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/nushey/agents-md-generator/agents-mdgit clone --depth 1 https://github.com/nushey/agents-md-generatorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/nushey/agents-md-generator/agents-md)<a href="https://agentmods.dev/instructions/nushey/agents-md-generator/agents-md"><img src="https://agentmods.dev/badge/instructions/nushey/agents-md-generator/agents-md.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.01317 | $0.01317 |
| Opus 5 | $0.00659 | $0.00659 |
| Sonnet 5 | $0.00263 | $0.00263 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
agents-md-generator 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — agents-md-generator
Project Overview
agents-md-generator is a Python-based MCP (Model Context Protocol) server designed to generate and maintain AGENTS.md files—architectural context documents for AI coding agents. It uses Tree-sitter for high-fidelity AST analysis across multiple languages (Python, TypeScript, Go, C#) and uv for dependency management. The system operates as an incremental, cache-aware pipeline that transforms a codebase into a structured payload for AI assistants to perform maintenance tasks without manual exploration.
Tech Stack
- Backend: Python, MCP SDK, Pydantic, Tree-sitter.
- Package Management:
uv. - Infrastructure: GitHub Actions (CI/CD), Pytest.
- Configuration:
pyproject.toml.
Project Map
| Module | Purpose |
|---|---|
src/agents_md_mcp/ |
Core analysis pipeline, caching logic, and MCP server implementation. |
src/agents_md_mcp/languages/ |
Language-specific AST analyzer implementations (Python, Go, TypeScript, C#). |
tests/ |
Unit and integration test suite covering the full analysis pipeline. |
tests/fixtures/ |
Sample source files in various languages used as AST parsing targets. |
docs/ |
Architectural design notes and technical documentation. |
.gemini/ |
Configuration and settings for the Gemini CLI agent. |
.claude/ |
Local settings and hooks for Claude Code. |
.github/workflows/ |
CI/CD workflow definitions for automated testing and releases. |
Architecture & Data Flow
The system follows a linear pipeline architecture: project_scanner identifies files, change_detector determines analysis targets via a git-based cache, ast_analyzer parses source code into structured symbols, aggregator collapses large directories, and context_builder assembles the final JSON payload.
- Architectural Anchors:
LanguageAnalyzer: The abstract base class insrc/agents_md_mcp/languages/base.pythat all language-specific analyzers must implement.ProjectConfig: Loaded viaload_configinsrc/agents_md_mcp/config.py, governing the scan scope and language mapping.
- Routing: The MCP interface is defined in
src/agents_md_mcp/server.pyusing@mcp.tooldecorators, which orchestrate the internal modules.
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 · 98 lines · 1,317 tokens per session scan A ba25102ea032
agents-md-generator AGENTS.md is an instructions file published in the GitHub repository nushey/agents-md-generator (6 stars, last pushed 23d ago), licensed MIT. It adds 1,317 tokens to every session, about $0.0066 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.