agentleFS
Sign inStart free
dagonetdagonet/claude-code-toolkit/skills/retro-review/SKILL.md

retro-review

Skill4 starsChanged 7 months agoMITView on GitHub

Review the local subagent-failure retro ledger, user-level config drift, and which consumer repos are behind the toolkit version. Triggers on /cct:retro-review.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. peterwangze/software-project-governance★ 2same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository11 other files it gives its agents.

The file

Create a free account to mount
Files
SKILL.md

Retro Review

The local counterpart to the toolkit-nightly-check routine. A cloud routine runs over a clone and cannot see ~/.claude, this machine's other checkouts, or anything uncommitted — which is exactly what this skill reads. That is why it is a skill you run here, not a routine.

Target project: $ARGUMENTS, or the current working directory if empty.

Steps

  1. Read the retro ledger. Slug the absolute project path exactly as hooks/retro-ledger.sh does — replace every :, \, /, . and _ with - — then read ~/.claude/projects/<slug>/memory/retro.md. No file means no subagent has failed there; say so and continue. Group the entries by cause (a wrong tools: allowlist, an under-briefed spawn prompt, a hook), not by date.
  2. Check user-level drift. From the claude-code-toolkit checkout, run bash scripts/verify-user-level-drift.sh. It compares user-level-reference/ with the live ~/.claude/; the reference leads and the live copy follows, so DRIFT means "sync is pending", not "broken". List the drifted files.
  3. Check consumer repos. For each G:/git/*/.claude/template-manifest.json, read its recorded template version and compare with line 1 of VERSION in the toolkit checkout. List only repos strictly behind it, worst first.
  4. Write the summary to ~/.claude/projects/<slug>/memory/retro-summary.md: at most 30 lines, overwriting any previous run. One section per step, each a short list of concrete next actions ("re-copy agents/architect.md", "add Skill to tester.md tools:"). Drop any section that found nothing. If all three are clean, write a single line saying so.

Running it unattended

env -u CLAUDE_CODE_SESSION_ID claude -p "/cct:retro-review" --permission-mode auto      # from the project directory

(env -u CLAUDE_CODE_SESSION_ID keeps a nested run from deleting an enclosing session's cct marker when it ends.)

Schedule that with Windows Task Scheduler or cron. It is a local headless session, not a cloud routine: it needs this machine's ~/.claude and its sibling checkouts, so it cannot be moved to /schedule. Keep it read-only — this skill reports, and the fixes are a separate, deliberate act.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free