kb-agents
CLAUDE.md1 starsChanged 7 months agoMITView on GitHub
This is the source repository for KB Agents — an LLM-powered knowledge management system with three AI agents built on the BMAD Framework. Each agent has: - SKILL.md — Agent definition and behavior rules - references/ — Capability prompt files (one per capability) - scripts/ — Python helper scripts for deterministic operations - assets/ — Sanctum templates for agent memory
In this repository27 other files it gives its agents.
- assets/CLAUDE.mdCLAUDE.md
- bmad-advanced-elicitationSkill
- bmad-agent-builderSkill
- bmad-bmb-setupSkill
- bmad-brainstormingSkill
- bmad-cis-agent-brainstorming-coachSkill
- bmad-cis-agent-creative-problem-solverSkill
- bmad-cis-agent-design-thinking-coachSkill
- bmad-cis-agent-innovation-strategistSkill
- bmad-cis-agent-presentation-masterSkill
- bmad-cis-agent-storytellerSkill
- bmad-cis-design-thinkingSkill
- bmad-cis-innovation-strategySkill
- bmad-cis-problem-solvingSkill
- bmad-cis-storytellingSkill
- bmad-distillatorSkill
- bmad-editorial-review-proseSkill
- bmad-editorial-review-structureSkill
- bmad-helpSkill
- bmad-index-docsSkill
- bmad-initSkill
- bmad-module-builderSkill
- bmad-party-modeSkill
- bmad-review-adversarial-generalSkill
- bmad-review-edge-case-hunterSkill
- bmad-shard-docSkill
- bmad-workflow-builderSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
All Python scripts are stdlib-only (no external dependencies)
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
KB Agents
This is the source repository for KB Agents — an LLM-powered knowledge management system with three AI agents built on the BMAD Framework.
Repository Structure
_bmad-output/— The three compiled KB agents (Ingest, Compiler, Linter)_bmad/— BMAD Framework (agent architecture, do not modify)kb-init.sh— Setup script that creates a new knowledge base vaultdocs/— User-facing documentation
For Contributors
- Tests:
pytest -v(89 tests covering all agent scripts) - Shell scripts must pass
shellcheck - All Python scripts are stdlib-only (no external dependencies)
- See CONTRIBUTING.md for branch conventions
Agents
| Agent | Skill Path | Capabilities |
| Archivist (Ingest) | _bmad-output/agent-kb-ingest/ | [AD] Auto-Discover, [IN] Ingest, [BI] Batch, [IX] Index |
| Cartographer (Compiler) | _bmad-output/agent-kb-compiler/ | [CS] Compile, [MC] Concepts, [MW] Wiki, [WC] Connections, [QW] Query |
| Inspector (Linter) | _bmad-output/agent-kb-linter/ | [HC] Health, [FX] Fix, [SA] Suggest, [CC] Consistency |
Each agent has:
SKILL.md— Agent definition and behavior rulesreferences/— Capability prompt files (one per capability)scripts/— Python helper scripts for deterministic operationsassets/— Sanctum templates for agent memory
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.

