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/reaatech/agents-md-kit/agents-mdgit clone --depth 1 https://github.com/reaatech/agents-md-kitWhat 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 | $0.04162 | $0.04162 |
| Opus 5 | $0.02081 | $0.02081 |
| Sonnet 5 | $0.00832 | $0.00832 |
| Haiku 4.5 | $0.00416 | $0.00416 |
Grade A, and why
agents-md-kit 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 yesterday.
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 — 532 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agents-md-kit — Agent Development Guide
What this is
This document defines how to use agents-md-kit to create, validate, and maintain
AGENTS.md and SKILL.md files — the "durable agent instruction artifacts" that define
how AI agents behave, what skills they possess, and how they integrate into multi-agent
systems.
Target audience: Engineers building AI agents who need to create standardized agent instruction files that follow community best practices and can be validated for correctness, completeness, and quality.
Architecture Overview
agents-md-kit is a pnpm monorepo of 9 independently versioned packages published
under the @reaatech/agents-markdown-* scope, plus examples and end-to-end tests.
┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐
│ Parser │ │ Validator │ │ Linter │ │ Reporter │
│ (remark) │───▶│ (zod) │───▶│ (rules) │───▶│ (4 formats) │
└─────────────┘ └─────────────┘ └─────────────┘ └─────────────┘
│ │
▼ ▼
┌─────────────┐ ┌─────────────┐
│ Core │ │ Scaffold │
│ (types + │ │ (handlebars)│
│ schemas) │ └─────────────┘
└─────────────┘ │
│ ┌──────┴──────┐
▼ ▼ ▼
┌─────────────────────────────────────────────────────────────────────┐
│ CLI │ MCP Server │
│ (commander) │ (@modelcontextprotocol) │
└─────────────────────────────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────────────┐
│ Observability (pino + OTel) │
└─────────────────────────────────────────────────────────────────────┘
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.
- yesterday First seen · 532 lines · 4,162 tokens per session scan A 6f6b7f97bb5f
agents-md-kit AGENTS.md is an instructions file published in the GitHub repository reaatech/agents-md-kit (2 stars, last pushed 8d ago), licensed MIT. It adds 4,162 tokens to every session, about $0.0208 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
repository-harness AGENTS.md
Instructions for hoangnb24/repository-harness, covering agent instructions and harness.
repository-harness CLAUDE.md
Instructions for hoangnb24/repository-harness, covering project rules and harness.
AGENTS.md AGENTS.md
Instructions for Anbeeld/AGENTS.md, covering global instructions, priorities, boundaries, uncertainty and evidence.
mda CLAUDE.md
Instructions for sno-ai/mda, covering claude.md — sno-ai/mda, release process for @markdown-ai/cli, to cut a release (any 1.1.x, 1.2.0, 2.0.0 — same flow), release notes — non-negotiable and what's new.
Monet CLAUDE.md
Instructions for Monet-AI-Editor/Monet, covering monet — claude agent guide, ⚠️ finding editorctl — mandatory (read this first), ⚠️ absolute paths only — mandatory, ⚠️ output file naming — mandatory (read this first) and ⚠️ audio on multi-clip timelines — mandatory.
agent-context-kit AGENTS.md
Instructions for Cynrath/agent-context-kit, covering agents.md — agentcontextkit v0.2.0, controlled-release governance, canonical entry points (read in this order), ackit-first / task-first / docs-first workflow and continuous execution hard rule (explicit user mandate).