Files
msd-core/gsd-core/workflows/import.md
Cody Anderson 8c9265d4e5 fix(#3724): warning-only Dimension 3b findings no longer force the revision loop (#3758)
* fix(#3724): stop advisory Dimension 3b findings from forcing the revision loop

Dimension 3b (undeclared/temporal coupling, #1954) is spec'd "never a
blocker" but tagged severity: warning — the tier plan-phase's revision
loop counts as must-fix — and the planner is never taught the rule, so
every multi-wave phase touching shared mutable state replans at least
once, and intentionally coupled plans re-flag identically every
iteration to the stall prompt.

Three coordinated changes:
- gsd-plan-checker: retag 3b to severity: info, the tier
  references/revision-loop.md already exempts by design; recognize a
  coupling_justified frontmatter declaration in the Do-NOT-flag list so
  deliberate pairs converge. Additions are offset by trimming 3b
  motivation prose — the checker sits 45 bytes under its LARGE hard cap.
- plan-phase step 12: INFO-only accept — an issues block with zero
  BLOCKER/WARNING entries accepts the plan and surfaces the advisories
  instead of re-entering the revision loop. Real blockers and warnings
  still gate unconditionally.
- gsd-planner: slim pointer in assign_waves to the new
  progressive-disclosure reference gsd-core/references/planner-coupling.md
  (the planner sits 19 chars under its own cap), which carries the
  shared-mutable-state rule and the coupling_justified escape hatch so
  first-pass plans avoid the finding when the coupling is unintentional.

Documented the coupling_justified field in docs/reference/plan-md.md.
Growth acks per #2914; inventory manifest and install-tree fixtures
regenerated for the new reference file.

Closes #3724

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* test(#3724): pin Dimension 3b at severity: info

The severity retag makes the old assertion (severity: warning) stale;
lock the advisory tier from both directions — info must be present,
warning must not — so a future edit cannot silently re-arm the
revision-loop trigger.

Refs #3724

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* chore(#3724): changeset fragment for PR #3758

Refs #3724

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* docs(#3724): roster planner-coupling.md in docs/INVENTORY.md

The new reference was enumerated in the manifest and all 19 install-tree
fixtures but missing its row in the Modular Planner Decomposition table —
the roster half the manifest-sync test cannot check. (Review Blocker.)

Refs #3724

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* test(#3724): cover all four acceptance criteria (review round 1)

- plan-checker-coupling: the 3b severity assertion is now a PARITY check
  deriving the exempt tier from revision-loop.md's flow instead of
  hardcoding info — editing either side alone reds the suite. New
  describe pins the other three criteria: plan-phase's INFO-only accept
  clause (proven failing-first), the BLOCKER + WARNING count staying
  intact, the coupling_justified Do-NOT-flag exemption + fix_hint, and
  the planner pointer + planner-coupling.md content.
- ack fragment: $comment's plan-phase figure corrected to +79B; the 2775
  pin note carried forward into the gsd-planner.md entry, updated for
  upstream's #3761/#3764 Rule-paragraph anchor (which this diff leaves
  verbatim).

The parallel-dependent-plans re-anchor this commit originally carried was
superseded by upstream #3764 during review; this branch no longer touches
that file.

Refs #3724

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* fix(#3724): review round 2 — align the stance enumeration, complete the template contract

MAJOR: <adversarial_stance>'s severity enumeration gains the INFO bullet so it
agrees with Dimension 3b's 'ALWAYS INFO' mandate instead of contradicting it.
Funded by extracting the inline <examples> block to the new progressive-
disclosure reference gsd-core/references/plan-checker-examples.md (@-inlined
from the same spot; #1949 precedent), which also restores the 3b motivation
clause round 1 traded away (Nit 4) and nets the agent file SMALLER than base
(49107 -> 48486) — the extraction the byte pressure was owed.

MINOR: gsd-core/templates/phase-prompt.md now carries coupling_justified, and
the field's shape becomes one 'plan-id: reason' string per coupled peer so a
plan justified against two peers can express it; docs/reference/plan-md.md's
Type column names the shape.

NIT: the 3409 ack's plan-phase entry no longer calls the #1168 workflow
ratchet an 'XL tier'.

Acks and derived artifacts updated accordingly (checker entry removed — a
shrink needs no ack; INVENTORY roster row + regen:derived for the new file).

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* test(#3724): derive the 3b negative severity assertion (review round 2)

Every severity token in the 3b span must BE the tier revision-loop.md exempts,
replacing the hardcoded severity:warning negative — if the loop's exemption
ever moves, the failure names the real conflict instead of blaming the agent
file with a mutually-unsatisfiable pair.

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* fix(#3724): refit the planner coupling pointer under the char cap

Upstream #3299 (PR #3390) grew agents/gsd-planner.md to 49146 chars at the
base, leaving 5 chars of headroom where the +16-char pointer was measured
against 13 more. The pointer prose shortens to 'Non-file coupling:' —
49150 chars, back under the strict 49152-char cap — and the ack figures
follow. The @-path the tests pin is unchanged.

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* fix(#3724): re-home the plan-phase ack after the #3823 spent-fragment sweep

Upstream #3078/#3823 deleted all fully-spent ack fragments, including
3409-unreachable-guard-arms.json, which carried this PR's plan-phase.md
+79B append. Per the collision remedy that sweep added: take the deletion
and home the still-live entry in this PR's own fragment. Figures
re-measured at this merge base (90871 -> 90950 LF bytes).

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* fix(#3724): absorb the spent #3172 plan-phase fragment into this PR's ack

Upstream #3825 shipped 3172-stated-failing-direction.json naming only
plan-phase.md, now spent at the base — colliding with this PR's live
plan-phase entry. Per the #3003 pattern the fully-spent single-path
fragment is deleted and this fragment stays the path's one source;
figures re-measured at this base (93073 -> 93152 LF bytes).

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* fix(#3724): review round 3 — true up the ack figures, restore the wave comment

The fragment's absolute sizes are re-measured and anchored to base
e40e9670 (planner 47259 -> 47330 chars, checker 45537 -> 44916 B,
plan-phase 91186 -> 91265 LF bytes), with a note that absolutes rot as
next moves — the deltas are the durable claims. The round-1 removal of
the '# Implicit dependency: files_modified overlap forces a later wave.'
pseudocode comment offset headroom base drift had already returned, so
it is restored (findings 2-3). Changeset gains the (#3724) backlink
(finding 4).

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* fix(#3724): review round 4 — close the verify-work surface, harden the boundaries

BLOCKER: verify-work.md's verify_gap_plans is the second multi-plan
consumer of the checker's sentinels, and its ISSUES FOUND handler entered
revision_loop with zero severity parsing — the guaranteed replan #3724
fixed in plan-phase, alive on the gap-closure surface. The handler now
counts BLOCKER + WARNING and accepts INFO-only returns with advisories
displayed. The checker's INFO stance bullet is reworded to the claim that
is true everywhere ('revision gates count only BLOCKER + WARNING').

Minor 1: plan-phase's iteration_count >= 3 arm recounts severities, so an
INFO-only third check accepts instead of halting on a '0 issues remain'
user gate. Minor 2: the coupling_justified exemption now requires the
entry to NAME the other plan, closing the blanket-suppression reading.
Nit 1: INVENTORY row states the extraction buys cap headroom, not context.
Nit 2: the advisory display gains a concrete format on both surfaces.

Ack fragment re-anchored at base ddde001a: verify-work.md +264B (new
entry), plan-phase.md +395B, checker still net negative (-512B).

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* test(#3724): pin the verify-work accept and the iteration-cap boundary (review round 4)

Two wiring assertions: verify_gap_plans' ISSUES FOUND handler gates on
BLOCKER + WARNING and accepts INFO-only blocks, and plan-phase's
iteration_count >= 3 arm recounts severities instead of gating advisories
— the limit+1 boundary of the gate this PR fixes.

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* fix(#3724): review round 5 — fail closed at the gates, surface the advisory

Blocker 1: the checker's step-10 status rule routes an INFO-only result to
## ISSUES FOUND (with a new ### Advisories (info) template section and a
severity-aware recommendation) so the orchestrator receives the block and
displays the advisory instead of silently accepting a bare PASSED.

Blockers 2+3: all three gate surfaces (plan-phase step 12 both arms,
verify-work verify_gap_plans) carry one canonical clause verbatim — an entry
whose severity is missing or unrecognized counts as a BLOCKER (fail closed) —
making the accept condition an explicit-INFO whitelist while keeping
issue_count coherent for stall math.

Major 1: the INFO stance bullet scopes its claim to the plan-phase and
verify-work gates (quick mode's loop still revises on any ISSUES FOUND).
Major 2: INVENTORY row and ack $comment state the extraction's real trade
(readability, +0.6 KB eager runtime context), not a cap remedy.
Minor 1: plan-md.md marks coupling_justified as prompt convention, unvalidated.
Nit 1: ack absolutes re-anchored at base 1e67ec97; checker now +120B and acked.

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* test(#3724): pin the round-5 contract — fail-closed parity, INFO-only return shape

New: three-surface verbatim parity test for the fail-closed clause (Blockers
2+3); checker return-contract test for the INFO-only ## ISSUES FOUND route and
advisories section (Blocker 1). All seven newly pinned tokens are absent at
f3a5682d, so each new assertion fails pre-fix.

Updated: accept-clause regexes track the explicit-INFO whitelist wording;
the severity sweep scopes to the span's fenced yaml examples via
yamlSeverityTiers (round-5 Minor 3, applied to the blocker negative too);
the iteration-cap comment states it is a prose pin, not an executed boundary
check (Minor 4); splitLines call sites document the line-pin coupling (Nit 2).

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* fix(#3724): adopt next's line wrap in the 3b motivation clause — drops a wrap-only hunk from the diff

Byte-identical content; the wrap difference was an artifact of the round-1
base adaptation predating upstream's #3003 landing.

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

* fix(#3724): review round 7 — gate every checker consumer, not just the two audited ones

Blocker: quick/steps/plan-checker-loop.md (issue-named in #3724) gets the
same canonical fail-closed clause and explicit-INFO whitelist accept as
plan-phase/verify-work — an INFO-only result proceeds instead of entering
quick mode's revision loop.
Major: import.md plan_validate handles the checker return by severity
(INFO-only never blocks an import) and is added to agent-contracts.md's
consumer enumeration, which had omitted it.
The checker's INFO stance bullet drops the quick-mode carve-out — the claim
is universally true again now that every consuming gate is severity-aware.
Minor: an applied coupling_justified exemption is surfaced as its own info
advisory so a stale one-sided declaration stays observable.
Nit: plan-phase's revision-iteration Display line is explicitly conditioned
on not having already proceeded to step 13.

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM
Emitted-Drift-Ack-Growth: import.md — #3724 round 7: the plan_validate step's checker-return handler becomes severity-aware — counts BLOCKER + WARNING failing closed and accepts an explicitly-INFO-only return with advisories displayed instead of blocking the import

* test(#3724): pin the round-7 surfaces — five-gate parity, quick/import accepts, exemption visibility

The verbatim fail-closed parity test extends to quick/steps/plan-checker-loop.md
and import.md plan_validate; new assertions pin quick mode's INFO-only proceed,
import's never-blocks accept, import.md's presence in agent-contracts.md's
consumer row, and the surfaced coupling_justified exemption advisory. All four
newly pinned token families are absent at the pre-fix head, so each new
assertion fails first.

Claude-Session: https://claude.ai/code/session_01GshUzpGjoxiw6uNRiFMHvM

---------

Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
2026-08-31 19:08:11 -04:00

13 KiB
Raw Blame History

Import Workflow

External plan ingestion with conflict detection and agent delegation.

  • --from: Import external plan → conflict detection → write PLAN.md → validate via gsd-plan-checker

Future: --prd mode (PRD extraction into PROJECT.md + REQUIREMENTS.md + ROADMAP.md) is planned for a follow-up PR.


Display the stage banner:

_GSD_SHIM_NAME="gsd-tools.cjs"; _GSD_RUNTIME_ROOT="${RUNTIME_DIR:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"; GSD_TOOLS="${_GSD_RUNTIME_ROOT}/gsd-core/bin/${_GSD_SHIM_NAME}"; _gsd_at() { for _p; do if [ -f "$_p" ]; then GSD_TOOLS="$_p"; return 0; fi; done; return 1; }; if _gsd_at "${_GSD_RUNTIME_ROOT}/gsd-core/bin/${_GSD_SHIM_NAME}" "${_GSD_RUNTIME_ROOT}/.claude/gsd-core/bin/${_GSD_SHIM_NAME}" "${_GSD_RUNTIME_ROOT}/.codex/gsd-core/bin/${_GSD_SHIM_NAME}"; then gsd_run() { node "$GSD_TOOLS" "$@"; }; elif unset -f gsd_run; _G="$(command -v gsd_run)"; then GSD_TOOLS="$_G"; gsd_run() { "$GSD_TOOLS" "$@"; }; elif _gsd_at "${CLAUDE_CONFIG_DIR:-$HOME/.claude}/gsd-core/bin/${_GSD_SHIM_NAME}" "${HERMES_HOME:-$HOME/.hermes}/gsd-core/bin/${_GSD_SHIM_NAME}" "${CURSOR_CONFIG_DIR:-$HOME/.cursor}/gsd-core/bin/${_GSD_SHIM_NAME}" "${CODEX_HOME:-$HOME/.codex}/gsd-core/bin/${_GSD_SHIM_NAME}" "${GEMINI_CONFIG_DIR:-$HOME/.gemini}/gsd-core/bin/${_GSD_SHIM_NAME}" "${COPILOT_CONFIG_DIR:-$HOME/.copilot}/gsd-core/bin/${_GSD_SHIM_NAME}" "${WINDSURF_CONFIG_DIR:-$HOME/.codeium/windsurf}/gsd-core/bin/${_GSD_SHIM_NAME}" "${AUGMENT_CONFIG_DIR:-$HOME/.augment}/gsd-core/bin/${_GSD_SHIM_NAME}" "${TRAE_CONFIG_DIR:-$HOME/.trae}/gsd-core/bin/${_GSD_SHIM_NAME}" "${QWEN_CONFIG_DIR:-$HOME/.qwen}/gsd-core/bin/${_GSD_SHIM_NAME}" "${CODEBUDDY_CONFIG_DIR:-$HOME/.codebuddy}/gsd-core/bin/${_GSD_SHIM_NAME}" "${CLINE_CONFIG_DIR:-$HOME/.cline}/gsd-core/bin/${_GSD_SHIM_NAME}" "${GROK_AGENTS_HOME:-$HOME/.agents}/gsd-core/bin/${_GSD_SHIM_NAME}" "${ANTIGRAVITY_CONFIG_DIR:-$HOME/.gemini/antigravity}/gsd-core/bin/${_GSD_SHIM_NAME}" "${OPENCODE_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/opencode}/gsd-core/bin/${_GSD_SHIM_NAME}" "${KILO_CONFIG_DIR:-${XDG_CONFIG_HOME:-$HOME/.config}/kilo}/gsd-core/bin/${_GSD_SHIM_NAME}"; then gsd_run() { node "$GSD_TOOLS" "$@"; }; else echo "ERROR: gsd-tools.cjs not found at $GSD_TOOLS and gsd_run is not on PATH. Run: npx -y @opengsd/gsd-core@latest --claude --local" >&2; exit 1; fi; GSD_IDENTITY_STATUS=unverified; case "$(gsd_run runtime-identity --raw 2>/dev/null || true)" in '{"packageName":"@opengsd/gsd-core"'*'}') GSD_IDENTITY_STATUS=ok;; esac; export GSD_IDENTITY_STATUS; [ "$GSD_IDENTITY_STATUS" = ok ] || echo "WARNING: \"$GSD_TOOLS\" did not prove it is @opengsd/gsd-core - it is either a different package or an @opengsd/gsd-core older than the runtime-identity verb. See docs/how-to/diagnose-a-foreign-gsd-tools.md" >&2; if [ -n "${CLAUDE_ENV_FILE:-}" ] && [ -n "${GSD_TOOLS:-}" ]; then printf "export PATH='%s':\"\$PATH\"\n" "${GSD_TOOLS%/*}" >> "$CLAUDE_ENV_FILE" 2>/dev/null || true; fi
RESPONSE_LANGUAGE=$(gsd_run query config-get response_language --raw --default "" 2>/dev/null || echo "")

If response_language is set: All user-facing questions, prompts, and explanations in this workflow MUST be presented in {response_language}. Technical terms, code, file paths, and subagent prompts stay in English — only user-facing output is translated.

### GSD ► IMPORT

Parse $ARGUMENTS to determine the execution mode:

  • If --from is present: extract FILEPATH (the next token after --from), set MODE=plan
  • If --prd is present: display message that --prd is not yet implemented and exit:
    GSD > --prd mode is planned for a future release. Use --from to import plan files.
    
  • If neither flag is found: display usage and exit:
Usage: /gsd:import --from <path>

  --from <path>   Import an external plan file into GSD format

Validate the file path:

Verify the path does not contain traversal sequences and the file exists:

case "{FILEPATH}" in
  *..* ) echo "SECURITY_ERROR: path contains traversal sequence"; exit 1 ;;
esac
test -f "{FILEPATH}" || echo "FILE_NOT_FOUND"

If FILE_NOT_FOUND: display error and exit:

### ERROR

File not found: {FILEPATH}

**To fix:** Verify the file path and try again.

Path A: MODE=plan (--from)

Load project context for conflict detection:

  1. Read .planning/ROADMAP.md — extract phase structure, phase numbers, dependencies
  2. Read .planning/PROJECT.md — extract project constraints, tech stack, scope boundaries. If PROJECT.md does not exist: skip constraint checks that rely on it and display:
    GSD > Note: No PROJECT.md found. Conflict checks against project constraints will be skipped.
    
  3. Read .planning/REQUIREMENTS.md — extract existing requirements for overlap and contradiction checks. If REQUIREMENTS.md does not exist: skip requirement conflict checks and continue.
  4. Glob for all CONTEXT.md files across phase directories:
    find .planning/phases/ -name "*-CONTEXT.md" -o -name "CONTEXT.md" 2>/dev/null
    
    Read each CONTEXT.md found — extract locked decisions (any decision in a <decisions> block)

Store loaded context for conflict detection in the next step.

Read the imported file at FILEPATH.

Determine the format:

  • GSD PLAN.md format: Has YAML frontmatter with phase:, plan:, type: fields
  • Freeform document: Any other format (markdown spec, design doc, task list, etc.)

Extract from the imported content:

  • Phase target: Which phase this plan belongs to (from frontmatter or inferred from content)
  • Plan objectives: What the plan aims to accomplish
  • Tasks listed: Individual work items described in the plan
  • Files modified: Any files mentioned as targets
  • Dependencies: Any referenced prerequisites

Run conflict checks against the loaded project context. The report format, severity semantics, and safety-gate behavior are defined by gsd-core/references/doc-conflict-engine.md — read it and apply it here. Operation noun: import.

BLOCKER checks (any one prevents import):

  • Plan targets a phase number that does not exist in ROADMAP.md → [BLOCKER]
  • Plan specifies a tech stack that contradicts PROJECT.md constraints → [BLOCKER]
  • Plan contradicts a locked decision in any CONTEXT.md <decisions> block → [BLOCKER]
  • Plan contradicts an existing requirement in REQUIREMENTS.md → [BLOCKER]

WARNING checks (user confirmation required):

  • Plan partially overlaps existing requirement coverage in REQUIREMENTS.md → [WARNING]
  • Plan has depends_on referencing plans that are not yet complete → [WARNING]
  • Plan modifies files that overlap with existing incomplete plans → [WARNING]
  • Plan phase number conflicts with existing phase numbering in ROADMAP.md → [WARNING]

INFO checks (informational, no action needed):

  • Plan uses a library not currently in the project tech stack → [INFO]
  • Plan adds a new phase to the ROADMAP.md structure → [INFO]

Render the full Conflict Detection Report using the format in gsd-core/references/doc-conflict-engine.md.

If any [BLOCKER] exists: apply the safety gate from the reference — exit WITHOUT writing any files. No PLAN.md is written when blockers exist.

If only WARNINGS and/or INFO (no blockers):

Text mode (workflow.text_mode: true in config or --text flag): Set TEXT_MODE=true if --text is present in $ARGUMENTS OR text_mode from init JSON is true. When TEXT_MODE is active, replace every AskUserQuestion call with a plain-text numbered list and ask the user to type their choice number. This is required for non-Claude runtimes (OpenAI Codex, Gemini CLI, etc.) where AskUserQuestion is not available.

Ask via AskUserQuestion using the approve-revise-abort pattern (see gsd-core/references/gate-prompts.md):

  • question: "Review the warnings above. Proceed with import?"
  • header: "Approve?"
  • options: Approve | Abort

If user selects "Abort": exit cleanly with message "Import cancelled."

Convert the imported content to GSD PLAN.md format.

Ensure the PLAN.md has all required frontmatter fields:

---
phase: "{NN}-{slug}"
plan: "{NN}-{MM}"
type: "feature|refactor|config|test|docs"
wave: 1
depends_on: []
files_modified: []
autonomous: true
must_haves:
  truths: []
  artifacts: []
---

Reject PBR naming conventions in source content: If the imported plan references PBR plan naming (e.g., PLAN-01.md, plan-01.md), rename all references to GSD {NN}-{MM}-PLAN.md convention during conversion.

Apply GSD naming convention for the output filename:

  • Format: {NN}-{MM}-PLAN.md (e.g., 04-01-PLAN.md)
  • NEVER use PLAN-01.md, plan-01.md, or any other format
  • NN = phase number (zero-padded), MM = plan number within the phase (zero-padded)

Determine the target directory by querying init.phase-op for the phase number extracted in plan_read_input. This ensures the project_code prefix from .planning/config.json is applied:

INIT=$(gsd_run query init.phase-op "{NN}")
if [[ "$INIT" == @file:* ]]; then INIT=$(cat "${INIT#@file:}"); fi
expected_phase_dir=$(echo "$INIT" | node -e "process.stdout.write(JSON.parse(require('fs').readFileSync('/dev/stdin','utf8')).expected_phase_dir)")

If the directory does not exist, create it:

mkdir -p "${expected_phase_dir}"

Set phase_dir="${expected_phase_dir}" for use in subsequent steps.

Write the PLAN.md file to the target directory.

Delegate validation to gsd-plan-checker:

Print: "Delegating to gsd-plan-checker (runs in a subagent — no output until it returns, ~1–5 min; expected, not a freeze)"

CHECKER_MODEL=$(gsd_run query resolve-model gsd-plan-checker --raw)

Runtime-aware dispatch (#2508 Phase 4). GSD workflows dispatch specialized subagents by role. Before dispatching on a built-in-only runtime (kimi-code — three built-ins only), resolve the role to a built-in via gsd_run query resolve-dispatch-type --requested <role> --raw. On named-dispatch runtimes (Claude/OpenCode/…) the role is returned unchanged; on kimi-code it maps to coder/explore/plan by role-suffix. The persona rides ${AGENT_SKILLS_<ROLE>} (Phase 3) regardless. See @gsd-core/references/runtime-aware-dispatch.md.

Model omission (#2517). Omit the model parameter entirely when the value it would carry (CHECKER_MODEL) is "inherit" or empty. An empty value 404s on runtimes without native tier aliases — the default on non-Claude runtimes. Omitting it inherits the orchestrator's model. See @gsd-core/references/model-profile-resolution.md.

Agent({
  subagent_type: "gsd-plan-checker",
  model: "{CHECKER_MODEL}",
  prompt: "Validate: ${phase_dir}/{plan}-PLAN.md — check frontmatter completeness, task structure, and GSD conventions. Report any issues."
})

ORCHESTRATOR RULE — CODEX RUNTIME: After calling Agent() above, stop working on this task immediately. Do not read more files, edit code, or run tests related to this task while the subagent is active. Wait for the subagent to return its result. This prevents duplicate work, conflicting edits, and wasted context. Only resume when the subagent result is available.

Handle the checker return by severity, never by the sentinel alone: count BLOCKER + WARNING entries in the YAML issues block; an entry whose severity is missing or unrecognized counts as a BLOCKER (fail closed). If the return is ## VERIFICATION PASSED, or the count is zero — every entry is explicitly INFO — display ℹ advisory — {dimension}: {description} per INFO entry and treat the plan as imported; INFO is advisory and never blocks an import (#3724). Otherwise:

  • Display the blocking issues to the user
  • Ask the user to resolve issues before the plan is considered imported
  • Do not delete the written file — the user can fix and re-validate manually

If the checker returns clean:

  • Display: "Plan validation passed"

Update .planning/ROADMAP.md to reflect the new plan:

  • Add the plan to the Plans list under the correct phase section
  • Include the plan name and description

Update .planning/STATE.md if appropriate (e.g., increment total plan count).

Commit the imported plan and updated files:

gsd_run query commit "docs({phase}): import plan from {basename FILEPATH}" --files .planning/phases/{phase}/{plan}-PLAN.md .planning/ROADMAP.md

Display completion:

### GSD ► IMPORT COMPLETE

Show: plan filename written, phase directory, validation result, next steps.


Anti-Patterns

Do NOT:

  • Violate the shared conflict-engine contract in gsd-core/references/doc-conflict-engine.md (no markdown tables, no new severity labels, no bypass of the BLOCKER gate)
  • Write PLAN.md files as PLAN-01.md or plan-01.md — always use {NN}-{MM}-PLAN.md
  • Use pbr:plan-checker or pbr:planner — use gsd-plan-checker and gsd-planner
  • Write .planning/.active-skill — this is a PBR pattern with no GSD equivalent
  • Reference pbr-tools, pbr:, or PLAN-BUILD-RUN anywhere
  • Write any PLAN.md file when blockers exist — the safety gate must hold
  • Skip path validation on the --from file argument