Menu
Execute an epic plan phase-by-phase, inline by default with opt-in worker spawns per task annotation
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
| name | run-epic |
| description | Execute an epic plan phase-by-phase, inline by default with opt-in worker spawns per task annotation |
| argument-hint | [--status] [--skip-tests] [--phase N] |
| when_to_use | Running a multi-phase epic created by /devloop:epic |
| allowed-tools | ["Read","Write","Edit","Grep","Glob","Bash","Bash(${CLAUDE_PLUGIN_ROOT}/scripts/*.sh:*)","Monitor","Agent","AskUserQuestion","Skill"] |
Execute an epic phase-by-phase. Tasks run inline by default; subagents are spawned per task [model:X] annotation (same pattern as /devloop:run). You are the orchestrator -- execute the phase, validate tests, commit, promote the next phase.
Read .devloop/epic.json.
/devloop:epic <topic> to create one." STOP.--status: Display phase tracker and STOP.status: "complete": "Epic already complete." STOP.--phase N: Override current phase and re-promote.Read .devloop/plan.md. Verify **Phase**: matches epic.json.current_phase.
${CLAUDE_PLUGIN_ROOT}/scripts/promote-phase.sh --force.[x]: skip to Step 5 (already completed).Read epic.json for context (user_stories, invariants, negative_cases, test_command). Keep this context in working memory while executing the phase.
Execute plan.md tasks inline, following the same model-annotation pattern as /devloop:run:
[model:haiku] tasks: spawn devloop:haiku-worker.[model:sonnet] tasks: spawn devloop:swarm-worker (sonnet).[depends:N.M] constraints and [parallel:X] groupings.Use the epic context to guide your work:
test_command after implementation tasks.Fallback (opt-in only): If the phase is very large (>15 tasks) and session context is already heavy, you MAY delegate the whole phase to a single sonnet subagent in a fresh context. This is a last-resort fresh-context reset, not the default path.
Run ${CLAUDE_PLUGIN_ROOT}/scripts/check-plan-complete.sh .devloop/plan.md.
Run tests (unless --skip-tests or test_command is null).
Use Monitor for real-time streaming when test_command matches a known long-running pattern
(test suites: npm test, pytest, go test, cargo test, etc.; builds; full-codebase linting).
Example:
Monitor({ description: "epic phase tests", command: "<test_command> 2>&1 | grep --line-buffered -E 'PASS|FAIL|Error|ok|error|passed|failed'", timeout_ms: 300000, persistent: false })
Fallback: if Monitor errors, run test_command with Bash directly.
git add changed files, commit with feat: phase N -- phase-name.epic.json: mark phase "complete", record commit hash, increment current_phase.epic.md Phase Tracker table.${CLAUDE_PLUGIN_ROOT}/scripts/promote-phase.sh --force.Report:
Phase N complete and committed.
Phase M loaded: "Phase Name" (X tasks)
The next phase is already loaded in plan.md. AskUserQuestion:
/clear, then /devloop:run-epic to execute Phase M." STOP.run-epic is resumable. epic.json is the source of truth:
/clear: reads epic.json, resumes from correct phase.If the repo is in a broken state (e.g. orphaned changes, mismatched plan), run-epic will detect the mismatch in Step 2 and re-promote the correct phase. Tests in Step 4 catch implementation issues before committing.
Now: Load epic state and begin.
Create or update the project security baseline, profile, suppressions file, and gitignore entries for security scans
Fix or guide remediation for a specific security finding from the latest scan report
Run a security assessment using deterministic static analysis tools with LLM-powered triage
Inspect and optionally install security scanning tools for the security plugin
Query ctx memory and inject results into context
Show ctx memory status (node counts, types, tiers, tokens)