agentrigs
+ submit rig
~ / rigs / stjbrown / agent-knowledge

stjbrown/agent-knowledge

Portable Agent Skills for building and maintaining Open Knowledge Format project wikis in plain Markdown.

↗ GitHub ★ 41 mit updated 2mo ago project Claude Code Claude plugin
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~153 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit stjbrown/agent-knowledge/skills ./rig-agent-knowledge/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit stjbrown/agent-knowledge/skills/kb-document .claude/skills/kb-document
$ npx degit stjbrown/agent-knowledge/skills/kb-ingest .claude/skills/kb-ingest
$ npx degit stjbrown/agent-knowledge/skills/kb-init .claude/skills/kb-init
$ npx degit stjbrown/agent-knowledge/skills/kb-lint .claude/skills/kb-lint
$ npx degit stjbrown/agent-knowledge/skills/kb-query .claude/skills/kb-query
$ npx degit stjbrown/agent-knowledge/skills/kb-visualize .claude/skills/kb-visualize
$ npx degit stjbrown/agent-knowledge/skills/kb .claude/skills/kb

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (7)

kb-documentkb-ingestkb-initkb-lintkb-querykb-visualizekb

Similar rigs

janezslapnik/llm-wiki-kb
A Claude Code template for an LLM-maintained knowledge base (Karpathy's LLM-Wiki pattern): four skills to find, ingest, lint and query sources in a Markdown wiki.
★ 0 project Claude Code 4 skills today
Minimalist 1.8k tok ·
sxhmilyoyo/sundayhao-plugins
🧠 Claude Code plugin marketplace featuring Second Brain - an agentic workflow system with persistent memory and tribal knowledge. Transform Claude from goldfish to elephant with cross-session learning.
★ 8 collection Claude Code 6 skills 2d ago
Pragmatist 461 tok ·
spywhere/dotfiles
A cross-platform, modular dotfiles installer for my personal setup
★ 51 setup Claude CodeCodex 4 skills 5d ago
Minimalist 957 tok ·
anomalyco/opencode
The open source coding agent.
★ 212k project Codex 2 skills 1d ago
Pragmatist 4.2k tok ·
copied ✓