菜单
Show current task state, lifecycle stage, audit results, and open gaps.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Run checkpoint audit, repair any findings, then reach DONE — all in one shot. Use after /dynos-work:execute.
Execute the approved plan. Orchestrates execution graph segments through specialized executor agents, including dependency management and error recovery.
Internal: Data Executor. Implements ETL, analytics, backfills, data quality, reconciliation, and data pipeline changes. Write evidence on completion.
Internal: Infrastructure Executor. Implements deployment, CI/CD, container, IaC, and environment configuration changes. Write evidence on completion.
Internal: Observability Executor. Implements logs, metrics, traces, alerts, dashboards, and reliability instrumentation. Write evidence on completion.
Internal: Release Executor. Implements version/changelog updates, rollout flags, rollback plans, release notes, and migration sequencing. Write evidence on completion.
| name | status |
| description | Show current task state, lifecycle stage, audit results, and open gaps. |
Show the current state of the active dynos-work task.
.dynos/ (manifest.json with stage not DONE/FAILED). If available in this repo, use "${CODEX_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}/bin/dynos" ctl active-task.dynos-work Status Report
========================
Task: task-20260327-001
Title: [First 80 chars of task]
Stage: CHECKPOINT_AUDIT
Risk: medium
Snapshot: dynos/task-20260327-001-snapshot
Lifecycle Progress:
✓ DISCOVERY
✓ DISCOVERY
✓ DESIGN_REVIEW
✓ SPEC_NORMALIZATION
✓ SPEC_REVIEW (user-approved)
✓ PLANNING
✓ PLAN_REVIEW (user-approved)
✓ PLAN_AUDIT
✓ TDD_GATE
✓ PRE_EXECUTION_SNAPSHOT
✓ EXECUTION (3/3 segments complete)
✓ TEST_EXECUTION (all tests passed)
→ CHECKPOINT_AUDIT (in progress)
○ FINAL_AUDIT
Execution Progress:
Segments: [N]/[total] complete
Current batch: [seg-003-ui, seg-004-tests]
Completed: [seg-001-db, seg-002-backend]
Acceptance Criteria: [N]/[total] covered
Latest Audit Results:
spec-completion: PASS | FAIL | not yet run
security: PASS | FAIL | not yet run
ui: PASS | FAIL | SKIPPED | SKIPPED_REUSE | not yet run
code-quality: PASS | FAIL | SKIPPED | SKIPPED_REUSE | not yet run
db-schema: PASS | FAIL | SKIPPED | SKIPPED_REUSE | not yet run
Open Blocking Findings:
[finding-id] [auditor]: [description] ([file:line])
Test Results: PASS | FAIL ([N] failing tests) | not yet run
Repair Cycle: [N] ([N] findings resolved, [N] remaining)
Next command: [one of the below based on current stage]
Recent Activity (last 10 lines of execution-log.md):
[last 10 log entries, or "No execution log yet" if file doesn't exist]
Always end the status report with a "Next:" line based on current stage:
| Stage | Next command |
|---|---|
| PLANNING | /dynos-work:plan (or /dynos-work:start for new tasks) |
| PLAN_REVIEW | /dynos-work:plan |
| PLAN_AUDIT | /dynos-work:plan |
| PRE_EXECUTION_SNAPSHOT | /dynos-work:execute |
| EXECUTION | /dynos-work:execute |
| TEST_EXECUTION | /dynos-work:execute |
| CHECKPOINT_AUDIT | /dynos-work:audit |
| REPAIR_PLANNING | /dynos-work:audit (or /dynos-work:repair for a specific finding) |
| REPAIR_EXECUTION | /dynos-work:audit (or /dynos-work:repair for a specific finding) |
| FINAL_AUDIT | /dynos-work:audit |
| DONE | Task complete |
| FAILED | Review failure report, consider /dynos-work:repair or rollback |