Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/erans/autoagent-action/agents-mdgit clone --depth 1 https://github.com/erans/autoagent-actionWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01807 | $0.01807 |
| Opus 5 | $0.00903 | $0.00903 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
autoagent-action AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AutoAgent Project Structure
AutoAgent is a composable GitHub Action that integrates with multiple AI agents (Cursor CLI, Claude Code, Gemini CLI, Codex CLI, Amp Code, and OpenCode) to run automated code analysis and prompts on repositories as part of Pull Request workflows.
Project Overview
AutoAgent provides a standardized way to run AI-driven code analysis in GitHub Actions, offering predefined security checks, code reviews, and refactoring suggestions, plus support for custom prompts. It automatically installs the required AI agent and posts structured results back to the PR as comments.
Directory Structure
Root Files
| File | Purpose |
|---|---|
action.yml |
GitHub Action definition with inputs, outputs, and execution steps |
README.md |
User documentation with usage examples and configuration options |
results.json |
Temporary file storing analysis results in JSON format |
test.sh |
Comprehensive test script that validates the entire implementation |
test-simple.sh |
Lightweight test script for syntax validation and basic functionality |
/docs/ - Documentation
| File | Purpose |
|---|---|
prd.md |
Product Requirements Document defining features, inputs, and behavior |
tech-prd.md |
Technical Implementation Guide with architecture and code structure details |
/rules/ - AI Agent Prompts
Contains predefined prompt templates that guide the AI agent's analysis:
| File | Purpose |
|---|---|
base.prompt |
Shared initialization context for all agents running in GitHub Actions |
code-review.prompt |
Comprehensive code review focusing on quality, architecture, performance, and maintainability |
owasp-check.prompt |
Security analysis based on OWASP Top 10 guidelines |
refactor-suggestions.prompt |
Code smell detection and refactoring opportunity identification |
comment.prompt |
Output formatting instructions for PR comments (concise, actionable, with compare links) |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 174 lines · 1,807 tokens per session scan A 0a642911c49c
autoagent-action AGENTS.md is an instructions file published in the GitHub repository erans/autoagent-action (17 stars, last pushed 11mo ago), licensed MIT. It adds 1,807 tokens to every session, about $0.0090 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
cmux CLAUDE.md
Claude Code instructions for manaflow-ai/cmux, covering cmux agent notes, setup, build and reload, shared mac fleet capacity and tag-bound debug cli.
sandbox-agent CLAUDE.md
Instructions for rivet-dev/sandbox-agent, covering instructions, naming and ownership, docs terminology, docs source of truth (http/cli) and docs styling.
my-ai-tools GEMINI.md
Instructions for jellydn/my-ai-tools, covering 🤖 gemini cli agent guidelines - my-ai-tools, 🚀 project overview, 🛠️ key commands, installation & sync and development & testing.
fallow-skills CLAUDE.md
Instructions for fallow-rs/fallow-skills: Read @AGENTS.md first. It is the shared repository contract for Claude, Codex, and contributors.
amp-acp AGENTS.md
Instructions for tao12345666333/amp-acp, covering agents.md, commands, architecture and code style.
testkube AGENTS.md
AGENTS.md instructions for kubeshop/testkube, covering working with testkube core (testkube), deprecated components — do not reference, purpose, entry points and mcp integration.