Make install + surface read the registry's derived profileMembership/
capabilityClusters so a capability's tier drives what installs + surfaces.
resolveProfile (when given the registry) unions capability skills for the
profiles its tier implies before the requires: closure; resolveSurface merges
capabilityClusters into the cluster map. bin/install.js, /gsd:surface, and the
capability-state resolver all thread the registry.
Shipped as a proven no-op: the UI capability is reconciled to tier:full (its
skills were full-only in the hand-authored profiles), so it contributes only to
the full profile (already the '*' sentinel) and core/standard are unchanged.
Equivalence tests prove resolveProfile/resolveSurface/listSurface/staging/
capability-state are identical with vs without the registry; the core-alias
staging path is verified equivalent (empty manifest → raw PROFILES.core).
Closes#949
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
- bin/install.js now copies scripts/changeset/ and scripts/lib/ into
<configDir>/scripts/ so $GSD_DIR/scripts/changeset/cli.cjs resolves
at runtime; aborts install with an explicit failure if the source
directory is missing from the package.
- gsd-core/workflows/update.md: corrected path from
gsd-core/scripts/changeset/cli.cjs to scripts/changeset/cli.cjs;
added an explicit [ ! -f ] guard so a missing CLI surfaces a clear
message rather than silently swallowing the error; stderr captured
via 2>&1 sentinel so node errors are visible in the preview output.
- release.yml's changeset-CLI invocations (node scripts/changeset/cli.cjs)
remain at the repo-root path and are unaffected by this change.
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#856): remove gsd-cmd-rewrites temp dirs after install
applyRuntimeContentRewritesForCommandsInPlace() returns a fresh
mkdtemp dir under os.tmpdir() (gsd-cmd-rewrites-*) with rewritten
command markdown. installRuntimeArtifacts() copied from it but never
removed it, leaking one temp dir per commands kind per install — on
tmpfs /tmp hosts these accumulate and consume RAM-backed storage.
Wrap the per-kind copy in try/finally and rmSync the temp dir (only
when it differs from the staged source, i.e. the commands kind) once
the copy completes or fails. dest creation moved inside the try so a
mkdir failure still triggers cleanup.
Regression test isolates os.tmpdir() to a private TMPDIR root and
asserts no gsd-cmd-rewrites-* dir survives the install.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#856): add changeset for installer temp-dir cleanup
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#834): derive installer --help skill counts from PROFILES
The installer --help text undercounted profile skill counts: it claimed
"core — 7 main-loop skills" and "standard — ~13 skills" when the real
counts in PROFILES (bin/lib/install-profiles.cjs) are 8 and 14. The
`surface` skill was added to core after the help string was written, and
standard was never updated.
Derive the core and standard counts from PROFILES.core.length and
PROFILES.standard.length so the help text cannot drift again. Replace the
stale hardcoded "all 66 skills" (actually 67) on the full line with
drift-proof "all skills" — full is the '*' sentinel with no array length
and no cheap authoritative total in the help path.
Add regression tests that run `node bin/install.js --help` and assert the
printed core/standard counts equal the PROFILES lengths, plus a guard
that the full line carries no hardcoded numeric count.
Closes#834
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#834): add changeset for installer --help count fix
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#770): register Claude Code lifecycle hooks (SubagentStop/Stop/PreCompact/FileChanged)
Wire three new context-tracking events (SubagentStop, Stop, PreCompact) to
gsd-context-monitor so context-headroom warnings surface at model-stop and
subagent-finalisation moments — not just on PostToolUse. Add a new
FileChanged hook (gsd-config-reload.js) that hot-reloads .planning/config.json
context mid-session when the user edits it, injecting a config summary as
hookSpecificOutput.additionalContext. Updates plugin manifest hooks.json,
managed-hooks-registry, installer-migration-report allowlist, and
shell-command-projection cleanup tables. Tests: 21 new assertions in
enh-770-claude-hook-events.test.cjs; enh-788 and issue-766 test suites updated.
Closes#770
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#770): document newly-registered Claude Code lifecycle hooks
Add a Hook coverage table to the Claude Code npm installer section of
docs/how-to/install-on-your-runtime.md describing SubagentStop, Stop,
PreCompact, and the new FileChanged (gsd-config-reload.js) hook that
hot-reloads .planning/config.json mid-session. Also fixes the changeset
frontmatter (adds type: Added + pr: 821) so docs-lint can consume the
fragment.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#770): add gsd-config-reload.js to INVENTORY.md and regenerate manifest
The feat commit added hooks/gsd-config-reload.js but did not bump the
Hooks count in docs/INVENTORY.md (14→15) or add the new row, and did not
regenerate docs/INVENTORY-MANIFEST.json. Both inventory-counts and
inventory-manifest-sync tests failed across the full CI matrix.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#770): make lifecycle-hook tests deterministic on scoped runner
Replace the shared hooks/dist/ ensemble setup (ensureHooksDist /
teardownHooksDist) in the Claude hook tests with per-test isolation:
pre-populate each test's own tmpDir/.claude/hooks/ with stub files and
pass installerMigrations:[] to install() so the first-time-baseline
migration does not remove the stubs before the copy step can run.
Root cause: hooks/dist/ is gitignored and absent on a fresh npm ci.
ensureHooksDist() created it and teardownHooksDist() deleted it, but
with --test-concurrency=4 both test files ran concurrently as separate
Node.js worker processes sharing the same filesystem. One file's
afterEach teardown deleted hooks/dist/ while the other file's install()
was copying from it, producing an ENOENT (reproduced 2/10 runs locally).
The additional issue: even with pre-placed stubs surviving the copy race,
the 000-first-time-baseline migration classified hooks/gsd-*.js as
bundled-gsd-hook artifacts, auto-removed them, and the copy step never
re-ran (hooks/dist/ absent) — leaving contextMonitorFile missing and all
hook registrations silently skipped (the 'got: []' symptom).
Fix: pre-populate targetDir/hooks/ per-test (isolated temp dir) AND pass
installerMigrations:[] so the baseline scan is skipped. The Qwen suites
already used this pattern correctly; the Claude suites are aligned to it.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#770): ship gsd-config-reload.js by adding it to build-hooks HOOKS_TO_COPY
The #770 feature added hooks/gsd-config-reload.js and registered it in
MANAGED_HOOKS, the installer, INVENTORY, and the test EXPECTED_ALL_HOOKS
list — but never added it to scripts/build-hooks.js HOOKS_TO_COPY. As a
result the hook was never copied into hooks/dist/ during the build, so:
- the hook would never ship to users (real production bug — the
FileChanged config-reload feature was dead-on-arrival), and
- install-minimal-hooks.test.cjs #1755 ("all expected hooks are copied
from hooks/dist/ to target", ".js hooks are executable after copy",
"manifest contains .js hook entries") failed on any environment with
a clean checkout (no pre-existing hooks/dist/): coverage, full test
macos-22/macos-24, test ubuntu-24.
The failures were masked locally only by a stale hooks/dist/ left from a
prior build (build-hooks copies into dist without clearing it). On CI's
fresh `npm ci` there is no dist, so the omission surfaced.
Fix: add 'gsd-config-reload.js' to HOOKS_TO_COPY so build-hooks stages it
into hooks/dist/ alongside the other JS hooks. Verified by removing
hooks/dist/ and rerunning the full suite green (0 fail).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#770): make config prototype-pollution beforeEach deterministic on scoped runner
Root cause: the #663 and alert-#26 prototype-pollution describe blocks
seeded .planning/config.json in beforeEach via a bare
runGsdTools('config-ensure-section') whose result was discarded. That
command runs in a spawned gsd-tools child; on the scoped CI lane
(--test-concurrency=4, config.test.cjs scheduled alongside the heavy
install/tarball suites that #770 pulled into the targeted set) the child
can be transiently killed under resource pressure (non-zero exit, empty
stderr — an OS-level kill, not an app error). The swallowed failure left
config.json absent, so the first subtest's readConfig() threw ENOENT
opening <tmp>/.planning/config.json. Only 1 of 4 subtests failed,
confirming a per-invocation transient, not a deterministic miss; the full
suite schedules files differently so config.test.cjs did not collide with
those heavy neighbors → passed there.
Fix: add ensureConfigReady(tmpDir) which retries config-ensure-section on
ANY failure or missing file and throws a clear diagnostic if it still
cannot create config.json, then use it in both prototype-pollution
beforeEach blocks. Setup is now deterministic under load; the #663/alert-#26
security assertions are unchanged.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#777): register Cursor-native hooks (.cursor/hooks.json) for session-start/post-tool parity
- Add gsd-cursor-session-start.js: injects STATE.md presence reminder (or
new-project nudge) into Cursor sessions via the sessionStart hook event
- Add gsd-cursor-post-tool.js: emits an additional_context nudge when
write-class tool calls touch .planning/ files (postToolUse hook event)
- Add 'cursor-hooks-json' installSurface to runtime-config-adapter-registry;
writeCursorHooksJson/reconcileCursorHooksJson write the canonical
{ version: 1, hooks: { sessionStart, postToolUse } } JSON shape with
idempotent reconciliation that preserves user-owned hook entries
- Hook scripts are copied with /gsd:→gsd- rewrite so installed files
contain no colon-form slash-command refs (bug-376 invariant)
- 20 new tests in tests/cursor-hooks.test.cjs cover all reconciler paths,
entry helpers, removal, runtime adapter surface, and hook script behavior
- Update CONTEXT.md, ARCHITECTURE.md, installer-migrations.md, and
000-first-time-baseline.cts to include Cursor hooks.json surface
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#777): build hooks/dist on demand in bug-376 test for scoped/windows CI
hooks/dist is gitignored and only produced by `npm run build:hooks`.
The CI scoped (ubuntu-latest/node-22) and windows (windows-latest/node-24)
test jobs do NOT run build:hooks before executing tests, so bug-376's
prerequisite suite was failing with "hooks/dist not found" on both legs.
Add ensureHooksDist() helper (mirrors bug-3357 pattern) that builds
hooks/dist on demand in the before() hooks of prerequisite and Suite 3.
Also add ensureHooksDist() call to Suite 3's before() so the snapshot
step is also hermetic.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#776): Gemini hook events (BeforeAgent/AfterAgent/BeforeModel) + hooksConfig.enabled check
Register three new Gemini-CLI hook events on install:
- BeforeAgent: fires before agent planning; wired to gsd-context-monitor
- AfterAgent: fires after final response generation; wired to gsd-context-monitor
- BeforeModel: fires before each LLM call (per-turn); wired to gsd-context-monitor
All three reuse gsd-context-monitor.js (no new hook files). Uninstall cleanup
loop extended to remove the new events. Non-array guard added for robustness
against malformed settings.
Also detect hooksConfig.enabled:false in Gemini settings and emit a clear
warning — without this check, all registered hooks silently do nothing.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: update changeset pr: 829
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#776): document Gemini hook events
Add hook coverage table to the Gemini CLI section of install-on-your-runtime.md,
covering the three new events (BeforeAgent/AfterAgent/BeforeModel wired to
gsd-context-monitor) plus a callout for the hooksConfig.enabled:false silent
failure mode detected by the installer.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#789): elevate CodeBuddy — emit slash commands (+ document subagent/MCP scope)
Emit a CodeBuddy slash-command surface so GSD workflows appear in the
'/' menu, reaching parity with other elevated runtimes.
- Add convertClaudeCommandToCodebuddyCommand and register a commands/
artifact kind for the codebuddy runtime (commands/gsd-<name>.md),
consistent with the Cursor (#785) and Augment (#790) commands surfaces.
- Mark emitted skills user-invocable:false so the commands surface is the
sole '/' entry point (no duplicate /gsd-* entries); skills stay
model-invocable. CodeBuddy's SKILL.md supports this field.
- Normalize $HOME/.codebuddy (bare + slash) path forms in runtime
rewrites so --config-dir/local installs don't leak the default home.
- Report installed commands/ count on install; uninstall prunes gsd-*
commands while preserving user-owned commands.
Scope: subagents (~/.codebuddy/agents/) are already emitted by the
generic agents block (unchanged); no mcp.json is written (gsd ships no
MCP server, and CodeBuddy's mcp.json registers only external servers).
Closes#789
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#789): set changeset pr number to 830
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#778): cross-runtime command enrichment (Gemini {{args}}/!{}, Qwen priority)
Enrich the installer's per-runtime command/skill generators with native,
verified, additive fields:
- Gemini CLI: map Claude's $ARGUMENTS -> Gemini's {{args}} in generated TOML
commands so typed arguments interpolate; inject live .planning/STATE.md into
/gsd:progress via a fixed, injection-safe !{cat .planning/STATE.md 2>/dev/null}
shell block (no interpolated input).
- Qwen Code: emit the optional numeric `priority` field on main-loop skills so
the most-used workflows sort first in the /skills list (higher = earlier per
the Qwen skills spec; the issue's inverse numbering was corrected).
OpenCode per-command model/agent/subtask/variant enrichment was evaluated and
intentionally not implemented: `model` reintroduces the #1156
ProviderModelNotFoundError regression for non-Anthropic providers (the converter
deliberately strips model:), `subtask`/`agent` change execution semantics for
GSD's interactive commands, and `variant` is not in the OpenCode command schema.
Schemas verified against primary docs (Gemini custom-commands, Qwen skills,
OpenCode commands/skills). Adds tests/enh-778-* and how-to + USER-GUIDE docs.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#778): set changeset PR number to 825
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#772): adopt stable Codex hook events + commandWindows for Windows parity
Register three new stable Codex hook events (SubagentStart, Stop,
PostToolUse) wired to gsd-context-monitor.js so Codex installs get
the same context-headroom tracking at subagent and session boundaries
that Claude/Qwen already have.
Add commandWindows field to the SessionStart hook entry on Windows so
Codex uses the .cmd shim directly (Git Bash/MSYS cannot POSIX-exec
node.exe). commandWindows is only emitted on win32; POSIX is unchanged.
Refactor reconcileCodexHooksJsonSessionStart into a generic
reconcileCodexHooksJsonEvent so any event name can be reconciled with
the same dedup/preserve-user-entries logic.
Add gsd-context-monitor.js and .cmd to MANAGED_HOOK_COMMAND_BASENAMES
_BY_SURFACE so idempotent re-runs de-duplicate entries correctly.
30 new tests covering: export surface, event registration for each of
the three events, commandWindows parity (POSIX vs win32), idempotency,
uninstall, and user-entry preservation.
Closes#772
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#772): windows path normalization + docs-lint
- Normalize scriptPath backslashes to forward slashes in
ensureCodexHooksJsonEvent and ensureCodexHooksJsonSessionStart so that
isManagedHookCommand can match stored commands against configDir on
Windows CI runners. path.resolve returns backslash paths on Windows,
but when platform is not 'win32' (e.g. platform:'linux' in tests),
projectManagedHookCommand skips normalization — producing a mismatch
that breaks idempotency deduplication (the same hook entry appended
twice on re-register). Forward-slash paths are always valid in both
Node.js and Codex, so the normalization is safe for all platforms.
- Fix changeset pr: 0 → 827 to resolve fail_malformed_fragment.
- Add Codex hook coverage table to docs/how-to/install-on-your-runtime.md
documenting the SubagentStart/Stop/PostToolUse events + commandWindows
Windows-parity field added by this enhancement.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#769): emit context:fork + effort: frontmatter on heavy workflow skills
Add `context: fork` and `effort: xhigh` to the three heaviest workflow
commands (plan-phase, execute-phase, autonomous) and `effort: low` to the
two quick-status commands (progress, stats).
On Claude Code, `context: fork` runs the skill in an isolated subagent
context window so the main session's context budget is protected.
`effort: xhigh` / `effort: low` signal the appropriate token-budget tier to
the runtime. Both fields are silently ignored by runtimes that do not
recognise them (Gemini, Codex, Cursor, etc.) — no behaviour change outside
Claude Code.
Update convertClaudeCommandToClaudeSkill in bin/install.js to preserve
`context:` and `effort:` when rewriting source command files to SKILL.md for
a Claude global install. Add install-suite tests to assert the fields are
present in both source commands and the installed SKILL.md output.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(#769): tighten regex assertions + add execute/plan-phase effort coverage
Fix low-severity adversarial finding: tighten test regex patterns from
`\s*` to `[ \t]*` so they cannot match across newlines (CRLF parity).
Add missing effort: xhigh assertions for gsd-execute-phase and gsd-plan-phase
SKILL.md install output to complete the black-box coverage gap.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#774): emit service_tier/model_verbosity in Codex agent TOML + agents/openai.yaml skill chip
- Add service_tier = "flex" and model_verbosity = "low" to the Codex
ConfigProfile TOML for light-tier agents (gsd-research-synthesizer,
gsd-codebase-mapper, gsd-plan-checker, and 8 others identified via
AGENT_DEFAULT_TIERS). Field names/values verified against Codex schema
(profile_toml.rs / config_types.rs Verbosity enum). Non-light agents
are unaffected.
- Add generateCodexSkillMetadataYaml() and writeCodexSkillMetadataFiles():
after installRuntimeArtifacts, iterate every gsd-* skill directory,
read the short-description already emitted in the SKILL.md frontmatter
by convertClaudeCommandToCodexSkill, and write agents/openai.yaml with
interface.display_name and interface.short_description for the Codex
TUI skill picker chip.
- yamlQuote (JSON.stringify) handles all YAML-unsafe chars.
- User-owned gsd-dev-preferences dir is never overwritten.
- Errors per-skill are swallowed so a bad SKILL.md can't abort install.
- agents/openai.yaml is covered by the snapshot/rollback system and
manifest hash (writeManifest hashes skill dirs recursively).
- Uninstall symmetry: _removeGsdEntries removes whole gsd-* dirs.
- 21 new tests in codex-config.test.cjs covering service_tier/verbosity
TOML emission, YAML generation (round-trip via js-yaml), and
writeCodexSkillMetadataFiles including an e2e integration test.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#774): correct docs-lint coverage — proper changeset format + USER-GUIDE entry
Rewrite the changeset fragment from old @opengsd/gsd-core:patch format to the
required type:/pr: schema so the docs-lint parser can consume it. Add a new
"Codex skill picker and agent scheduling (#774)" section to docs/USER-GUIDE.md
describing the flex-tier scheduling and /skills TUI chip enrichments — both are
user-visible and belong in docs rather than behind a docs-exempt marker.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#768): pre-populate settings.json permissions.allow/deny for Claude Code
Adds mergeClaudePermissions() to bin/install.js which non-destructively
appends GSD's known-safe tool-call patterns to permissions.allow and
defense-in-depth credential-file patterns to permissions.deny during
Claude Code installs. Merge is idempotent (no duplicates on reinstall)
and additive (existing user entries preserved). Uninstall removes only
the exact GSD-owned entries.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore: update changeset pr number to 819
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#813): apply per-runtime skill path rewrites in applySurface
applySurface() re-staged skill artifacts but, unlike installRuntimeArtifacts(),
never applied the per-runtime path rewrites. So /gsd:surface
(profile/enable/disable/reset) overwrote installed SKILL.md bodies with the
converter's default ~/.claude paths instead of the install target (pathPrefix),
silently regressing skill path references for every skillsKind runtime until
the next reinstall.
applySurface now mirrors installRuntimeArtifacts: for kind.kind === 'skills' it
derives pathPrefix the same way and applies applyRuntimeContentRewritesInPlace
on the staged dir before syncing.
- bin/install.js: export applyRuntimeContentRewritesInPlace
- runtime-artifact-layout.cts: carry resolved scope on Layout; export
getInstallExports; type computePathPrefix/applyRuntimeContentRewritesInPlace
on InstallExports
- surface.cts: lazily derive pathPrefix (only when a skills kind exists) and
apply the rewrite via the shared getInstallExports accessor — single source of
truth with install, only skills kinds rewritten (matches install)
- tests: regression test parameterized over cursor + codex asserting
post-applySurface bodies carry the install pathPrefix, not ~/.claude
- CONTEXT.md: glossary updated for the applySurface rewrite parity + scope seam
Closes#813
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#813): add changeset fragment for PR #817
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(#813): normalize configDir prefix to forward slashes for Windows CI
The #813 regression assertion compared skill bodies against a raw
${configDir}/ prefix, but production derives pathPrefix via
path.resolve(configDir).replace(/\\/g, '/'). On Windows, mkdtempSync
returns backslash paths while the rewritten body uses forward slashes,
so the assertion would fail Windows-only (not covered by local gsd-test).
Normalize the expected prefix the same way production does.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#784): emit native skills for OpenCode + Kilo runtimes
OpenCode and Kilo share a config schema and both discover on-demand
skills from skills/<name>/SKILL.md. The installer previously emitted
only flat commands (command/) and file-based agents (agents/) for these
runtimes. Add a shared OpenCode-family skill writer that stages each GSD
command as a spec-compliant SKILL.md (name matching the directory,
description 1-1024 chars), wired through the runtime artifact layout so
uninstall cleans skills/ automatically. Skills respect the active
install profile.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#784): correct skill body paths + preserve user dev-preferences
Address adversarial-review findings:
- Add opencode/kilo cases to _applyRuntimeRewrites so staged SKILL.md
bodies are re-pointed from the converter's hardcoded default config dir
to the actual install target (fixes --local / --config-dir installs;
commands/agents already did this by applying pathPrefix pre-conversion).
- Preserve user-owned skills/gsd-dev-preferences across reinstall in
installOpencodeFamilySkills (snapshot+restore around the gsd-* prune),
matching installRuntimeArtifacts.
- Export installOpencodeFamilySkills and add regression tests.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#784): guarantee command/skill body parity, fix kilo-alt double-rewrite
Follow-up adversarial-review found the post-conversion path rewrite could
double-rewrite custom Kilo dirs (kilo -> kilo-alt -> kilo-alt-alt) because
the kilo pathPrefix is a $HOME (non-absolute) superset of the hardcoded
default base. Restructure so OpenCode/Kilo skills mirror copyFlattenedCommands
exactly: stage raw commands, apply pathPrefix BEFORE conversion via a new
shared applyOpencodeFamilyPathPrefix() helper (now used by both the command
and skill writers), then convert. This guarantees byte-for-byte command/
skill body parity for global, --local, and --config-dir installs and removes
the prefix-overlap hazard. Drop the fragile _applyRuntimeRewrites opencode/
kilo case. Strengthen the path regression test.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(#784): derive opencode/kilo skills from the same staged command set
Pass the installer's _stageSkills() output directly to
installOpencodeFamilySkills instead of re-staging via the layout, so the
command/ and skills/ surfaces always cover the identical profile-resolved
set — including the --minimal/--core-only alias path, which stages
differently from a plain --profile=core. Verified: minimal install now
emits 8 commands and 8 skills.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#784): set changeset PR number to 810
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* test(#784): fully escape backslashes in test helper (CodeQL js/incomplete-string-escaping)
Replace the dot-only escape `replace(/[.]/g, '\\.')` with a complete
regex-escape pattern `replace(/[\\.*+?^${}()|[\]]/g, '\\$&')` so all
regex metacharacters (including backslash itself) in `defaultBase` are
safely escaped before interpolation into `new RegExp(...)`.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Cline added a global skills system (~/.cline/skills/<name>/SKILL.md) in
v3.48.0, but gsd treated Cline as rules-only and emitted zero skills
(getGlobalSkillsBase('cline')=null, empty artifact kinds). This makes gsd
emit skills for Cline at global scope, alongside the existing .clinerules.
- runtime-homes: getGlobalSkillsBase('cline') -> ~/.cline/skills (was null)
- runtime-artifact-layout: cline emits a skills kind for GLOBAL scope only
(local stays .clinerules-only), mirroring claude's scope dispatch
- install.js: convertClaudeCommandToClineSkill emits name+description-only
SKILL.md frontmatter (Cline/agentskills.io spec; no Claude-specific
allowed-tools/argument-hint/agent), hyphen-normalized + .cline/-rewritten
body; global cline routed through the skills path while .clinerules is
still written; _applyRuntimeRewrites cline case handles custom
CLINE_CONFIG_DIR; convertClaudeToCliineMarkdown also rewrites bare
~/.claude and CLAUDE_CONFIG_DIR
- docs: install-on-your-runtime.md documents Cline global skills vs local rules
- tests: converter (name+description-only), global emission, skills+.clinerules
coexistence, scope-aware layout, custom-dir paths, idempotency
Closes#782
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#788): expand Qwen Code hook-event coverage to 4 new events
Register SubagentStop, Stop, PreCompact (gsd-context-monitor.js) and
UserPromptSubmit (gsd-prompt-guard.js) in the Qwen Code installer.
Guard is isQwen-only — Claude Code and all other runtimes are unchanged.
Uninstall loop extended to include the 4 new event names.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#788): reconcile to 3 Qwen-only events — defer UserPromptSubmit
gsd-prompt-guard exits unless tool_name is Write|Edit (PreToolUse
payload shape); UserPromptSubmit carries raw user-prompt text with no
tool_name field, so wiring it would be a silent no-op. Deferred to a
follow-on issue.
Artifacts made consistent:
- bin/install.js: drop UserPromptSubmit registration block; uninstall
loop drops UPS from event list
- .changeset/788-qwen-hook-events.md: corrected to 3 events + rationale
- docs/how-to/install-on-your-runtime.md: remove UPS row from hook table
- tests/enh-788-qwen-hook-events.test.cjs: assert UPS NOT registered;
fix idempotency suite to persist settings between installs; drop
UPS-specific assertions
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(#788): update changeset PR number to #807
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(#788): prune stale install-bucket allowlist entry for enh-788 test
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(#812): honor COPILOT_HOME in Copilot global config-dir resolution
getGlobalConfigDir('copilot') resolved the global config directory using
only --config-dir > COPILOT_CONFIG_DIR > ~/.copilot, ignoring the
COPILOT_HOME env var. Per GitHub's Copilot CLI docs, COPILOT_HOME
overrides the default ~/.copilot location (and user-level hooks are read
from $COPILOT_HOME/hooks/), so a global --copilot install wrote all
artifacts (skills, agents, copilot-instructions.md, the gsd-session.json
hook) to ~/.copilot even when the user relocated their Copilot home,
making them undiscoverable by Copilot CLI.
Mirror the codex/CODEX_HOME branch: precedence is now
--config-dir > COPILOT_CONFIG_DIR > COPILOT_HOME > ~/.copilot. Uninstall
uses the same resolver, so it stays symmetric.
Also: document COPILOT_HOME in the installer --help notes, the
USER-GUIDE env-var table, and the installer-migrations Copilot row; and
clear COPILOT_HOME in the two default-path test suites so they stay
hermetic now that the resolver honors it.
Closes#812
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#812): add changeset for PR #814
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#787): elevate Cline — .clinerules/ dir form, PreToolUse hook, AGENTS.md
Migrate the installer's Cline output from a single-file .clinerules to the
.clinerules/ directory form (.clinerules/gsd.md), which is the prerequisite for
Cline's v3.36 hooks (a path cannot be both a file and a directory). Add a
.clinerules/hooks/PreToolUse lifecycle hook implementing Cline's JSON stdin ->
{cancel,errorMessage,contextModification} protocol; it guards .planning/
artifacts and fails open. On global installs, merge GSD instructions into the
cross-tool ~/.agents/AGENTS.md target (marker-delimited, merge-safe). A legacy
single-file .clinerules is migrated in place; --uninstall removes the new
artifacts and strips the AGENTS.md GSD block.
Also fixes the uninstall targetDir for Cline local installs (it pointed at
./.cline instead of the project root) and re-runs writeManifest after the
Cline artifacts are written so they are hash-tracked.
Self-contained: implemented independently of the #782 Cline skills work.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#787): address review findings
- Scope PreToolUse hook path-walk to PATH_KEY fields only (eliminates false
positive when doc body content mentions .planning/)
- Use lstatSync + isSymbolicLink() for migration guard so GSD never writes
through a user's symlinked .clinerules into an external directory
- Add regression tests for both cases
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore(#787): set changeset pr: 803
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* feat(#785): write .cursor/commands/ as Cursor 1.6 slash-command surface
Cursor 1.6 (released 2025-09-12) introduced plain-markdown slash commands
in `.cursor/commands/<name>.md` — no frontmatter, invocable via `/` in the
Agent input. GSD previously emitted only `~/.cursor/skills/` for Cursor.
This PR wires a second artifact kind for `cursor` in
`runtime-artifact-layout.cts`: `convertedCommandsKind('commands', 'gsd-',
'convertClaudeCommandToCursorCommand', configDir)`. The new kind applies the
same `convertClaudeToCursorMarkdown` transforms (tool renames, brand
substitution, slash-command normalisation) and then strips YAML frontmatter
so the output is plain prose. Skills output is unchanged.
`stageCommandsForRuntimeFlat` in `install-profiles.cts` stages each source
`.md` as a flat `<stem>.md` in a temp dir; the existing `_copyStaged` commands
path then prefixes and copies to `<configDir>/commands/`.
`.cursor/mcp.json` is explicitly OUT OF SCOPE: GSD ships no MCP server; the
`mcpServers` schema cannot be usefully populated by the installer.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(#785): address review nit
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(#786): elevate Copilot installer with lifecycle hook + AGENTS.md
Emit a self-contained sessionStart hook config (.github/hooks/gsd-session.json
local, ~/.copilot/hooks/gsd-session.json global) and write AGENTS.md at the repo
root (Copilot CLI reads it as primary instructions) alongside
copilot-instructions.md. The hook is an inline `command` hook (no separate hook
script), so it cannot dangle. Uninstall removes both and preserves user content.
Verified against GitHub Copilot CLI primary docs: hooks-configuration (camelCase
events, version+hooks shape, inline bash/powershell command hooks) and
add-custom-instructions (AGENTS.md read at repo root as primary instructions).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#786): set changeset pr number to 804
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(#56): retire legacy runtime directory helpers into runtime-homes projection
Consolidate per-runtime global config-dir resolution onto the single
canonical projection runtime-homes:getGlobalConfigDir. Extend it with the
explicitDir override (CLI --config-dir) and the opencode/kilo
OPENCODE_CONFIG/KILO_CONFIG file-path precedence the installer helpers had,
making it byte-for-behavior equivalent to the old getGlobalDir across all
15 install runtimes.
Delete bin/install.js's getGlobalDir/getOpencodeGlobalDir/getKiloGlobalDir
(and the orphaned local expandTilde), repoint all 9 call-sites, and remove
getGlobalDir from module.exports (net -242 lines in the installer). Migrate
the 5 test importers to the canonical projection; harden default/XDG
assertions against ambient *_CONFIG env vars. getAgentsDir now respects
OPENCODE_CONFIG/KILO_CONFIG consistently with the installer (intentional
convergence). Update CONTEXT.md Installer Module entry.
Completes the installer-refactor chain #58 -> #60 -> #56.
Closes#56
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#56): add changeset for runtime directory helper retirement
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(#60): make runtime config adapter registry explicit
Replace scattered inline `runtime === '...'` config-mutation branching in
bin/install.js with an explicit, typed adapter registry. The new
src/runtime-config-adapter-registry.cts maps each of the 15 supported
runtimes to a config intent { installSurface, writesSharedSettings,
finishPermissionWriter }; install()/finishInstall() dispatch by resolved
intent instead of runtime-name checks (cursor/windsurf/trae collapse to one
profile-marker-only branch).
Behavior-preserving: the same config files are written for the same runtimes
(opencode still writes both settings.json and its permissions; kilo writes
only its permissions; codex minimal-mode and opencode GSD_TEST_MODE guards
unchanged). Unknown runtimes fail loudly via TypeError, with an Object.hasOwn
barrier so prototype-chain keys (__proto__/constructor) also throw rather than
returning a bogus intent. Leads the installer-refactor chain (#58 -> #60 ->
#56), building on ADR-58.
Closes#60
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#60): add changeset for runtime config adapter registry
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* docs(#60): register Runtime Config Adapter Registry in CONTEXT.md glossary
Per docs/contributor-standards.md, every new Module/seam must get a
`### <Name>` entry under the domain glossary. Adds the entry for the
runtime-config-adapter-registry seam introduced in this PR (interface,
policy boundary, source file, ADR-58 / #60 cross-references).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#683): auto-degrade phase execution to sequential on worktree base mismatch
Claude Code forks worktree-isolated executors off the repository default
branch (origin/HEAD), not the orchestrator's HEAD. Running /gsd-execute-phase
on a branch diverged from the default (unmerged milestone/feature branch) left
every executor without the phase's plan files and tripped the
worktree-branch-check guard with `exit 42` — 100% reproducible, all OSes.
- New module src/worktree-base-ref.cts: HEAD-vs-fork-base drift detection
(origin/HEAD with symbolic-ref fallback) and no-clobber worktree.baseRef
management, exposed as `worktree base-check` / `worktree set-baseref`.
- execute-phase.md: pre-dispatch, for Claude Code with worktrees enabled,
auto-degrades the run to sequential on the main tree when a base mismatch
is detected, recommending worktree.baseRef:"head". The exit-42 guard stays
as a backstop.
- Installer: fresh local Claude installs set worktree.baseRef:"head" in
.claude/settings.local.json (no-clobber, respecting an explicit shared
settings.json value); upgrades print an opt-in notice pointing at
`gsd-tools worktree set-baseref`.
- Docs: how-to guide, CLI/config reference, planning-config cross-ref.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#683): auto-apply worktree.baseRef on upgrade; gate fresh+upgrade on use_worktrees
Per maintainer direction: on a local Claude Code UPGRADE, set
worktree.baseRef:"head" automatically (no opt-in notice) when the project's
workflow.use_worktrees is enabled, instead of merely printing a remediation
notice. For consistency the FRESH path is now gated the same way: both paths
compute worktrees-enabled once (bounded walk-up read of .planning/config.json,
default enabled unless workflow.use_worktrees === false) and apply the
no-clobber baseRef only when enabled — never overwriting an explicit value in
settings.local.json or a shared settings.json. gsd-tools worktree set-baseref
remains for manual use. Docs + changeset updated; tests hardened (file-exists
assertions, fresh+disabled case, upgrade idempotency).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#683): measure workflow byte-budget on LF, fixing Windows-only CI failure
The workflow-size-budget test failed only on Windows: git checks out the .md
files as CRLF (no eol=lf in .gitattributes) and byteCount used
fs.statSync().size (raw on-disk bytes), counting an extra \r per line. That
inflated execute-phase.md — the XL high-water-mark file pinned near its ceiling
by the tighten-only ratchet — from 88492 LF bytes to ~90245 on Windows, over
the 90000 XL ceiling, while passing on the LF-checkout Mac/Linux runners.
The ceilings are explicitly "calibrated against raw `wc -c`" on an LF checkout,
so the measurement should be LF-based on every platform. byteCount now reads the
file and counts Buffer.byteLength after stripping CR, making the budget
platform-independent (a no-op on LF checkouts; verified statSync === normalized
for all 88 workflow files). No ceilings changed. Added a regression test
asserting CRLF and LF content of the same file count identically.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#683): make worktree-base-ref test path mocks Windows-safe (path.join)
tests/worktree-base-ref.test.cjs keyed its injected readFile/writeFile mocks
(and a few expected `file` values) with forward-slash template literals like
`${claudeDir}/settings.local.json`. The module composes those paths with
path.join(), which emits backslashes on Windows, so the mock keys never matched
the module's lookup → readFile returned null → resolveEffectiveBaseRef /
cmdWorktreeBaseCheck / cmdWorktreeSetBaseRef (and the JSONC variants) failed on
the Windows full-test runner only (they passed on Mac/Linux, and the install
tests passed because they use the real filesystem). The module is correct;
only the test fixtures hardcoded '/'.
All mock keys and path assertions now use path.join(base, ...) mirroring the
module, so they match on every platform (no-op on POSIX). 19 path references
across 16 lines.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
* refactor(#712): replace Codex slash-command denylist lookbehind with positive-boundary match
The hyphen-style /gsd-<cmd> -> $gsd-<cmd> conversion in
convertSlashCommandsToCodexSkillMentions used a negative-lookbehind DENYLIST
enumerating characters that must NOT precede a real mention. #637 -> #704 showed
this is an unbounded treadmill: each new unanticipated preceding char (/, ., word
chars, then }, )) leaked the same path-corruption bug class, and a backtick-wrapped
path (`/gsd-core/workflows/update.md`) still leaked through.
Replace it with a POSITIVE two-boundary definition of a mention:
1. Left: opens at start-of-string, whitespace, or an inline-prose delimiter
(backtick/quote/paren/bracket).
2. Right: the command token is not followed by a path separator `/` (a path
continues, a command does not). The (?![a-z0-9/-]) lookahead also blocks
regex backtracking to a shorter command.
This closes the whole class by construction (no preceding-char denylist to
maintain) and fixes the backtick-wrapped-path corruption the #704 test
documented as a pre-existing gap, while preserving conversion of legitimate
backtick-wrapped mentions (e.g. CONTEXT.md's `/gsd-execute-phase` lists).
The colon-style /gsd: replace is intentionally left unguarded (it never appears
as a filesystem path segment) and is annotated as such.
Tests assert the regex directly (function now exported) across a convert/
don't-convert matrix plus one end-to-end pipeline assertion for the headline
backtick-path case.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* chore(#712): add changeset fragment for PR #747
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
- stage generated Kimi root and subagent YAML/prompt files under agents/
- copy and remove only GSD-owned Kimi agent files while preserving user files
- print explicit kimi --agent-file launch hint
- Wire Kimi global layout to convertClaudeCommandToKimiSkill
- Keep --kimi --local guarded as a no-op
- Add Kimi self-invocation hint without agent or tool artifacts
- Resolve Kimi global skills under the generic agents path
- Add empty Kimi layout placeholder and local install no-op guard
- Keep selection/path tests aligned without Kimi skill conversion
* fix(#704): exclude } and ) from Codex path-rewrite lookbehind
Shell variable expressions like \${VAR}/gsd-core/ and command-substitution
paths like \$(cmd)/gsd-local-patches were being rewritten to \$gsd-core and
\$gsd-local-patches respectively because the negative lookbehind in
convertSlashCommandsToCodexSkillMentions did not include } or ).
Add both characters to the lookbehind set:
(?<![a-zA-Z0-9./})])
Also adds regression test:
tests/bug-704-codex-launcher-path-corruption.test.cjs
Closes#704
* chore: add changeset for #704
* test: use RUNTIME_ROOT_PATH in assertion to eliminate dead-code lint warning
Replace the partial hard-coded fragment '}/gsd-core/bin/' with the
existing RUNTIME_ROOT_PATH const so the assertion both compiles clean
(no unused variable) and self-documents which canonical launcher path
must survive Codex conversion intact (#704).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* chore: link changeset to PR #710
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(#656): add Research Store module (content-addressed cache, TTL staleness)
Content-addressed research cache behind a clock seam: researchKey (sha256, deterministic), putResearch/getResearch ({hit,stale}, never throws), ttlForSource (curated HIGH 30d / MED 7d / web LOW 1d), two-tier resolveStorePath (curated -> ~/.gsd/research-cache, web/synthesis -> project .planning/research/.cache). 28 behavioral + property tests; boundary coverage at ttl-1/ttl/ttl+1.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#656): add Research Provider module (waterfall + confidence + plan)
Single source of truth for the Balanced provider waterfall (docs Context7->Ref->Jina, web Exa+Tavily, fallback Perplexity/Brave, Firecrawl scrape-only). classifyConfidence stamps HIGH|MEDIUM|LOW by provider (never throws). providerAvailability maps config flags to usable providers. planResearch checks the Research Store (injected seam) and returns cache-hits + a per-question fetch plan, falling through the waterfall to the always-available websearch terminal. 22 behavioral + property tests.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#656): add Package Legitimacy module (registry-API verdicts, slopcheck optional)
Replaces the pip-install-or-degrade slopcheck prose gate with code: classifyPackage (pure, never throws) computes OK|SUS|SLOP from tunable thresholds (minAgeDays 30, minWeeklyDownloads 1000, requireRepo). checkPackages queries injectable npm/PyPI/crates registry adapters (real https with 5s timeout, degraded-not-thrown on failure); slopcheck is one optional adapter that can only escalate severity, never degrade to [ASSUMED]. 34 behavioral + property tests; boundary coverage on age and downloads (limit-1/limit/limit+1).
Known follow-up: real npm adapter must add api.npmjs.org last-week downloads fetch (currently null -> unknown-downloads). Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#656): detect Tavily/Ref/Perplexity/Jina provider keys; complete npm downloads adapter
config: add tavily_search/ref_search/perplexity/jina availability flags (env var or ~/.gsd/<x>_api_key), mirroring brave_search/exa_search/firecrawl, so the Research Provider waterfall can gate them. package-legitimacy: real npm adapter now fetches api.npmjs.org last-week downloads (bounded, degraded-not-thrown) so weeklyDownloads is populated. +12 config tests; 34 legitimacy tests unchanged.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#656): expose Research seam via gsd-tools query (research-plan, research-store, package-legitimacy)
Routes the L2-hybrid surface so agents reach it as CLI: 'query research-store get/put' (cache, HOME-sandboxable), 'query research-plan --input' (cache-hits + fetch plan from planResearch), 'query package-legitimacy check --ecosystem' (async registry verdicts). Commands skip .planning root resolution and appear in top-level usage. 5 behavioral runGsdTools tests; command-contract unchanged (335).
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* docs(#656): document Research module (CONTEXT predicates, ADR-0656, architecture, changeset)
Adds GSD-RESEARCH.* + DEFECT.RESEARCH-PROVIDER-PROSE-DRIFT predicates to CONTEXT.md, ADR-0656 recording the L2-hybrid seam decision, a docs/ARCHITECTURE.md Research Module subsection, and an Added changeset fragment (pr:0, backfill on PR). Notes the #657 deferrals (agent collapse + install.js MCP mapping).
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#656): sync inventory for research modules
Regenerate INVENTORY-MANIFEST.json and bump docs/INVENTORY.md CLI Modules count 82->85 with rows for research-store/research-provider/package-legitimacy (DEFECT.INVENTORY-DRIFT).
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#656): eslint-ignore generated research .cjs artifacts (ADR-457)
research-store/research-provider/package-legitimacy .cjs are tsc-generated from src/*.cts, so they belong in the ESLint ignore block (lint the .cts source, not the emitted .cjs). Fixes tests/551-eslint-bin-lib-coverage.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#656): backfill changeset pr number to #664
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#656): satisfy eslint lint-tests gate
Fix 20 eslint errors in the new research files: use helpers.cleanup() instead of raw fs.rmSync() in tests (local/no-raw-rmsync-in-tests, Windows-EBUSY retry budget); drop redundant '| string' union members and unnecessary type assertions; deterministic object normalization in researchKey (no-base-to-string). Logic unchanged; 6180 tests still green.
Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): harden package legitimacy per review (W1/W2/I3/I4)
W1: httpsGet now reads statusCode; npm/PyPI/crates map 404 -> exists:false -> SLOP (registry-existence is the #1 slopsquatting defense; previously only npm caught it). Transport made injectable (_setHttpGet) for hermetic 404 tests. W2: suspicious-postinstall is now terminal SLOP independent of the optional slopcheck adapter, and the regex drops the bare https?:// arm (over-fired on esbuild/sharp/node-gyp) for shell-exec/download-exec signatures only. I3: checkPackages now threads version to registry.lookup and adapters verify that specific version exists. I4: moreServerVerdict -> moreSevereVerdict. +11 regression tests (all RED-first); 45 total green.
Addresses review by @davesienkowski on #664. Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): research-store tier coherence + freshness + version TTL (W4/I1/I2/I4)
I1: tier now derives from source (curated -> user ~/.gsd, else -> project .planning), not kind, so put-tier and get-tier can't diverge; kind is a key component only. W4: getResearch searches both tiers and returns the freshest (non-stale preferred), never letting a stale curated entry shadow a fresh web one; blank version caps TTL at 1 day (no 30d on version-blind keys). I2: atomic platformWriteSync instead of raw fs.writeFileSync on the shared global path. I4: dropped the dead ttlForSource arm. CLI get now searches both tiers. +5 RED-first regression tests; 38 green.
Addresses review by @davesienkowski on #664. Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): expose classifyConfidence as a CLI route, killing dead code (W3)
Adds 'gsd-tools query classify-confidence --provider X [--verified]' so research agents get the confidence tier FROM CODE (provider waterfall + verification lever) instead of asserting it in prose. classifyConfidence previously had no runtime caller. HIGH means 'trusted provider'; --verified raises web results to MEDIUM (verification semantics documented in ADR-0656). +4 behavioral tests.
Addresses review by @davesienkowski on #664 (W3). Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): close Codex adversarial-review findings (path-traversal, version-age, malformed-cache)
HIGH: research key must be 64-hex sha256 (isValidResearchKey) + resolved-path containment check in put/get + CLI validation -> blocks '../../x' arbitrary-file-write. HIGH: package legitimacy now derives publishedAt from the REQUESTED version (npm time[version], PyPI releases[version] upload_time, crates versions[].created_at) so a new malicious version of an old package can't inherit old age and evade 'too-new'. MEDIUM: getResearch validates entry shape (finite fetched_at + positive ttl + required fields) -> malformed cache entry is a miss, not fresh-forever. +regression tests (RED-first); 111 green.
Codex adversarial review (required pre-PR gate). Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): close code-review correctness findings
(1) package-legitimacy CLI now rejects unknown --flags instead of silently consuming the following package as a flag value; only --ecosystem takes a value. (2) crates recent_downloads (90-day) normalized to a weekly figure before the minWeeklyDownloads threshold (was ~13x too lenient). (3) research-plan --input validates parsed JSON is an object with an Array questions before destructuring -> clean usage error instead of an uncaught TypeError on null/bad input. (4) research-store put rejects a flag value that is itself a --flag (no more storing '--source' as content). (5) planResearch skips questions whose text is not a non-empty string instead of emitting question:undefined. +13 RED-first regression tests; 143 green.
Code-review gate. Issue #656. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(#657): extract researcher documentation_lookup to shared @-reference
6 researcher agents carried a near-duplicate <documentation_lookup> block; consolidate into gsd-core/references/research-documentation-lookup.md (@-included). Unifies the ctx7 CLI fallback to the safer 'command -v ctx7' guard (drops silent 'npx --yes ctx7@latest' execution in 5 agents). Behavior-preserving dedup; inventory 63->64 references. Phase A of the agent collapse.
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* refactor(#657): extract researcher philosophy + verification-protocol to shared @-references
philosophy and the pitfalls+pre-submission-checklist common-core were near-duplicated in project/phase researchers; consolidate into gsd-core/references/research-{philosophy,verification-protocol}.md (@-included). phase-researcher keeps its 3 extra checklist items inline. Pre-submission domains checklist made agent-agnostic so project-researcher doesn't lose features/architecture coverage. Write-contract intentionally left inline (bug-214 tests assert it verbatim). Inventory 64->66 refs. Behavior-preserving. Phase A.
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#657): wire gsd-phase-researcher to the Research seam (Phase B / S1)
The phase researcher now CALLS the code seam instead of carrying inline mechanics: provider waterfall -> 'gsd-tools query research-plan' (+ research-store put to cache digests); confidence-tier prose -> 'gsd-tools query classify-confidence'; slopcheck pip-install protocol -> 'gsd-tools query package-legitimacy check'. This makes the Research module a real runtime consumer (validates the seam end-to-end, addresses reviewer S1) and removes the duplicated waterfall/confidence/slopcheck prose. RESEARCH.md output contract, commit step, structured returns, and Phase-A @-includes unchanged. package-legitimacy-gate.test.cjs rewritten prose-grep -> behavioral (asserts the seam invocation).
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#657): wire gsd-project-researcher to the seam + add tavily/ref/jina MCP tools (Phase C.1)
project-researcher now calls gsd-tools query research-plan / classify-confidence (+ research-store put) instead of the inline provider waterfall + confidence-tier prose (mirrors the phase-researcher rewire; no package-legitimacy — phase-only). Output contract (STACK/FEATURES/ARCHITECTURE/PITFALLS/SUMMARY.md + sections, no-commit, structured returns, Phase-A @-includes) unchanged. Adds mcp__tavily/ref/jina__* to the project/phase/ui researcher tools frontmatter (Balanced provider set) so install.js MCP mapping (C.2) has a consumer.
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* test(#657): cover tavily/ref/jina MCP install handling + frontmatter parity guard (Phase C.2)
Investigation: exa/firecrawl have no explicit per-runtime tool-mapping — every mcp__<server>__* except context7 rides the generic passthrough (Copilot lowercases; OpenCode/Cursor/Windsurf/Augment keep as-is; Gemini auto-discovers). tavily/ref/jina are handled identically, no install path broken. Added 12 copilot-install passthrough tests + a mcp-tool-inheritance parity guard (tavily co-declared with exa, jina with firecrawl, ref present across the 3 web researchers) so the MCP set can't drift. No io.github registry ids invented (none sourceable in-repo); documented as a follow-up. 488 tests green.
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* feat(#657): profiles as source of truth for researcher agents + drift-guard (Phase C.3)
scripts/research-profiles.cjs declares each of the 7 researcher agents' identity + contract (name, description, color, tools, required @-includes, required gsd-tools seam calls, output-contract markers). scripts/gen-research-agents.cjs --check validates every committed agent against its profile; --write regenerates ONLY the frontmatter from profiles (body untouched) and is a verified no-op against the current agents (zero diff = fidelity). tests/research-agent-profiles.test.cjs is the DEFECT.GENERATIVE-FIX drift guard. Design note: profiles govern the generatable/contract surface rather than destructively regenerating the disparate operational prose bodies (those were deduped via @-includes in Phase A). scripts/ is not inventoried (no inventory change).
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#657): complete agent provider-dispatch + parity guard; align legitimacy field; validate profiles
Adversarial-review findings: (HIGH) the seam-wired agents' Step-C dispatch only mapped 6 providers, so a planResearch result of jina/ref/perplexity/brave (reachable via the waterfall fallbacks) had no handling -> agent stall; completed both agents' dispatch to all 9 PROVIDER_WATERFALL ids + a catch-all, and added a parity test asserting agent dispatch stays in sync with research-provider PROVIDER_WATERFALL (DEFECT.GENERATIVE-FIX). (MEDIUM) phase-researcher package-legitimacy JSON example used 'package' but the module returns 'name' -> aligned. (LOW) gen-research-agents checkAgent now returns a clear failure for a malformed profile instead of throwing. +parity/validation tests (RED-first).
Issue #657. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* fix(#656): make classifyConfidence verification-evidence-driven (W3)
Confidence conflated provider authority with claim verification — context7/ref
stamped HIGH purely by provider identity, and the only verification lever was a
self-set --verified flag. Split into two axes: provider authority (static) +
verification evidence (code-computed). HIGH now requires ground-truth
corroboration (legitimacyVerdict OK), independent of provider; authority alone
caps at MEDIUM; SLOP caps at LOW; the self-reported --verified is demoted to a
MEDIUM-only web lever. HIGH = corroborated-against-authoritative-source, not a
correctness guarantee. Adds --legitimacy-verdict to the classify-confidence CLI;
updates CONTEXT.md predicate + ADR-0656 (tier set unchanged, ADR-consistent).
Addresses davesienkowski's W3 review on #664.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#656): bind classify-confidence verdict to code, closing CLI self-grading
Adversarial review found the new --legitimacy-verdict flag was caller-supplied,
so an agent could self-assert OK->HIGH without any real legitimacy check —
reintroducing the exact self-grading hole W3 closes. Remove the free flag; the
CLI now computes the verdict via checkPackages only when --package/--ecosystem
is given (code-computed, not agent-asserted). Update the stale CLI test
(context7 alone -> MEDIUM) and extend the property test to vary legitimacyVerdict.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* chore(#604): rename get-shit-done/ runtime directory to gsd-core/
Renames the installed runtime directory `get-shit-done/` to `gsd-core/` so the
on-disk name matches the package (`@opengsd/gsd-core`), repo, and binary
(`gsd-tools`). The npm package name and binary are unchanged; npx/npm consumers
are unaffected.
Mechanical (bulk, ~90% of the diff):
- `git mv get-shit-done gsd-core`
- Swept path/identifier references across the repo via
`perl -pe 's/get-shit-done(?!-\w)/gsd-core/g'`. The negative lookahead
preserves the five legitimate slug variants that are NOT the directory:
get-shit-done-{OLD,cc,classic,cli,redux} (old package/repo names).
- Build/manifest wiring: package.json (bin, files, coverage globs),
tsconfig.build.json (outDir), ~86 .gitignore build-output entries,
stryker.config.mjs, scan-ignore files, install.js path strings.
- Frozen (not rewritten): CHANGELOG.md history; translated docs
(README.<locale>.md and docs/{ja-JP,ko-KR,pt-BR,zh-CN}/).
New logic (review here):
- src/installer-migrations/003-rename-get-shit-done-to-gsd-core.cts: a proper
ADR-0008 installer migration. On upgrade it walks the legacy
`~/.claude/get-shit-done/` tree, classifies each file via the prior install
manifest, and emits remove-managed / backup-and-remove for managed files
while PRESERVING unknown user-added files. Symlink-safe (skips a symlinked
root and symlinked entries; bounds-checks every path under configDir). The
framework rolls back on install failure. Emptied dirs may remain (framework
has no recursive dir-removal primitive) — documented.
- scripts/lint-legacy-dir-name.cjs: CI regression guard forbidding the bare
`get-shit-done` directory token (split token to avoid self-match; case-
insensitive; `(?!-\w)` lookahead allows the slug variants; allowlists
CHANGELOG, translated docs, and `gsd-allow-legacy-name` marker lines).
Wired into the lint-tests CI job.
- Restored scripts/lint-package-identity-drift.cjs detection regexes (the
mechanical sweep had wrongly rewritten the old-name patterns it exists to
detect) and marked them as intentional legacy references.
- TDD tests for the migration and the guard; do.md slash-command guard regex
tightened so a `/gsd-core/bin` path segment is not mistaken for a command;
changeset + docs/installer-migrations.md row added.
Breaking: the installed runtime path moves `~/.claude/get-shit-done/` ->
`~/.claude/gsd-core/`. Migration 003 removes the stale legacy dir's managed
files (preserving user files) on upgrade. Users with custom hooks/configs
hardcoding the old path must update them.
Closes#604
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#604): unsweep pending changesets + allowlist injection-example docs
CI fixes for the rename PR:
- Do not sweep pending .changeset/*.md (ephemeral release-note fragments,
like CHANGELOG); reverted those body edits so 5 pre-existing malformed
fragments (missing type/pr) no longer enter the PR diff and trip docs-lint.
Allowlisted .changeset/ in the legacy-name guard accordingly.
- Allowlisted TEST-EXAMPLES.md and docs/explanation/security-model.md in
prompt-injection-scan.sh: they contain intentional injection examples /
security-model prose; the path-reference rewrites are kept.
CodeQL alerts on this PR are pre-existing (alert lines unchanged by this PR;
none in the new migration/guard) and are out of scope for the rename.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#604): resolve CodeQL alerts surfaced on this PR
The rename diff touched files carrying pre-existing CodeQL findings; per the
no-pre-existing-dismissal rule, fixing every surfaced alert rather than waving
them off. All behavior-preserving:
- scripts/ci-test-scope.cjs: build the config-path match from string
.includes() instead of a RegExp over an arg-derived value (js/regex-injection).
- src/profile-output.cts: escape backslashes before pipe-escaping desc/safeName
so the table-cell escape is complete (js/incomplete-sanitization).
- tests/{bug-2643,bug-2808,docs-parity-live-registry}: two-pass HTML-comment
strip so a bare/unclosed `<!--` cannot survive (js/incomplete-multi-character-sanitization).
- tests/inline-plan-threshold: drop the no-op `\s`->`\s` identity replace,
keep the meaningful POSIX-class conversion (js/identity-replacement).
Verified: build:lib green; the touched test files + ci-test-scope + profile-output
suites pass; lint:legacy-name clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#604): correctly resolve remaining CodeQL alerts (regex-injection + sanitization)
The prior commit's fixes for two alerts were ineffective:
- ci-test-scope.cjs js/regex-injection: the alert is the CLI-arg-derived `file`
reaching static regex `.test(file)` calls (not the config rule). Removed ALL
regex over file/t — startsWith/includes/=== string checks + an isWindowsHint
helper — so there is no regex sink for the tainted value.
- js/incomplete-multi-character-sanitization (3 test files): a single
`.replace(/<!--...-->/g,'')` can let `<!--` re-form. Replaced with a fixpoint
loop (replace until stable) plus a final bare-opener strip.
Verified: no regex over file/t remains; ci-test-scope + the 3 test suites pass;
lint:legacy-name clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#604): make ci-test-scope + comment-strippers regex-free to clear CodeQL
CodeQL flags the regex PATTERNS syntactically (regex-injection on the
--files arg split; incomplete-multi-character-sanitization on the <!--...-->
replace), so loop fixes do not satisfy it. Made these paths regex-free:
- ci-test-scope.cjs splitFiles: char-by-char separator tokenizer (no /[,\\s]+/).
- 3 test files: indexOf/slice HTML-comment stripper (no .replace(/<!--/)).
Behavior preserved; ci-test-scope + the 3 suites pass; guard clean.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#604): unblock security base64 scan on the large rename diff
The security job hit its 10m timeout: base64-scan.sh choked on the binary
test fixture tests/feat-3594-parser-property-style.test.cjs (embedded NUL/
non-UTF8 bytes -> thousands of bogus blobs + "ignored null byte" warnings),
and the ~800-file rename diff is slow to scan regardless.
- scripts/base64-scan.sh: skip binary-by-content files (grep -Iq .) — they
can't carry base64-obfuscated *text* and feeding NUL bytes through the
per-line scanner is pathologically slow. collect_files already filtered
binary *extensions*; this catches binary *content* in text extensions.
- .github/workflows/security-scan.yml: raise the security job timeout 10m->30m
to accommodate very large diffs (the scan itself is unchanged).
Verified locally: scan skips the fixture, 0 "ignored null byte" warnings,
0 findings, exit 0.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#604): sweep get-shit-done refs introduced by merging next
The branch was updated with next (#614/#384/#618 etc.), which reference the
get-shit-done/ dir (still named that on next). Swept the stale references in
the merged files to gsd-core so the rename stays consistent and lint:legacy-name
passes:
- commands/gsd/discuss-phase.md (runtime-launcher shim paths)
- src/core.cts (getAgentsDir layout comments)
- tests/bug-384-agents-runtime-aware.test.cjs (require path to runtime lib)
Verified: guard 0 violations; build green.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#604): exclude gsd-core/ path segments from bug-3683 command cross-ref invariant
The #614 runtime-launcher shim added to discuss-phase.md references
`${_GSD_RUNTIME_ROOT}/gsd-core/bin/...`. bug-3683's REF_PATTERN excluded path-y
refs only via lookbehind, but `}` precedes `/gsd-core/` in the shim, so it
mis-read the directory path as a dangling `/gsd-core` command ref (same class as
the #604 bug-2954 fix). Added a trailing `(?![\w-]*\/)` so `/gsd-<x>/...` path
segments are not treated as slash-command references.
Verified locally on BOTH platforms before pushing:
- mac (node 26) full suite: 0 failures
- gsd-test-runner (linux, node22 image) full suite: 0 failures
- bug-3683 + bug-2954 pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#604): lazily resolve findProjectRoot in gsd-tools (harden flaky CI)
CI intermittently failed state.test's gsd-tools subprocess with
"findProjectRoot is not a function" (flip-flopping across legs; not reproducible
on mac full suite, gsd-test linux full suite, test:unit, or state.test x8).
findProjectRoot is a re-export from core.cjs (sourced from project-root.cjs);
binding it via destructure at module-load can be undefined under a load-ordering
edge. Resolve it lazily at call time via a small wrapper so the lookup happens
after core.cjs is fully initialized.
Verified green on BOTH platforms before pushing:
- mac (node 26) full suite: 0 failures
- gsd-test-runner (linux, node22) full suite: 0 failures
- state.test.cjs: 106/106; gsd-tools loads cleanly.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* fix(#604): allowlist verification-patterns.md placeholder examples in secret scan
The rename git-mv'd references/verification-patterns.md into gsd-core/, pulling
it into the secret-scan diff. It documents stub/placeholder RED-FLAG env-var
examples (illustrative Stripe test-key / database-URL / API-key placeholders) —
not real credentials. Added it to .secretscanignore with the strict annotation,
mirroring the existing gsd-core/workflows/plan-phase.md exception.
Verified locally: secret-scan-lint --strict OK; secret-scan --diff origin/next
exits 0 with 0 findings.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
