agentrigs
+ submit rig
~ / rigs / colbymchenry / codegraph

colbymchenry/codegraph

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, CoPilot, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

↗ GitHub ★ 72.6k mit updated 8d ago project Claude CodeCodexCursor
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~11.9k tokens
Heavy · 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 colbymchenry/codegraph/.claude ./rig-codegraph  # inspect, then merge into .claude/

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 colbymchenry/codegraph/.claude/skills/add-lang .claude/skills/add-lang
$ npx degit colbymchenry/codegraph/.claude/skills/agent-eval .claude/skills/agent-eval

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 (2)

add-langagent-eval

Cursor rules (1)

codegraph · always

Similar rigs

OZ-50/ozm-codex-agent-governance-skills
Codex-native OZM skill pack for AI coding agent governance, agentic coding loops, claim ceilings, and AGENTS.md-aware workflows.
★ 1 collection Claude CodeCodexCursor 2 skills 4mo ago
Minimalist 1.8k tok ·
dpthinh910/ai-agent-timmy
AI agent skills, Claude Code config, and Antigravity configuration - consolidated workspace for intelligent coding workflows
★ 0 project Claude CodeCodex 26 skills 8 agents 12 hooks 6mo ago
Orchestrator 2.1k tok ·
timurgaleev/vibestack
Sixty commands for AI coding assistants — /office-hours to shape an idea, /review before you merge, /ship to open the PR — plus the standing rules they assume. One install covers Claude Code, Cursor, Kiro and Codex CLI. Plain bash, MIT, no
★ 7 collection Claude CodeCodex 59 skills today
Skill Collector 7.1k tok ·
socialadsmentor/sam-agentic-harness
A working Claude Code harness scrubbed from a production agency setup: always-on rules, on-demand skills, hooks, model-scored subagents, three-tier memory, and a self-improvement loop gated by human approval. The installer checks fit and wa
★ 4 setup Claude Code 103 skills 1mo ago
Skill Collector 5.9k tok ·
copied ✓