agentrigs
+ submit rig
~ / rigs / RTopdar / agent-docs-template

RTopdar/agent-docs-template

One-command scaffold for AI coding-agent project docs: AGENTS.md/CLAUDE.md rules, incident-handler & doc-sync subagents, OKF-format doc/ bundles.

↗ GitHub ★ 1 MIT updated 1mo ago collection Claude CodeCodex
share on X
ARCHETYPE
Minimalist
Lean instructions, few tools, tiny context tax. Lets the model think.
CONTEXT TAX · EVERY TURN
~1.5k 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 RTopdar/agent-docs-template/.claude ./rig-agent-docs-template  # 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.

$ curl -fsSL --create-dirs -o .claude/agents/doc-sync.md https://raw.githubusercontent.com/RTopdar/agent-docs-template/master/.claude/agents/doc-sync.md
$ curl -fsSL --create-dirs -o .claude/agents/incident-handler.md https://raw.githubusercontent.com/RTopdar/agent-docs-template/master/.claude/agents/incident-handler.md

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 *)"
    ]
  }
}

Subagents (2)

doc-sync
model: inherit
Keeps technical docs in sync with codebase. Scans git diff for changes, updates IMPLEMENTATION_PLAN.md and the doc/feature/ OKF bundle, validates architecture stays documented, flags when code and doc
incident-handler
model: inherit
Use PROACTIVELY whenever the user reports a bug or issue in this repo. Checks doc/bug/index.md first for a known resolution; if none exists, investigates the codebase, fixes the issue, writes up a doc

Similar rigs

cablate/ai-toolkit
Battle-tested Claude Code skills for relentless AI delivery
★ 4 project Claude Code 6 skills 6 agents 6mo ago
Orchestrator 759 tok ·
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 ·
copied ✓