メニュー
Read-only snapshot of the current project's Ralph state. Shows story completion, the next runnable story, dependency blocks, active blockers, and /ralph-loop state. Runs in a fraction of a second; safe to invoke at any time — it touches nothing.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Cancel an active ralph-loop. Removes the loop state file so the Stop hook becomes a no-op on the next session exit. Optional --remove-hook flag also unregisters the hook from .claude/settings.local.json.
Stop-hook driven Ralph loop. Activates a session-level Stop hook that reads prd.json, picks the next incomplete story, and re-prompts the assistant to implement it via the ralph-worker skill. Loop ends when all stories pass or --max-iterations is hit.
Implements a single user story from prd.json with fresh context. Team-aware - spawns specialized agents (designers, developers, reviewers) based on story type. Used by ralph-agent orchestrator or manually for single-story implementation.
AI-powered architectural critique of an entire prd.json before the loop runs. Spawns one Backend Architect agent on the full PRD to flag ordering issues, sizing problems, missing stories, and dependency gaps that would otherwise surface as wasted retries mid-iteration. Complements `/ralph-validate` (which is static/structural) with judgment.
Autonomous coding agent that implements user stories from prd.json iteratively. Spawns specialized agent teams (designers, developers, reviewers) per story type. Works through stories one by one until all pass.
Static validator for prd.json. Checks structure, required fields, dependency consistency, acceptance criteria coverage, and detects cycles. Run before /ralph-agent or /ralph-loop to catch planning-time issues that would otherwise crash the loop mid-iteration.
| name | ralph-status |
| description | Read-only snapshot of the current project's Ralph state. Shows story completion, the next runnable story, dependency blocks, active blockers, and /ralph-loop state. Runs in a fraction of a second; safe to invoke at any time — it touches nothing. |
One-shot read of prd.json, .ralph-blocker.md, and the /ralph-loop state file. Answers "where am I?" in ~100ms without running the loop or spawning agents.
/ralph-status
/ralph-status path/to/prd.json
Invokes skills/ralph-status/status.sh. Exits 0 if prd.json is readable, 1 otherwise. Produces no side effects.
depends_on satisfied.ralph-blocker.md exists, which story, when it was blocked, and where to read the verdict/ralph-loop is active, current iteration and maxRalph Status — Task Status (feature/task-status)
────────────────────────────────────────────────────────────
Stories: 1 passing / 4 total (3 incomplete)
Next runnable: US-002 — Return status in API (backend)
Blocked by dependencies:
US-004 — Status filter (waiting on: US-002, US-003)
⛔ Blocker active: US-002 (since 2026-04-23T22:45:00Z)
Read .ralph-blocker.md for the review verdict and unblock options.
/ralph-loop active: iteration 7 / 20 (started 2026-04-23T20:00:00Z)
jq on PATHprd.json in the working directory (or passed as the first argument)