메뉴
Install guard hooks into user-scoped ~/.claude/settings.json. Use when the user says "install guard hooks", "set up guard hooks", or "enable guard hooks".
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Run quality checks on a task's implementation before it closes to done. Triggers: 'is this ready?', 'run the review gate', 'check my work', 'I think this is done'. Reviews code + spec adherence, runs tests/build. Design review uses taskmaster:spec-review.
Log a lightweight idea into .taskmaster/ideas/. Triggers: '/add-idea', 'save this as an idea', 'remember this idea', 'log this idea', or something worth keeping, not yet a task. Only way - not backlog_idea_create directly.
Log/update/close project bugs in .taskmaster/bugs/. Triggers: 'log a bug', 'this is a bug', 'track this defect', 'I found a bug', 'shelve this for later', 'list open bugs', 'promote B-XX', 'close B-XX'. Also for ambiguous 'issue' phrasing lacking recurring/systemic/outstanding evidence - falls back here. Only correct way to transition a project Bug.
Scan the codebase for TODO/FIXME/HACK/XXX and cross-reference the backlog. Triggers: 'check todos', 'are my todos tracked', 'scan for todos', 'todo audit', 'what's untracked'.
Write/resolve/drop project decisions in .taskmaster/decisions/. Invoke when about to write an inline option menu - route here, not Options: in chat. Also 'choose between', 'pick an option', 'decide on', 'open question', 'resolve DEC-X', 'drop DEC-X'. Only correct way - do not call backlog_decision_create directly.
Close out a work session. Triggers: 'end session', 'I'm done for today', 'let's wrap up', 'mark this task done', 'save progress'. ONLY correct way to mark tasks done/in-review with a session record.
| name | install |
| description | Install guard hooks into user-scoped ~/.claude/settings.json. Use when the user says "install guard hooks", "set up guard hooks", or "enable guard hooks". |
As of v2.7.x the guard hooks are Python scripts auto-registered by the
plugin's own hooks/hooks.json — enabling the plugin is the installation.
Do NOT copy hook scripts into ~/.claude/hooks/; detached copies go stale
and stop matching the plugin's behavior (jq is no longer required either).
Confirm the plugin is enabled (it is, if this skill is available). The
hooks register automatically at session start; there is nothing to write
into ~/.claude/settings.json.
Check that a usable Python is available — run:
python3 -c 'import sys; sys.exit(0 if sys.version_info >= (3, 9) else 1)' \
|| python -c 'import sys; sys.exit(0 if sys.version_info >= (3, 9) else 1)' \
|| py -3 -c 'import sys; sys.exit(0 if sys.version_info >= (3, 9) else 1)'
If none succeeds, tell the user the hooks will be INACTIVE (they fail open — tool calls work but nothing is guarded) and how to fix it:
winget install Python.Python.3.12brew install pythonsudo apt install python3CLAUDE_HOOKS_PYTHON to an interpreter command if Python is
installed somewhere unusual.Tell the user to restart their Claude Code session for the hooks to take effect (hook registrations are snapshotted at SessionStart).
If ~/.claude/settings.json contains old user-scoped guard entries
(commands referencing ~/.claude/hooks/guard-destructive.sh or
guard-edits.sh), offer to remove those entries and delete the copied
scripts from ~/.claude/hooks/ — the plugin's auto-registered hooks
replace them, and leaving both active runs every guard twice.