57,13 @@ const fs = require('fs');
 // Write pid to lock file so acquireStateLock sees a live pid and retries.
 fs.writeFileSync(workerData.lockPath, String(process.pid));
 parentPort.postMessage({ pid: process.pid });
-// Synchronous sleep — blocks this worker thread for holdMs ms.
-const buf = new Int32Array(new SharedArrayBuffer(4));
-Atomics.wait(buf, 0, 0, workerData.holdMs);
+// Hold the lock until the writer signals it has made its first FAILED lock
+// attempt (deterministic contention), or until holdMs elapses as a safety cap.
+// Atomics.wait blocks this thread while releaseFlag[0] === 0. A fixed timer here
+// was racy: on a slow/loaded runner the writer's spawn+init could exceed the
+// timer, so the lock released before the writer ever contended (lockAttempts:1).
+const releaseFlag = new Int32Array(workerData.releaseSab);
+Atomics.wait(releaseFlag, 0, 0, workerData.holdMs);
 // Release the lock.
 try { fs.unlinkSync(workerData.lockPath); } catch { /* already gone */ }
 parentPort.postMessage({ done: true });
@@ -88,17 +92,29 @@ global.SharedArrayBuffer = StubSAB;
 // path — without this witness, a no-retry success would yield sabCount === 1
 // from BOTH pre-fix and post-fix code (the SAB is allocated unconditionally
 // post-fix, and exactly once for the single successful open pre-fix), giving
-// a false-pass against the bug. The 1000ms holdMs + 200ms SUT retry delay
-// guarantees >=4 attempts even on the slowest CI runners.
+// a false-pass against the bug. Contention is deterministic here: this worker
+// signals the holder to release only after its first failed attempt, so a
+// retry always occurs (lockAttempts >= 2) regardless of runner speed.
 const realOpenSync = fs.openSync.bind(fs);
+const releaseFlag = new Int32Array(workerData.releaseSab);
 let lockAttempts = 0;
 fs.openSync = function(filePath, flags, mode) {
-  if (typeof filePath === 'string' && filePath.endsWith('.lock') &&
+  const isLockCreate = typeof filePath === 'string' && filePath.endsWith('.lock') &&
       typeof flags === 'number' &&
-      (flags & fs.constants.O_CREAT) && (flags & fs.constants.O_EXCL)) {
-    lockAttempts++;
+      (flags & fs.constants.O_CREAT) && (flags & fs.constants.O_EXCL);
+  if (isLockCreate) lockAttempts++;
+  try {
+    return realOpenSync(filePath, flags, mode);
+  } catch (e) {
+    // On the FIRST failed atomic-create (lock is held → contention proven),
+    // signal the holder worker to release so the next retry succeeds. Makes the
+    // retry path deterministic regardless of worker-spawn latency.
+    if (isLockCreate && lockAttempts === 1) {
+      Atomics.store(releaseFlag, 0, 1);
+      Atomics.notify(releaseFlag, 0);
+    }
+    throw e;
   }
-  return realOpenSync(filePath, flags, mode);
 };
 
 // Delete cache entry to ensure a fresh require picks up the stubbed constructor.
@@ -160,17 +176,18 @@ describe('perf #316: acquireStateLock hoists sleep buffer — exactly one SAB pe
     { timeout: 8000 },
     async () => {
       // ── Worker A: hold the lock for 1000ms ─────────────────────────────────
-      // state.cjs retry delay = 200ms + 0-50ms jitter; 1000ms hold guarantees
-      // >=4 retries even on the slowest CI worker (~200ms spawn + 4 retry
-      // intervals ~1000ms ≈ hold duration). The lockAttempts assertion below
-      // proves the retry path was exercised end-to-end.
+      // The holder releases the lock only when the writer signals its first
+      // failed lock attempt (see WRITER_WORKER_CODE), so the writer is guaranteed
+      // to contend at least once regardless of worker-spawn latency. holdMs is now
+      // only a safety cap in case that signal never arrives.
       const holdMs = 1000;
+      const releaseSab = new SharedArrayBuffer(4);
       let resolveLockWritten;
       const lockWritten = new Promise((resolve) => { resolveLockWritten = resolve; });
       const holderDone = new Promise((resolve, reject) => {
         holderWorker = new Worker(HOLDER_WORKER_CODE, {
           eval: true,
-          workerData: { lockPath, holdMs },
+          workerData: { lockPath, holdMs, releaseSab },
         });
         holderWorker.on('message', (msg) => {
           if (msg.pid !== undefined) resolveLockWritten();
@@ -223,6 +240,7 @@ describe('perf #316: acquireStateLock hoists sleep buffer — exactly one SAB pe
               statePath,
               content: MINIMAL_STATE_MD,
               tmpDir,
+              releaseSab,
             },
           });
           writerWorker.on('message', resolve);
@@ -259,8 +277,8 @@ describe('perf #316: acquireStateLock hoists sleep buffer — exactly one SAB pe
       assert.ok(
         writeResult.lockAttempts >= 2,
         'SUT must have entered the retry path (>=1 failed lock attempt before success). ' +
-          'Got lockAttempts: ' + writeResult.lockAttempts + '. The 1000ms holdMs + 200ms ' +
-          'SUT retry delay guarantees >=2 attempts on any CI runner.'
+          'Got lockAttempts: ' + writeResult.lockAttempts + '. The holder releases only ' +
+          'after the writer signals its first failed attempt, so contention is deterministic.'
       );
 
       // THE KEY INVARIANT:
diff --git a/tests/workflow-size-baseline.json b/tests/workflow-size-baseline.json
index d389e7147..2f8dfb639 100644
--- a/tests/workflow-size-baseline.json
+++ b/tests/workflow-size-baseline.json
@@ -11,13 +11,13 @@
   "autonomous.md": 42474,
   "check-todos.md": 9475,
   "cleanup.md": 9941,
-  "code-review-fix.md": 23934,
-  "code-review.md": 31646,
+  "code-review-fix.md": 24320,
+  "code-review.md": 31916,
   "complete-milestone.md": 31071,
   "debug.md": 13549,
   "diagnose-issues.md": 12864,
   "discovery-phase.md": 8651,
-  "discuss-phase-assumptions.md": 27028,
+  "discuss-phase-assumptions.md": 27302,
   "discuss-phase-power.md": 11273,
   "discuss-phase.md": 31986,
   "do.md": 10353,
@@ -59,7 +59,7 @@
   "pr-branch.md": 15963,
   "profile-user.md": 21246,
   "progress.md": 30599,
-  "quick.md": 50452,
+  "quick.md": 50470,
   "reapply-patches.md": 20312,
   "remove-phase.md": 8513,
   "remove-workspace.md": 7551,