promptwheel-ai-logbookSAFE

[](https://github.com/promptwheel-ai/logbook/actions/workflows/ci.yml) [](https://www.npmjs.com/package/@promptwheel/logbook)

Coding agents often skip git history. It is large, and an arbitrary slice can give the wrong picture.

Every feature gets added by someone who can read the code but not the decisions behind it: the module that was rewritten three times, the approach that was tried and reverted, the "fix" last quarter that was actually a skipped test. Fresh agent sessions often start without those decisions. Code maps (Graphify and friends) tell them where things are, not what happened. The logbook mines the existing git history — up to the newest 20,000 commits — and writes a compact recall layer that your agent is instructed to consult.

npx -y @promptwheel/logbook init

One line: it reads the history, writes the brief, and adds a history workflow to your agent config (AGENTS.md, CLAUDE.md, or .cursorrules).

1,326 commits · 322 files · 7.3 years · 354 authors

✓ wrote LOGBOOK.md     hotspots · do-not-retry · suppression ledger
✓ wrote events.jsonl   1,326 structured events
✓ wrote JOURNEY.md     the repo's story, told back to you

Single file. Zero npm dependencies. It never touches your source code or git history, and no repository data leaves your machine — it writes only its own brief files (and init adds a block to your agent config).

Why "logbook"

Because you need a compact index of the decisions its detectors can recover without pulling every book out of the library. In a random 400-repo sample of the top 2,500 GitHub repositories, 34% of full logs exceeded a 150k-token context estimate. Logbook