* docs: add design spec for /gsd-ultraplan-phase beta command
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: add /gsd-ultraplan-phase [BETA] command
Offloads GSD plan phase to Claude Code's ultraplan cloud infrastructure.
Plan drafts remotely while terminal stays free; browser UI for inline
comments and revisions; imports back via existing /gsd-import --from.
Intentionally isolated from /gsd-plan-phase so upstream ultraplan changes
cannot break the core planning pipeline.
Closes#2374
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: resolve 5 pre-existing test failures before PR
- ARCHITECTURE.md: update command count 75→80 and workflow count 72→77
(stale doc counts; also incremented by new ultraplan-phase files)
- sketch.md: add TEXT_MODE plain-text fallback for AskUserQuestion (#2012)
- read-guard.test.cjs: clear CLAUDECODE env var alongside CLAUDE_SESSION_ID
so positive-path hook tests pass when run inside a Claude Code session
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs: add BETA.md with /gsd-ultraplan-phase user documentation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: address CodeRabbit review — MD040 fence labels and sketch.md TEXT_MODE duplicate
- Add language identifiers to all unlabeled fenced blocks in
ultraplan-phase.md and design spec (resolves MD040)
- Remove duplicate TEXT_MODE explanation from sketch.md mood_intake step
(was identical to the banner step definition)
- Make AskUserQuestion conditional explicit in mood_intake prose
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The hook skips its advisory on two env vars: CLAUDE_SESSION_ID and
CLAUDECODE. runHook() cleared CLAUDE_SESSION_ID but inherited CLAUDECODE
from process.env, so tests run inside a Claude Code session silently
no-oped and produced no stdout, causing JSON.parse to throw.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds tiered agent-size-budget test to prevent unbounded growth in agent
definitions, which are loaded verbatim into context on every subagent
dispatch. Extracts two duplicated blocks (mandatory-initial-read,
project-skills-discovery) to shared references under
get-shit-done/references/ and migrates the 5 top agents (planner,
executor, debugger, verifier, phase-researcher) to @file includes.
Also fixes two broken relative @planner-source-audit.md references in
gsd-planner.md that silently disabled the planner's source audit
discipline.
Closes#2361
Co-authored-by: Claude Opus 4.7 <noreply@anthropic.com>
* feat: add /gsd-spec-phase — Socratic spec refinement with ambiguity scoring (#2213)
Introduces `/gsd-spec-phase <phase>` as an optional pre-step before discuss-phase.
Clarifies WHAT a phase delivers (requirements, boundaries, acceptance criteria) with
quantitative ambiguity scoring before discuss-phase handles HOW to implement.
- `commands/gsd/spec-phase.md` — slash command routing to workflow
- `get-shit-done/workflows/spec-phase.md` — full Socratic interview loop (up to 6
rounds, 5 rotating perspectives: Researcher, Simplifier, Boundary Keeper, Failure
Analyst, Seed Closer) with weighted 4-dimension ambiguity gate (≤ 0.20 to write SPEC.md)
- `get-shit-done/templates/spec.md` — SPEC.md template with falsifiable requirements
(Current/Target/Acceptance per requirement), Boundaries, Acceptance Criteria,
Ambiguity Report, and Interview Log; includes two full worked examples
- `get-shit-done/workflows/discuss-phase.md` — new `check_spec` step detects
`{padded_phase}-SPEC.md` at startup; displays "Found SPEC.md — N requirements
locked. Focusing on implementation decisions."; `analyze_phase` respects `spec_loaded`
flag to skip "what/why" gray areas; `write_context` emits `<spec_lock>` section
with boundary summary and canonical ref to SPEC.md
- `docs/ARCHITECTURE.md` — update command/workflow counts (74→75, 71→72)
Closes#2213
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(worktrees): auto-prune merged worktrees in code, not prose
Adds pruneOrphanedWorktrees(repoRoot) to core.cjs. It runs on every
cmdInitProgress call (the entry point for most GSD commands) and removes
linked worktrees whose branch is fully merged into main, then runs
git worktree prune to clear stale references. Guards prevent removal of
the main worktree, the current process.cwd(), or any unmerged branch.
Covered by 4 new real-git integration tests in
tests/prune-orphaned-worktrees.test.cjs (TDD red→green).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(agents): add no-re-read critical rules to ui-checker and planner (#2346)
Closes#2346
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(agents): correct contradictory heredoc rule in read-only ui-checker
The critical_rules block instructed the agent to "use the Write tool"
for any output, but gsd-ui-checker has no Write tool and is explicitly
read-only. Replaced with a simple no-file-creation rule.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(planner): trim verbose prose to satisfy 46KB size constraint
Condenses documentation_lookup, philosophy, project_context, and
context_fidelity sections — removing redundant examples while
preserving all semantic content. Fixes CI failure on planner
decomposition size test.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Under a .kilo install the runtime root is .kilo/ and the command
directory is command/ (not commands/gsd/). Hardcoded paths produced
semantically empty intel files. Add runtime layout detection and a
mapping table so paths are resolved against the correct root.
Closes#2351
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The sliding-window pattern serialized discuss to one phase at a time
even when phases had no dependency relationship. Replaced it with a
simple predicate: every undiscussed phase whose dependencies are
satisfied is marked is_next_to_discuss, letting the user pick any of
them from the manager's recommended_actions list.
Closes#2268
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: add /gsd-spec-phase — Socratic spec refinement with ambiguity scoring (#2213)
Introduces `/gsd-spec-phase <phase>` as an optional pre-step before discuss-phase.
Clarifies WHAT a phase delivers (requirements, boundaries, acceptance criteria) with
quantitative ambiguity scoring before discuss-phase handles HOW to implement.
- `commands/gsd/spec-phase.md` — slash command routing to workflow
- `get-shit-done/workflows/spec-phase.md` — full Socratic interview loop (up to 6
rounds, 5 rotating perspectives: Researcher, Simplifier, Boundary Keeper, Failure
Analyst, Seed Closer) with weighted 4-dimension ambiguity gate (≤ 0.20 to write SPEC.md)
- `get-shit-done/templates/spec.md` — SPEC.md template with falsifiable requirements
(Current/Target/Acceptance per requirement), Boundaries, Acceptance Criteria,
Ambiguity Report, and Interview Log; includes two full worked examples
- `get-shit-done/workflows/discuss-phase.md` — new `check_spec` step detects
`{padded_phase}-SPEC.md` at startup; displays "Found SPEC.md — N requirements
locked. Focusing on implementation decisions."; `analyze_phase` respects `spec_loaded`
flag to skip "what/why" gray areas; `write_context` emits `<spec_lock>` section
with boundary summary and canonical ref to SPEC.md
- `docs/ARCHITECTURE.md` — update command/workflow counts (74→75, 71→72)
Closes#2213
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(hooks): add gsd-read-injection-scanner PostToolUse hook (#2201)
Adds a new PostToolUse hook that scans content returned by the Read tool
for prompt injection patterns, including four summarisation-specific patterns
(retention-directive, permanence-claim, etc.) that survive context compression.
Defense-in-depth for long GSD sessions where the context summariser cannot
distinguish user instructions from content read from external files.
- Advisory-only (warns without blocking), consistent with gsd-prompt-guard.js
- LOW severity for 1-2 patterns, HIGH for 3+
- Inlined pattern library (hook independence)
- Exclusion list: .planning/, REVIEW.md, CHECKPOINT, security docs, hook sources
- Wired in install.js as PostToolUse matcher: Read, timeout: 5s
- Added to MANAGED_HOOKS for staleness detection
- 19 tests covering all 13 acceptance criteria (SCAN-01–07, EXCL-01–06, EDGE-01–06)
Closes#2201
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(ci): add read-injection-scanner files to prompt-injection-scan allowlist
Test payloads in tests/read-injection-scanner.test.cjs and inlined patterns
in hooks/gsd-read-injection-scanner.js legitimately contain injection strings.
Add both to the CI script allowlist to prevent false-positive failures.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(test): assert exitCode, stdout, and signal explicitly in EDGE-05
Addresses CodeRabbit feedback: the success path discarded the return
value so a malformed-JSON input that produced stdout would still pass.
Now captures and asserts all three observable properties.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat: add /gsd-spec-phase — Socratic spec refinement with ambiguity scoring (#2213)
Introduces `/gsd-spec-phase <phase>` as an optional pre-step before discuss-phase.
Clarifies WHAT a phase delivers (requirements, boundaries, acceptance criteria) with
quantitative ambiguity scoring before discuss-phase handles HOW to implement.
- `commands/gsd/spec-phase.md` — slash command routing to workflow
- `get-shit-done/workflows/spec-phase.md` — full Socratic interview loop (up to 6
rounds, 5 rotating perspectives: Researcher, Simplifier, Boundary Keeper, Failure
Analyst, Seed Closer) with weighted 4-dimension ambiguity gate (≤ 0.20 to write SPEC.md)
- `get-shit-done/templates/spec.md` — SPEC.md template with falsifiable requirements
(Current/Target/Acceptance per requirement), Boundaries, Acceptance Criteria,
Ambiguity Report, and Interview Log; includes two full worked examples
- `get-shit-done/workflows/discuss-phase.md` — new `check_spec` step detects
`{padded_phase}-SPEC.md` at startup; displays "Found SPEC.md — N requirements
locked. Focusing on implementation decisions."; `analyze_phase` respects `spec_loaded`
flag to skip "what/why" gray areas; `write_context` emits `<spec_lock>` section
with boundary summary and canonical ref to SPEC.md
- `docs/ARCHITECTURE.md` — update command/workflow counts (74→75, 71→72)
Closes#2213
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(pattern-mapper): prevent redundant file reads and add early-stop rule (#2312)
Adds three explicit constraints to the agent prompt:
1. Read each analog file EXACTLY ONCE (no re-reads from context)
2. For files > 2,000 lines, use Grep + Read with offset/limit instead of full load
3. Stop analog search after 3–5 strong matches
Also adds <critical_rules> block to surface these constraints at high salience.
Adds regression tests READS-01, READS-02, READS-03.
Closes#2312
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(pattern-mapper): clarify re-read rule allows non-overlapping targeted reads (CR feedback)
"Read each file EXACTLY ONCE" conflicted with the large-file targeted-read
strategy. Rewrites both the Step 4 guidance and the <critical_rules> block to
make the rule precise: re-reading the same range is forbidden; multiple
non-overlapping targeted reads for large files are permitted.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(install): replace all ~/.claude/ paths in generated Codex .toml files (#2320)
installCodexConfig() only rewrote get-shit-done/-scoped paths; all other
~/.claude/ references (hooks, skills, configDir) leaked into generated .toml
files unchanged. Add three additional regex replacements to catch $HOME/.claude/,
~/.claude/, and ./.claude/ patterns and rewrite them to .codex equivalents.
Adds regression test PATHS-01.
Closes#2320
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(install): handle bare .claude end-of-string and scan all .toml files (CR feedback)
- Use capture group (\/|$) so replacements handle both ~/.claude/ and bare
~/.claude at end of string, not just the trailing-slash form
- Expand PATHS-01 test to scan agents/*.toml + top-level config.toml
- Broaden leak pattern to match ./.claude, ~, and $HOME variants with or
without trailing slash
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Closes#2301
## Root cause
graphify's JSON output uses the key `links` for edges, but graphify.cjs
reads `graph.edges` at four sites (buildAdjacencyMap, status edge_count,
diff currentEdgeMap/snapshotEdgeMap, snapshot writer). Any graph produced
by graphify itself therefore reported edge_count: 0 and adjacency maps
with no entries.
## Fix
Added `|| graph.links` fallback at all four read sites so both key names
are accepted. The snapshot writer now also normalises to `edges` when
saving, ensuring round-trips through the snapshot path use a consistent key.
## Test
Added LINKS-01/02/03 regression tests covering buildAdjacencyMap,
graphifyStatus edge_count, and graphifyDiff edge change detection with
links-keyed input graphs.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The autocompact buffer percentage was hardcoded to 16.5%. Users who set
CLAUDE_CODE_AUTO_COMPACT_WINDOW to a custom token count (e.g. 400000 on
a 1M-context model) saw a miscalibrated context meter and incorrect
warning thresholds in the context-monitor hook (which reads used_pct from
the bridge file the statusline writes).
Now reads CLAUDE_CODE_AUTO_COMPACT_WINDOW from the hook env and computes:
buffer_pct = acw_tokens / total_tokens * 100
Defaults to 16.5% when the var is absent or zero, preserving existing
behavior.
Also applies the renameDecimalPhases zero-padding fix for clean CI.
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
- uat.cjs: change result capture from \w+ to \[?(\w+)\]? so result: [pending],
[blocked], [skipped] are parsed correctly (Closes#2273)
- phase.cjs: capture zero-padded prefix in renameDecimalPhases so renamed dirs
preserve original format (e.g. 06.3-slug → 06.2-slug, not 6.2-slug)
- tests/uat.test.cjs: add regression test for bracketed result values (#2273)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
settings.md was reading and writing .planning/config.json directly while
gsd-tools config-get/config-set route to .planning/workstreams/<slug>/config.json
when GSD_WORKSTREAM is active, causing silent write-read drift (Closes#2282).
- config.cjs: add cmdConfigPath() — emits the planningDir-resolved config path as
plain text (always raw, no JSON wrapping) so shell substitution works correctly
- gsd-tools.cjs: wire config-path subcommand
- settings.md: resolve GSD_CONFIG_PATH via config-path in ensure_and_load_config;
replace hardcoded cat .planning/config.json and Write to .planning/config.json
with $GSD_CONFIG_PATH throughout
- phase.cjs: fix renameDecimalPhases to preserve zero-padded prefix (06.3 → 06.2
not 6.2) — pre-existing test failure on main
- tests/config.test.cjs: add config-path command tests (#2282)
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(handoffs): include project identity in all Next Up blocks
Adds project_code and project_title to withProjectRoot() and updates
all 30 Next Up headings across 18 workflow files to include
[PROJECT_CODE] PROJECT_TITLE suffix for multi-project clarity.
Closes#1948
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(review): add withProjectRoot tests and fix placeholder syntax (#1951)
Address code review feedback:
- Add 4 tests for project_code/project_title injection in withProjectRoot()
- Fix inconsistent placeholder syntax in continuation-format.md canonical
template (bare-brace → shell-dollar to match variant examples)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* fix(phase): preserve zero-padded prefix in renameDecimalPhases
Captures the zero-padded prefix (e.g. "06" from "06.3-slug") with
(0*${baseInt}) so renamed directories keep their original format
(06.2-slug) instead of stripping padding (6.2-slug).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Brandon Higgins <brandonscotthiggins@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Extends /gsd-progress with opt-in --forensic mode that appends a
6-check integrity audit after the standard routing report. Default
behavior is byte-for-byte unchanged — the audit only runs when
--forensic is explicitly passed.
Checks: (1) STATE vs artifact consistency, (2) orphaned handoff files,
(3) deferred scope drift, (4) memory-flagged pending work, (5) blocking
operational todos, (6) uncommitted source code. Emits CLEAN or
N INTEGRITY ISSUE(S) FOUND verdict with concrete next actions.
Closes#2189
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds --all to /gsd-discuss-phase so users can skip the AskUserQuestion
area-selection step and jump straight into discussing all gray areas
interactively. Unlike --auto, --all does NOT auto-advance to plan-phase —
it only eliminates the selection friction while keeping full interactive
control over each discussion.
Closes#2188
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* docs: sync ARCHITECTURE.md command count to 74
commands/gsd/ has 74 .md files; the two count references in
ARCHITECTURE.md still said 73. Fixes the command-count-sync
regression test.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix: embed model_overrides in Codex TOML and OpenCode agent files (#2256)
Codex and OpenCode use static agent files (TOML / markdown frontmatter)
rather than inline Task(model=...) parameters, so model_overrides set in
~/.gsd/defaults.json was silently ignored — all subagents fell through to
the runtime's default model.
Fix: at install time, read model_overrides from ~/.gsd/defaults.json and
embed the matching model ID into each agent file:
- Codex: model = "..." field in the agent TOML (generateCodexAgentToml)
- OpenCode: model: ... field in agent frontmatter (convertClaudeToOpencodeFrontmatter)
Also adds readGsdGlobalModelOverrides() helper and passes the result
through installCodexConfig() and the OpenCode agent install loop.
Closes#2256
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(commands): add gsd:inbox command for GitHub issue/PR triage
inbox.md was created but not committed, causing the command count
to read 73 in git while ARCHITECTURE.md correctly stated 74.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
When ROADMAP.md uses unpadded phase numbers (e.g. "Phase 1:") and
the phases/ directory uses zero-padded names (e.g. "01-auth"), the
phasesByNumber Map held two separate entries — one keyed "1" from the
ROADMAP heading scan and one keyed "01" from the directory scan —
doubling phases_total in /gsd-stats output.
Apply normalizePhaseName() to all Map keys in both the ROADMAP heading
scan and the directory scan so the two code paths always produce the
same canonical key and merge into a single entry.
Closes#2195
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The gsd-intel-updater agent writes file-roles.json, api-map.json,
dependency-graph.json, arch-decisions.json, and stack.json. But
INTEL_FILES in intel.cjs declared files.json, apis.json, deps.json,
arch.md, and stack.json. Only stack.json matched. Every query/status/
diff/validate call iterated INTEL_FILES and found nothing, reporting
all intel files as missing even after a successful refresh.
Update INTEL_FILES to use the agent's actual filenames. Remove the
arch.md special-case code paths (mtime-based staleness, text search,
.md skip in validate) since arch-decisions.json is JSON like the rest.
Update all intel tests to use the new canonical filenames.
Closes#2205
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
autonomous.md reported 11,748 tokens (over the Claude Code Read tool's 10K
limit), causing it to be read in 150-line chunks and generating a warning
on every /gsd-autonomous invocation.
Extract the 280-line smart_discuss step into a new reference file
(get-shit-done/references/autonomous-smart-discuss.md) and replace the
step body with a lean stub that directs the agent to read the reference.
This follows the established planner decomposition pattern.
autonomous.md: 38,750 → 29,411 chars (~7,350 tokens, well under 10K limit)
Fixes#2196
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Prevents infinite config-get loops on Kimi K2.5 and other models that
re-execute bash tool calls when they encounter config-get subshell patterns.
Values are now bundled into the init plan-phase JSON so step 15 of
plan-phase.md can read them directly without separate shell calls.
Closes#2192
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
The audit-open case in gsd-tools.cjs called bare output() on both the --json
and text paths. output is never in scope at the call site — the entire core
module is imported as `const core`, so every other command uses core.output().
Two-part fix:
- Replace output(...) with core.output(...) on both branches
- Pass result (the raw object) on the --json path, not JSON.stringify(result)
— core.output always calls JSON.stringify internally, so pre-serialising
caused double-encoding and agents received a string instead of an object
Adds three CLI-level regression tests to milestone-audit.test.cjs that invoke
audit-open through runGsdTools (the same path the agent uses), so a recurrence
at the dispatch layer is caught even if lib-level tests continue to pass.
Closes#2236
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
- Build completedNums from current milestone phases as before
- Also scan full rawContent for [x]-checked Phase lines across all
milestone sections (including <details>-wrapped shipped milestones)
- Phases from prior milestones are complete by definition, so any
dep on them should always resolve to deps_satisfied: true
- Add regression tests in tests/init-manager-deps.test.cjs
Closes#2267
Local installs write to .claude/settings.json inside the project, which
takes precedence over the user's global ~/.claude/settings.json. Writing
statusLine here silently clobbers any profile-level statusLine the user
configured. Guard the write with !isGlobal && !forceStatusline; pass
--force-statusline to override.
Closes#2248
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test: guard ARCHITECTURE.md component counts against drift (#2258)
Add tests/architecture-counts.test.cjs — 3 tests that dynamically
verify the "Total commands/workflows/agents" counts in
docs/ARCHITECTURE.md match the actual *.md file counts on disk.
Both sides computed at runtime; zero hardcoded numbers.
Also corrects the stale counts in ARCHITECTURE.md:
- commands: 69 → 74
- workflows: 68 → 71
- agents: 24 → 31
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(init): remove literal ~/.claude/ from deprecated root identifiers to pass Cline path-leak test
The cline-install.test.cjs scans installed engine files for literal
~/.claude/(get-shit-done|commands|...) strings that should have been
substituted during install. Two deprecated-legacy entries added by #2261
used tilde-notation string literals for their root identifier, which
triggered this scan.
root is only a display/sort key — filesystem scanning always uses the
path property (already dynamic via path.join). Switching root to the
relative form '.claude/get-shit-done/skills' and '.claude/commands/gsd'
satisfies the Cline path-leak guard without changing runtime behaviour.
Update skill-manifest.test.cjs assertion to match the new root format.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Add tests/command-count-sync.test.cjs which programmatically counts
.md files in commands/gsd/ and compares against the two count
occurrences in docs/ARCHITECTURE.md ("Total commands: N" prose line and
"# N slash commands" directory-tree comment). Counts are extracted from
the doc at runtime — never hardcoded — so future drift is caught
immediately in CI regardless of whether the doc or the filesystem moves.
Fix the current drift: ARCHITECTURE.md said 69 commands; the actual
committed count is 73. Both occurrences updated.
Closes#2257
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
PR #2038 added detect-custom-files to gsd-tools.cjs and the backup_custom_files
step to update.md, but commit 7bfb11b6 is not an ancestor of v1.36.0: main was
rebuilt after the merge, orphaning the change. Users on 1.36.0 running /gsd-update
silently lose any locally-authored files inside GSD-managed directories.
Root cause: git merge-base 7bfb11b6 HEAD returns aa3e9cf (Cline runtime, PR #2032),
117 commits before the release tag. The "merged" GitHub state reflects the PR merge
event, not reachability from the default branch.
Fix: re-apply the three changes from 7bfb11b6 onto current main:
- Add detect-custom-files subcommand to gsd-tools.cjs (walk managed dirs, compare
against gsd-file-manifest.json keys via path.relative(), return JSON list)
- Add 'detect-custom-files' to SKIP_ROOT_RESOLUTION set
- Restore backup_custom_files step in update.md before run_update
- Restore tests/update-custom-backup.test.cjs (7 tests, all passing)
Closes#2229Closes#1997
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(hooks): stamp gsd-hook-version in .sh hooks and fix stale detection regex (#2136, #2206)
Three-part fix for the persistent "⚠ stale hooks — run /gsd-update" false
positive that appeared on every session after a fresh install.
Root cause: the stale-hook detector (gsd-check-update.js) could only match
the JS comment syntax // in its version regex — never the bash # syntax used
in .sh hooks. And the bash hooks had no version header at all, so they always
landed in the "unknown / stale" branch regardless.
Neither partial fix (PR #2207 regex only, PR #2215 install stamping only) was
sufficient alone:
- Regex fix without install stamping: hooks install with literal
"{{GSD_VERSION}}", the {{-guard silently skips them, bash hook staleness
permanently undetectable after future updates.
- Install stamping without regex fix: hooks are stamped correctly with
"# gsd-hook-version: 1.36.0" but the detector's // regex can't read it;
still falls to the unknown/stale branch on every session.
Fix:
1. Add "# gsd-hook-version: {{GSD_VERSION}}" header to
gsd-phase-boundary.sh, gsd-session-state.sh, gsd-validate-commit.sh
2. Extend install.js (both bundled and Codex paths) to substitute
{{GSD_VERSION}} in .sh files at install time (same as .js hooks)
3. Extend gsd-check-update.js versionMatch regex to handle bash "#"
comment syntax: /(?:\/\/|#) gsd-hook-version:\s*(.+)/
Tests: 11 new assertions across 5 describe blocks covering all three fix
parts independently plus an E2E install+detect round-trip. 3885/3885 pass.
Approach credit: PR #2207 (j2h4u / Maxim Brashenko) for the regex fix;
PR #2215 (nitsan2dots) for the install.js substitution approach.
Closes#2136, #2206, #2209, #2210, #2212
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* refactor(hooks): extract check-update worker to dedicated file, eliminating template-literal regex escaping
Move stale-hook detection logic from inline `node -e '<template literal>'` subprocess
to a standalone gsd-check-update-worker.js. Benefits:
- Regex is plain JS with no double-escaping (root cause of the (?:\\/\\/|#) confusion)
- Worker is independently testable and can be read directly by tests
- Uses execFileSync (array args) to satisfy security hook that blocks execSync
- MANAGED_HOOKS now includes gsd-check-update-worker.js itself
Update tests to read worker file instead of main hook for regex/configDir assertions.
All 3886 tests pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
When a new milestone reuses a phase number that exists in an archived
milestone (e.g., v2.0 Phase 2 while v1.0-phases/02-old-feature exists),
findPhaseInternal falls through to the archive and returns the old
phase. init plan-phase and init execute-phase then emitted archived
values for phase_dir, phase_slug, has_context, has_research, and
*_path fields, while phase_req_ids came from the current ROADMAP —
producing a silent inconsistency that pointed downstream agents at a
shipped phase from a previous milestone.
cmdInitPhaseOp already guarded against this (see lines 617-642);
apply the same guard in cmdInitPlanPhase, cmdInitExecutePhase, and
cmdInitVerifyWork: if findPhaseInternal returns an archived match
and the current ROADMAP.md has the phase, discard the archived
phaseInfo so the ROADMAP fallback path produces clean values.
Adds three regression tests covering plan-phase, execute-phase, and
verify-work under the shared-number scenario.
Add W017 warning to cmdValidateHealth that detects linked git worktrees that are stale (older than 1 hour, likely from crashed agents) or orphaned (path no longer exists on disk). Parses git worktree list --porcelain output, skips the main worktree, and provides actionable fix suggestions. Gracefully degrades if git worktree is unavailable.
Closes#2167
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Architecture diagrams generated by gsd-phase-researcher now enforce
data-flow style (conceptual components with arrows) instead of
file-listing style. The directive is language-agnostic and applies
to all project types.
Changes:
- agents/gsd-phase-researcher.md: add System Architecture Diagram
subsection in Architecture Patterns output template
- get-shit-done/templates/research.md: add matching directive in
both architecture_patterns template sections
- tests/phase-researcher-flow-diagram.test.cjs: 8 tests validating
directive presence, content, and ordering in agent and template
Closes#2139
* fix: display relative time instead of UTC in intel status output
The `updated_at` timestamps in `gsd-tools intel status` were displayed
as raw ISO/UTC strings, making them appear to show the wrong time in
non-UTC timezones. Replace with fuzzy relative times ("5 minutes ago",
"1 day ago") which are timezone-agnostic and more useful for freshness.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
* test: add regression tests for timeAgo utility
Covers boundary values (seconds/minutes/hours/days/months/years),
singular vs plural formatting, and future-date edge case.
Addresses review feedback on #2132.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Codex install registered gsd-check-update.js in config.toml but never
copied the hook file to ~/.codex/hooks/. The hook-copy block in install()
was gated by !isCodex, leaving a broken reference on every fresh Codex
global install.
Adds a dedicated hook-copy step inside the isCodex branch that mirrors
the existing copy logic (template substitution, chmod). Adds a regression
test that verifies the hook file physically exists after install.
Closes#2153
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
Parallel `phase add` invocations each read disk state before any write
completes, causing all processes to calculate the same next phase number
and produce duplicate directories and ROADMAP entries.
The new `add-batch` subcommand accepts a JSON array of phase descriptions
and performs all directory creation and ROADMAP appends within a single
`withPlanningLock()` call, incrementing `maxPhase` within the lock for
each entry. This guarantees sequential numbering regardless of call
concurrency patterns.
Closes#2165
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(2155): add list/status/resume subcommands and security hardening to /gsd-quick
- Add SUBCMD routing (list/status/resume/run) before quick workflow delegation
- LIST subcommand scans .planning/quick/ dirs, reads SUMMARY.md frontmatter status
- STATUS subcommand shows plan description and current status for a slug
- RESUME subcommand finds task by slug, prints context, then resumes quick workflow
- Slug sanitization: only [a-z0-9-], max 60 chars, reject ".." and "/"
- Directory name sanitization for display (strip non-printable + ANSI sequences)
- Add security_notes section documenting all input handling guarantees
* feat(2156): formalize thread status frontmatter, add list/close/status subcommands, remove heredoc injection risk
- Replace heredoc (cat << 'EOF') with Write tool instruction — eliminates shell injection risk
- Thread template now uses YAML frontmatter (slug, title, status, created, updated fields)
- Add subcommand routing: list / list --open / list --resolved / close <slug> / status <slug>
- LIST mode reads status from frontmatter, falls back to ## Status heading
- CLOSE mode updates frontmatter status to resolved via frontmatter set, then commits
- STATUS mode displays thread summary (title, status, goal, next steps) without spawning
- RESUME mode updates status from open → in_progress via frontmatter set
- Slug sanitization for close/status: only [a-z0-9-], max 60 chars, reject ".." and "/"
- Add security_notes section documenting all input handling guarantees
* test(2155,2156): add quick and thread session management tests
- quick-session-management.test.cjs: verifies list/status/resume routing,
slug sanitization, directory sanitization, frontmatter get usage, security_notes
- thread-session-management.test.cjs: verifies list filters (--open/--resolved),
close/status subcommands, no heredoc, frontmatter fields, Write tool usage,
slug sanitization, security_notes
* feat(2148): add specialist_hint to ROOT CAUSE FOUND and skill dispatch to /gsd-debug
- Add specialist_hint field to ROOT CAUSE FOUND return format in gsd-debugger structured_returns section
- Add derivation guidance in return_diagnosis step (file extensions → hint mapping)
- Add Step 4.5 specialist skill dispatch block to debug.md with security-hardened DATA_START/DATA_END prompt
- Map specialist_hint values to skills: typescript-expert, swift-concurrency, python-expert-best-practices-code-review, ios-debugger-agent, engineering:debug
- Session manager now handles specialist dispatch internally; debug.md documents delegation intent
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* feat(2151): add gsd-debug-session-manager agent and refactor debug command as thin bootstrap
- Create agents/gsd-debug-session-manager.md: handles full checkpoint/continuation loop in isolated context
- Agent spawns gsd-debugger, handles ROOT CAUSE FOUND/TDD CHECKPOINT/DEBUG COMPLETE/CHECKPOINT REACHED/INVESTIGATION INCONCLUSIVE returns
- Specialist dispatch via AskUserQuestion before fix options; user responses wrapped in DATA_START/DATA_END
- Returns compact ≤2K DEBUG SESSION COMPLETE summary to keep main context lean
- Refactor commands/gsd/debug.md: Steps 3-5 replaced with thin bootstrap that spawns session manager
- Update available_agent_types to include gsd-debug-session-manager
- Continue subcommand also delegates to session manager
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(2148,2151): add tests for skill dispatch and session manager
- Add 8 new tests in debug-session-management.test.cjs covering specialist_hint field,
skill dispatch mapping in debug.md, DATA_START/DATA_END security boundaries,
session manager tools, compact summary format, anti-heredoc rule, and delegation check
- Update copilot-install.test.cjs expected agent list to include gsd-debug-session-manager
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(2136): add failing test for MANAGED_HOOKS missing bash hooks
Asserts that every gsd-*.js and gsd-*.sh file shipped in hooks/ appears
in the MANAGED_HOOKS array inside gsd-check-update.js. The three bash
hooks (gsd-phase-boundary.sh, gsd-session-state.sh, gsd-validate-commit.sh)
were absent, causing this test to fail before the fix.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(2136): add gsd-phase-boundary.sh, gsd-session-state.sh, gsd-validate-commit.sh to MANAGED_HOOKS
The MANAGED_HOOKS array in gsd-check-update.js only listed the 6 JS hooks.
The 3 bash hooks were never checked for staleness after a GSD update, meaning
users could run stale shell hooks indefinitely without any warning.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(2134): add failing test for code-review SUMMARY.md YAML parser section reset
Demonstrates bug #2134: the section-reset regex in the inline node parser
in get-shit-done/workflows/code-review.md uses \s+ (requires leading whitespace),
so top-level YAML keys at column 0 (decisions:, metrics:, tags:) never reset
inSection, causing their list items to be mis-classified as key_files.modified
entries.
RED test asserts that the buggy parser contaminates the file list with decision
strings. GREEN test and additional tests verify correct behaviour with the fix.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
* fix(2134): fix YAML parser section reset to handle top-level keys (\s* not \s+)
The inline node parser in compute_file_scope (Tier 2) used \s+ in the
section-reset regex, requiring leading whitespace. Top-level YAML keys at
column 0 (decisions:, metrics:, tags:) never matched, so inSection was never
cleared and their list items were mis-classified as key_files.modified entries.
Fix: change \s+ to \s* in both the reset check and its dash-guard companion so
any key at any indentation level (including column 0) resets inSection.
Before: /^\s+\w+:/.test(line) && !/^\s+-/.test(line)
After: /^\s*\w+:/.test(line) && !/^\s*-/.test(line)
Closes#2134
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
* test(2129): add failing tests for 999.x backlog phase exclusion
Bug A: phase complete reports 999.1 as next phase instead of 3
Bug B: init manager returns all_complete:false when only 999.x is incomplete
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
* fix(2129): exclude 999.x backlog phases from next-phase scan and all_complete check
In cmdPhaseComplete, backlog phases (999.x) on disk were picked as the
next phase when intervening milestone phases had no directory yet. Now
the filesystem scan skips any directory whose phase number starts with 999.
In cmdInitManager, all_complete compared completed count against the full
phase list including 999.x stubs, making it impossible to reach true when
backlog items existed. Now the check uses only non-backlog phases.
Closes#2129
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
