Tom Boucher
1452b1275b
fix(dispatcher): rename Task→Agent in allowed-tools, workflow prose, and agent tools frontmatter
...
Fixes #3168
The Claude Code subagent dispatcher tool is named `Agent` (with `subagent_type`
parameter). The `Task*` namespace (TaskCreate, TaskList, TaskGet, TaskUpdate,
TaskOutput, TaskStop) is the separate task-tracker. GSD's commands, workflows,
and agents were partially migrated and still referenced `- Task` / `Task(` in
55 files, causing orchestrators to silently fall back to inline execution when
no `Task` tool appeared on their tool surface.
Changes:
- `commands/gsd/*.md` allowed-tools: replaced `- Task` with `- Agent` in 24
files; removed duplicate `- Task` from autonomous.md (already had `- Agent`)
- `get-shit-done/workflows/*.md`: replaced dispatcher `Task(` → `Agent(` in
29 workflow files (~133 call sites); TaskCreate/List/Get/Update/Output/Stop
left untouched
- `agents/gsd-debug-session-manager.md`: replaced `Task` → `Agent` in tools
frontmatter (the only remaining agent with the wrong name)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-05-06 15:00:08 -04:00
Tom Boucher
81f9534b5a
feat(adr-0002): command contract validation module + prose @-ref cleanup + workflow extraction
...
ADR-0002: commands/gsd/*.md contract now enforced at two layers:
LINT (scripts/lint-command-contract.cjs — new CI step):
- name: present, starts with gsd: or gsd-
- description: non-empty
- allowed-tools: non-empty, all entries canonical
- execution_context @-refs: resolve on disk, no trailing prose on same line
- handles both @~/ and $HOME/ path prefixes
TEST (tests/command-contract.test.cjs — 361 assertions):
- Behavioral contract for all 65 command files
- Replaces scattered coverage in enh-2790 + bug-3135
- Per-command per-rule test — one failure names the exact file + rule
CI (.github/workflows/test.yml):
- 'Lint — command contract (ADR-0002)' step added to lint-tests job
PROSE @-REF CLEANUP (39 command files, ~900 tokens/invocation recovered):
- Removed redundant @~/.claude/get-shit-done/... paths from <process> prose
- execution_context block is now the single authoritative load declaration
- Routing commands (sketch, spike, update, pause-work, etc.) keep routing
instructions; only the inert path token is stripped
WORKFLOW EXTRACTION (debug.md + thread.md, ~15,000 chars / ~3,750 tokens):
- get-shit-done/workflows/debug.md: full process extracted from commands/gsd/debug.md
- get-shit-done/workflows/thread.md: full process extracted from commands/gsd/thread.md
- Command files reduced to frontmatter + objective + execution_context + context
- debug.md: 9,603 → 1,703 chars; thread.md: 7,868 → 585 chars
RENAME:
- get-shit-done/workflows/extract_learnings.md → extract-learnings.md
(aligns with hyphen convention of all other workflow files)
DOCS:
- docs/INVENTORY.md: count 85→87, new rows, rename row, fix add-todo --backlog attribution
- docs/INVENTORY-MANIFEST.json: +debug.md +thread.md +extract-learnings.md -extract_learnings.md
Closes ADR-0002 implementation.
2026-05-05 15:18:13 -04:00
Bantuson
2154e6bb07
feat: add security-first enforcement layer with threat-model-anchored verification
...
Adds /gsd:secure-phase command and gsd-security-auditor agent as a
threat-model-anchored security gate parallel to Nyquist validation.
New files:
- agents/gsd-security-auditor.md — verifies PLAN.md threat mitigations
exist in implemented code; SECURED/OPEN_THREATS/ESCALATE returns
- commands/gsd/secure-phase.md — retroactive command, mirrors validate-phase
- get-shit-done/workflows/secure-phase.md — enforcing gate: threats_open > 0
blocks phase advancement; accepted risks log prevents resurface
- get-shit-done/templates/SECURITY.md — per-phase threat register artifact
Modified:
- config.json — security_enforcement (absent=enabled), security_asvs_level,
security_block_on parallel to nyquist_validation pattern
- VALIDATION.md — Threat Ref + Secure Behavior columns in verification map
- gsd-planner.md — <threat_model> block in PLAN.md format + quality gate
- gsd-executor.md — Rule 2 threat model reference + ## Threat Flags scan
- gsd-phase-researcher.md — ## Security Domain mandatory research section
- plan-phase.md — step 5.55 Security Threat Model Gate
- execute-phase.md — security gate announcement in aggregate step
- verify-work.md — /gsd:secure-phase surfaced in completion routing
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-25 11:18:30 +02:00
