iroha924

iroha924/mumei

Hook

Runs after the context is compacted for manual and auto tool calls, executing post-compact-validate.sh via bash. From iroha924/mumei.

iroha924/mumei

Hook

Runs on the FileChanged event for requirements.md, tasks.md and state.json tool calls, executing file-changed-validate.sh via bash. From iroha924/mumei.

iroha924/mumei

Hook

Runs on the CwdChanged event, executing cwd-changed-detect.sh via bash. From iroha924/mumei.

iroha924/mumei

Hook

Runs after instructions files are loaded for session_start and compact tool calls, executing instructions-loaded-audit.sh via bash. From iroha924/mumei.

iroha924/mumei

Hook

Runs to expand your prompt before the agent sees it for ^mumei:shelve$ tool calls, executing userprompt-expansion-context.sh via bash. From iroha924/mumei.

iroha924/mumei

Hook

Runs on the ConfigChange event for user_settings, project_settings, local_settings, policy_settings and skills tool calls, executing config-change-audit.sh via bash. From iroha924/mumei.

iroha924/mumei

Hook

Runs when a session ends, executing session-end-audit.sh via bash. From iroha924/mumei.

iroha924/mumei

Hook

Runs when a tool call fails for Bash, Edit, Write and MultiEdit tool calls, executing post-tool-failure-audit.sh via bash. From iroha924/mumei.

iroha924/mumei

Hook

Runs when a subagent starts for ^(mumei:)?(adversarial-reviewer, design-reviewer, requirements-reviewer, security-reviewer, spec-compliance-reviewer, tasks-reviewer, issue-validator and memory-curator)$ tool calls, executing subagent-cost-log-start.sh and subagent-context-inject.sh via bash (2 commands). From…

iroha924/mumei

Hook

Runs when a subagent finishes for ^(mumei:)?(adversarial-reviewer, design-reviewer, requirements-reviewer, security-reviewer, spec-compliance-reviewer, tasks-reviewer, issue-validator and memory-curator)$ tool calls, executing subagent-cost-log.sh via bash. From iroha924/mumei.

iroha924/mumei

Skill Claude CodeCodex

Render a detailed reliability view of a mumei feature — pass^3 over the most recent 10 trials plus a table of the last 10 trial rows from reliability-log.jsonl. Triggered only by explicit user invocation /mumei:attest . Reads .mumei/specs/ /reliability-log.jsonl or .mumei/plans/ /reliability-log.jsonl via…

iroha924/mumei

Skill Claude CodeCodex

The mumei orchestrator. For new features, presents a vehicle picker — spec (full SDD workflow: clarification → requirements → design → tasks each auto-reviewed up to 3 iterations → single user approval → Wave-by-Wave implementation → 4-stage review) or plan (Claude Code plan-mode wrapper: hand off to plan mode…

iroha924/mumei

Skill Claude CodeCodex

Render a one-line reliability summary of the active mumei feature (or a specified one). Prints | pass^3: (n= , window=10, k=3) to stdout — exactly one line, no headers. Triggered only by explicit user invocation /mumei:glance (no args reads .mumei/current) or /mumei:glance . Outputs no active feature to stdout (not…

iroha924/mumei

Skill Claude CodeCodex

This skill should be used BEFORE any feature design. It runs structured gleaning with the user — asking 5 high-leverage questions per round, up to 3 rounds, to extract Goal / Scope / Constraints / Edges / Done. Output is saved to .mumei/scratch/ .md and used as input for /mumei:compose. Triggers include "I want to add…

iroha924/mumei

Skill Claude CodeCodex

One-time setup for a project to use mumei. Detects existing CLAUDE.md / .claude/rules/, proposes additions about mumei's expectations (phase gates, Wave commits, review pipeline), and applies them with user approval. Triggers when the user says "set up mumei", "install mumei", or "initialize mumei in this project".

iroha924/mumei

Skill Claude CodeCodex

Generate a retrospective markdown for an archived (or about-to-be-archived) mumei feature. Reads requirements / design / tasks / spec-reviews / reviews / cost-log and emits muse.md with AC count, Wave count, review iter counts, fix-spiral detection, token cost, cache hit rate, and hook firing breakdown. Triggered by…

iroha924/mumei

Skill Claude CodeCodex

Plan-vehicle review pipeline. Runs Stage 0 detector (semgrep + osv-scanner) plus security-reviewer and adversarial-reviewer in parallel against the current diff, validates each finding via issue-validator, aggregates a verdict, and writes a review JSON to .mumei/plans/ /reviews/ .json. Triggers when the user invokes…

iroha924/mumei

Skill Claude CodeCodex

Use when the user wants a one-shot, strongest-available code review of the current diff WITHOUT the full mumei spec/plan workflow — including users who drive their own spec or are doing a change too small to plan. Reviews git diff $(git merge-base HEAD) (PR-pushed commits + uncommitted changes) through the shared…

iroha924/mumei

Skill Claude CodeCodex

Moves a completed feature directory to .mumei/archive/ / / once the feature reaches phase=done. Auto-detects the active vehicle by checking .mumei/specs/ / first, then .mumei/plans/ /. Triggers when the user explicitly shelves a feature or when /mumei:compose or /mumei:peruse finishes with verdict=PASS and the user…