SkillsMay 14, 2026·2 min read

agentrules — Multi-Provider AGENTS.md Generator

agentrules generates AGENTS.md via a six-phase analysis pipeline; verified 117★. Install with `pip install -U agentrules`, then run `agentrules analyze`.

Script Depot
Script Depot · Community
Agent ready

This asset can be read and installed directly by agents

TokRepo exposes a universal CLI command, install contract, metadata JSON, adapter-aware plan, and raw content links so agents can judge fit, risk, and next actions.

Native · 98/100Policy: allow
Agent surface
Any MCP/CLI agent
Kind
Skill
Install
Single
Trust
Trust: Established
Entrypoint
Asset
Universal CLI install command
npx tokrepo install 4323a51e-d760-5437-87f1-813720527be3
install contractmetadata JSONadapter planraw content
Intro

agentrules generates AGENTS.md via a six-phase analysis pipeline; verified 117★. Install with pip install -U agentrules, then run agentrules analyze.

Best for: Engineers standardizing repo guidance for multiple coding agents across providers

Works with: Anthropic/OpenAI/Google/DeepSeek/xAI providers and optional local Codex runtime (per README)

Setup time: 12-25 minutes

Key facts (verified)

  • GitHub: 117 stars · 18 forks · pushed 2026-05-08.
  • License: MIT · owner avatar + repo URL verified via GitHub API.
  • README-backed entrypoint: pip install -U agentrules.

Main

  • Run agentrules analyze to generate an AGENTS.md-style contract based on your repo structure, then keep it as a durable entrypoint for agents.

  • Use the interactive configure flow to keep provider keys and presets out of the repo and inside user config (README points to ~/.config/agentrules/config.toml).

  • Start with an offline/low-risk smoke run (README includes a smoke test) before turning on web search or live API providers in CI.

Source-backed notes

  • README shows PyPI install: pip install -U agentrules and a smoke test agentrules analyze /path/to/project.
  • README says settings live in ~/.config/agentrules/config.toml (override via AGENTRULES_CONFIG_DIR).
  • README describes a six-phase analysis pipeline ending in AGENTS.md generation.

FAQ

  • Is it tied to one model provider?: No — README lists multiple providers and also mentions optional local Codex runtime presets.
  • Where do keys live?: README says keys and preferences are stored in ~/.config/agentrules/config.toml.
  • What is the first command to try?: Install, then run agentrules analyze /path/to/project as the smoke test in README.
🙏

Source & Thanks

Source: https://github.com/trevor-nichols/agentrules-architect > License: MIT > GitHub stars: 117 · forks: 18

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

VT Code — Multi-Provider Coding Agent with MCP

VT Code is an open-source coding agent with multi-provider support, shell safety, and docs for Skills, ACP, and MCP integration.

SkillsCLI Tools
Agent Toolkit

Uni-CLI — Governed Software Commands + MCP for Agents

Searchable CLI catalog (282 sites, 1680 commands) that serves governed tools to agents via MCP, with repairable adapters; verified 73★, pushed 2026-05-13.

SkillsCLI Tools
Script Depot

dmux — Git Worktree Multiplexer for Coding Agents

dmux multiplexes coding agents with tmux + isolated git worktrees, so parallel tasks never collide. Verified 1,552★; setup ~5–10 minutes.

SkillsCLI Tools
Script Depot

OpenAI Agents SDK — Build Multi-Agent Systems in Python

Official OpenAI Python SDK for building multi-agent systems with handoffs, guardrails, and tracing. Agents delegate to specialists, enforce safety rules, and produce observable traces. 8,000+ stars.

SkillsCLI Tools
OpenAI
◈Home🔍Search👤Me