agentrigs
+ submit rig
~ / rigs / lizhiyao / oh-my-knowledge

lizhiyao/oh-my-knowledge

OMK — Evidence-backed evaluation and observability for prompts, RAG, skills, agents, and workflows. Native Codex, Claude Code, and DeepSeek Harness support.

↗ GitHub ★ 22 MIT updated today project Claude CodeCodex
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~1.9k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

$ git clone --depth 1 https://github.com/lizhiyao/oh-my-knowledge

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 lizhiyao/oh-my-knowledge/.agents/skills/omk .claude/skills/omk
$ npx degit lizhiyao/oh-my-knowledge/examples/agent-runtime/skills/repo-answerer .claude/skills/repo-answerer
$ npx degit lizhiyao/oh-my-knowledge/examples/agent-runtime/skills/repo-navigator .claude/skills/repo-navigator
$ npx degit lizhiyao/oh-my-knowledge/examples/custom-executor/skills/echo-assistant .claude/skills/echo-assistant
$ npx degit lizhiyao/oh-my-knowledge/examples/rag-eval/skills/context-answerer .claude/skills/context-answerer
$ npx degit lizhiyao/oh-my-knowledge/examples/rag-eval/skills/rag-answerer .claude/skills/rag-answerer
$ npx degit lizhiyao/oh-my-knowledge/examples/skill-map-showcase/skills/release-checklist .claude/skills/release-checklist
$ npx degit lizhiyao/oh-my-knowledge/examples/skill-map-showcase/skills/release-readiness .claude/skills/release-readiness

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 (8)

omkrepo-answererrepo-navigatorecho-assistantcontext-answererrag-answererrelease-checklistrelease-readiness

Similar rigs

zzallirog/agent-atlas
A modular working-memory layout for LLM agents that work across many repositories.
★ 1 project Codex 1 skills 5mo ago
Minimalist 904 tok ·
herbeus/graft
One shared directory of AI-agent context, linked into every repository you work on - found by git remote URL, not by hardcoded path
★ 0 setup Claude Code 1 skills 1mo ago
Minimalist 33 tok ·
GreenLv/skillferry
Portable agent workspace across Codex, Claude Code, and DeepSeek Harness
★ 0 project Claude Code 2 skills 1mo ago
Minimalist 95 tok ·
jordanhubbard/nanolang
A tiny experimental language designed to be targeted by coding LLMs
★ 629 project Claude CodeCodexCursor 1 mcp 7 skills 2 hooks 5d ago
Pragmatist 6.6k tok ·
copied ✓