> and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.
npx skills add https://github.com/huytieu/COG-second-brain --skill retro
Every non-tiny shipped or escalated run gets a retro. Retro is advisory but strongly expected: it is how the harness improves.
/ultragoal phase (one retro per phase)/retro <run-dir or spec path>Read:
04-projects/harness/runs/<id>/evidence/ (ledger, checkpoints.tsv, CP-* files).claude/logs/loop-ledger.tsv (last rows for this run)04-projects/<goal>/STATUS.md if an ultragoal phaseFor each CP the lane required, mark Expected vs Actual vs Gap:
| CP | tiny | normal | full |
|---|---|---|---|
| CP-1 spec | skip | required | required |
| CP-3v component | skip | required | required |
| CP-4 integration | skip | skip | required if multi-task |
| CP-5 acceptance | if mutate | required | required |
| CP-6 ship | if external | if external | required |
Ask:
Copy 04-projects/harness/templates/retro.md to:
04-projects/harness/retro/YYYY-MM-DD-<slug>.md
Fill all sections. Action items get IDs (AI-01…).
AI-n rows to 04-projects/harness/BACKLOG.md if harness workAC-n## Checkpoint log CP-7 rowbash .claude/lib/checkpoint.sh record <run-dir> CP-7 PASS "retro: <path>"TL;DR: outcome, top lesson, top action item, retro path.
Take huytieu/cog-second-brain-retro from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.