Don't re-derive what past-you already figured out.

vibebook plugin turns your past Claude Code and VS Code Copilot Chat sessions into a searchable book of decisions, dead ends, and fixes. Run /vibebook once a week to digest; run /vibebook-recall before any non-trivial task to surface what's relevant.

Claude Code plugin Self-contained · No external service MIT

Install View on GitHub

The friction this removes

Every coding session your AI agent runs is a one-shot. The next session, the next agent, the next morning — none of them remember what you debugged yesterday. They re-derive every architecture decision, re-discover every Mac quirk, re-read code you've already explained twice.

Your Claude Code session-history is right there in ~/.claude/projects/. vibebook reads it, structures it, and lets future sessions stand on it.

Two slash commands

`/vibebook`

Walks ~/.claude/projects/ and your Copilot Chat history, then digests each session into per-project artifacts:

chronicles — one per work thread, with AI-first frontmatter (files_touched, commits, decisions, blockers, status) plus a 4-section body (Context / What worked / Dead ends / Open questions).
topics — one per subsystem, cross-references the chronicles that contributed.

Auto-detects project from cwd; in non-project dirs it asks before doing a full sweep.

`/vibebook-recall`

Three-stage progressive recall before new work. Designed for AI agents to consume cheaply:

Stage 1 — project's topic list (~5 KB).
Stage 2 — chronicles in one topic, frontmatter only (no bodies).
Stage 3 — Read the chronicles you actually need, full body.

Cheap to invoke; you can fire stage 1 on every "how did we…" question without thinking about token cost.

What recall actually does — a worked example

Recall isn't something you remember to invoke. It's something Claude reaches for itself when it notices the task probably overlaps with past work. Imagine you say to Claude:

> this integration test has been flaky for a week, fix it

You didn't ask "have we seen this before". You asked for a fix. But Claude reads "flaky test" as a recall trigger and runs /vibebook-recall stage 1 first — a 5 KB topic list, cheap. Stage 1 surfaces a topic flaky-tests with two contributing chronicles. Claude drills into the relevant one and pulls back a structured summary:

Real root cause (last time) — the test assumed UTC; CI runner was on America/Los_Angeles. Failed only between 4 PM and midnight local time, looked random.
Fix that shipped — wrap the date assertion in a fixed-zone helper; commit a1b2c3d.
Dead ends already explored — added a mutex around the shared fixture (no effect; not a race); bumped the network timeout to 30 s (no effect; no network involved); bisected dependencies (waste — the failure predates the suspect upgrade).
Open question left — three other tests in the same file use raw new Date(); they will hit the same trap eventually.

Now Claude tells you up front:

Per chronicle flaky-test-investigation: this same suite was flaky in
March, root cause was a timezone assumption. The mutex / timeout /
bisect paths were already tried and ruled out. Want me to apply the
same fixed-zone fix here, plus prophylactically patch the other
three suspect call sites flagged in the chronicle?

That last paragraph is what makes recall worth invoking unprompted. Without it, Claude would have walked the same dead ends — git log would have shown a "fix flaky test" commit, but commit messages don't record what you ruled out along the way. Chronicles preserve both halves; recall surfaces them before Claude burns context exploring them again.

Install

Two commands inside Claude Code:

/plugin marketplace add june9593/vibebook-plugin
/plugin install vibebook

That's it. Open any Claude Code session and run /vibebook to digest your local sessions, or /vibebook-recall to surface past notes. No npm install, no external service, your data stays in ~/.vibebook/.

Files written

Everything stays under ~/.vibebook/session-repo/:

raw_sessions/<tool>/<project>/<date>/*.{md,raw.json} — rendered copies of your sessions
book/<project>/{chronicle,topics}/*.md — digested book
.vibebook/index.json — per-session entry index
.vibebook/index.book.json — chronicle / topic catalog

The plugin does not create or modify .git/ or any of the optional npm CLI's config files — those are owned by the cross-device sync tool when present.

Cross-device sync (optional)

To carry your sessions across multiple machines, install the optional vibebook npm CLI:

npm i -g vibebook
vibebook init

It syncs ~/.vibebook/session-repo/ to a private GitHub repo across your devices. The plugin and the npm CLI cooperate on the same spool path with sessionId-keyed entries — install one, both, or neither based on what you need.

vibebook npm CLI →

Memex hand-off (optional)

For atomic Zettelkasten cards (one insight per card with backlinks, organize, orphan detection), vibebook delegates to memex. Install it and the /vibebook skill will offer to chain /memex-retro after writing chronicles. /vibebook-recall folds memex's catalog into stage 1 so agents see both layers in one triage pass.

Memex is optional — vibebook works fine without it; you just won't have an atomic-card layer.

Project

MIT licensed · 22-test suite covering autonomy, scan, orchestrator and config tolerance · Self-contained 386 KB esbuild bundle, no runtime npm install required.