Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches. Triggered by /harvest, SessionEnd hook staging, or nightly enhance. Never writes durable knowledge without your approval.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Adapted from dwarves-kit harvest hook + vault lizard pipeline. Prevents tacit knowledge dying in the transcript.
/harvest — manual end-of-session/harvest promote — curate staging → lizard drafts (uses harvest-curator)stop hook (.cursor/hooks/harvest-stager.sh)Scan the current session for:
Append to 04-projects/harness/harvest/staging-<YYYY-MM-DD>.md:
## <HH:MM> — <trigger>
- type: correction|fact|process|skill-gap
- source: <file or "session">
- text: <one paragraph max>
- proposed_home: <path or "new lizard note">
Dedup: skip if same fact already in staging today or in 05-knowledge.
/harvest promote)Spawn harvest-curator (Sonnet). It writes /tmp/harvest-curate-<date>.md.
Lead (Opus) presents to the user:
05-knowledge/lizard/YYYY-MM-DD-<slug>.mdOnly after approval: write durable files. Update 05-knowledge/lizard/index.md.
One line to 01-daily/journal/<today>.md:
Harvest: <n> staged, <m> promoted, <k> folded
/memory-hygiene monthly for environment-dependent facts in ~/.claude/.../memory/.If you want harvest to run unattended, schedule a job that invokes the skills in this order. There is nothing to install first, since COG ships no hooks.
/memory-hygiene
/harvest promote # only if the staging file is non-empty
/content-factory # only if scheduled
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis
The English summary is being prepared. Showing the original description.
Quick capture of raw thoughts with intelligent domain classification and competitive intelligence extraction
The English summary is being prepared. Showing the original description.
Run one task through the V-model verification loop: CP-2 plan → CP-3 build → CP-3v component verify → CP-4 integration verify (full lane) → CP-5 acceptance. The worker never grades its own homework; evidence rows trace back to AC-n. Opt-in: invoke with /closed-loop or by asking for the closed loop, proper verification, or an evidence trail. Ordinary work does not run this.
The English summary is being prepared. Showing the original description.
Deep-dive 7-day analysis across all data sources for weekly reviews, board prep, and strategic planning
The English summary is being prepared. Showing the original description.
Autonomous content pipeline - scout announcements in your field, triage by trend momentum and personal angle, produce posts/blogs/videos in your voice with ledger-based dedup, hard volume caps, and screenshot-verified publishing
The English summary is being prepared. Showing the original description.
Create user stories with duplicate checking across any project tracker (Linear, GitHub Issues, Jira)
The English summary is being prepared. Showing the original description.