build-capture
Skill4 starsChanged 5 months agoMITView on GitHub
A hands-off daily log of everything you build in Claude Code. Once a day it reads that day's sessions and the files that changed, and appends a short entry per real build (what it is, what shipped) to a local markdown file. No /wrap, no manual step. Perfect for standups, changelogs, or a running record of what you've made.
In this repository17 other files it gives its agents.
- ai-writing-qaSkill
- build-modeSkill
- fitfoSkill
- flow-mapSkill
- generate-system-mapSkill
- imessageSkill
- leanSkill
- meta-promptSkill
- no-bullshitSkill
- plain-englishSkill
- pressure-testSkill
- problem-logSkill
- reality-checkSkill
- swipeSkill
- video-breakdownSkill
- viral-hook-creatorSkill
- working-with-claudeSkill
The file
Files
build-capture
The stuff you build in Claude Code never gets written down unless you stop and do it. You won't. This does it for you.
Once a day a cron reads that day's Claude Code sessions plus the files that changed in a folder you watch, figures out what you actually built or shipped, and appends a short entry for each to a markdown file. Hands-off. Routine chatter and pure Q&A are skipped.
What you get, per build
- Name — short title of the thing you built
- What it is — one plain sentence
- Latest — what happened today (built, shipped, fixed, refactored)
- Type (skill / script / app / fix) + date
Setup (2 minutes)
- Requires the
claudeCLI on your PATH and Python 3. - Set
WATCH_DIRto the folder you build in (default: the current repo /~/.claude/skills), andLOG_FILEfor the log (default~/build-log.md). - Install the daily cron:
(On Linux, use thecp com.example.build-capture-daily.plist ~/Library/LaunchAgents/ # edit the path inside to point at this folder, then: launchctl load ~/Library/LaunchAgents/com.example.build-capture-daily.plistcrontabline indaily-sweep.sh's header.)
Run it by hand
./daily-sweep.sh # log today's builds now
./daily-sweep.sh dry # print what it would log, write nothingHow it works
build_digest.py (pure local, no LLM) collects the last day's session text, the files that changed under WATCH_DIR, and recent git commits, into one digest. A headless claude pass reads it per SWEEP_PROMPT.md and appends the builds to your log, deduping by name so re-runs don't pile up. Additive only, it never edits past entries.
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
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.

