agentleFS
Brumm-LabsBrumm-Labs/kb-agents/assets/CLAUDE.md

kb-agents / assets

CLAUDE.md1 starsChanged 7 months agoMITView on GitHub

This is a knowledge base vault managed by KB Agents. Three agents are installed as Claude Code skills in .claude/skills/:

The file

Files
CLAUDE.md

Knowledge Base

This is a knowledge base vault managed by KB Agents.

Vault Structure

  • raw/ — Raw source files (articles, papers, images). Drop files here for ingestion.
    • raw/_source-index.md — Auto-maintained index of all ingested sources
  • wiki/ — Compiled knowledge (managed by the Compiler agent)
    • wiki/_index.md — Master index with all concepts, summaries, and stats
    • wiki/summaries/ — Source summaries with [[wiki-links]]
    • wiki/concepts/ — Concept articles (stub → draft → mature)
    • wiki/connections/ — Relationship documents between concepts
  • outputs/ — Generated reports, query results
  • _bmad/memory/ — Agent memory (Sanctums). Do not edit manually.

Agents

Three agents are installed as Claude Code skills in .claude/skills/:

AgentWhat to sayWhat it does
Archivist (Ingest)"Scan for new sources"Finds and normalizes files in raw/
Cartographer (Compiler)"Compile the new sources"Creates summaries, concepts, and connections in wiki/
Inspector (Linter)"Health check"Audits quality, finds broken links, suggests improvements

Common Commands

  • "Scan for new sources" — Ingest agent auto-discovers new files in raw/
  • "Compile the new sources" — Compiler processes uncompiled sources into wiki
  • "Health check" — Linter audits the entire knowledge base
  • "What do my sources say about X?" — Query the wiki on any topic
  • "Index stats" — Show counts by type, tag frequency, status

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.