agentrigs
+ submit rig
~ / rigs / levi-qiao / longgraph-skill

levi-qiao/longgraph-skill

Long-horizon agent skill for Claude Code / Cursor / Codex / Grok Build — multi-task ledger loop, host-portable, clean-context supervisor, verified gates. Markdown library (loop-graph), not a framework.

↗ GitHub ★ 63 mit updated 2mo ago collection Claude CodeCodex Claude plugin
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~1.9k 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 levi-qiao/longgraph-skill/skills ./rig-longgraph-skill/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 levi-qiao/longgraph-skill/skills/loop-converge .claude/skills/loop-converge
$ npx degit levi-qiao/longgraph-skill/skills/loop-deliver .claude/skills/loop-deliver
$ npx degit levi-qiao/longgraph-skill/skills/loop-graph .claude/skills/loop-graph
$ npx degit levi-qiao/longgraph-skill/skills/loop-research .claude/skills/loop-research

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

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

Skills (4)

loop-convergeloop-deliverloop-graphloop-research

Similar rigs

multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
★ 217k collection Claude CodeCursor 1 skills 6mo ago
Minimalist 723 tok ·
shareAI-lab/learn-claude-code
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
★ 78.0k project Claude Code 4 skills 11d ago
Minimalist 156 tok ·
tt-a1i/archify
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
★ 76.3k project Claude CodeCodex 1 skills 7d ago
Minimalist 484 tok ·
ayghri/i-have-adhd
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
★ 53.7k project CodexCursorGemini CLI 1 skills 20d ago
Minimalist 1.4k tok ·
copied ✓