kb-status
Skill0 starsChanged 26 days agoMITView on GitHub
Health of the knowledge base in one table plus the next three actions. Use to see what needs attention (lint errors, unowned open points, unchecked extractions, files waiting in inbox/).
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- askSkill
- captureSkill
- impactSkill
- ingestSkill
- init-brainSkill
- review-noteSkill
The file
Files
uv run python tools/kb/refresh.py- Print the
AUTO:statusblock ofknowledge/index.mdand the lint summary line, as they are. - At most 3 bullets of next actions, by value: lint errors to fix; open OPs with owner
TBD(SELECT id, title FROM kb.reg_open_points WHERE owner = 'TBD' AND status = 'open'); large unchecked extractions (SELECT path, chars FROM kb.catalog WHERE status = 'extracted' ORDER BY chars DESC LIMIT 3); files still waiting ininbox/. No other commentary.
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.