What is claude-agents-md AGENTS.md?

A Claude Code plugin that loads AGENTS.md files, shared instructions for coding agents, even though Claude Code normally reads CLAUDE.md files. It finds those files and makes their instructions available during a session.

Use it to discover project instructions at session start or when prompts are submitted, keep them synchronized with Claude Code, and test the scanning hook.

It lets projects keep one set of agent instructions that can also work with tools such as Cursor, Codex, Windsurf, and Continue.dev.

How hexsprite/claude-agents-md configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to hexsprite/claude-agents-md. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hexsprite/claude-agents-md/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hexsprite/claude-agents-md

Made for: Claude Code, Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hexsprite/claude-agents-md/agents-md/github.svg)](https://agentmods.dev/instructions/hexsprite/claude-agents-md/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hexsprite/claude-agents-md/agents-md"><img src="https://agentmods.dev/badge/instructions/hexsprite/claude-agents-md/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hexsprite/claude-agents-md/agents-md"><img src="https://agentmods.dev/badge/instructions/hexsprite/claude-agents-md/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,304 This file is loaded in full into every session.

When invoked 1,304 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.1	$0.01304	$0.01304
Opus 5.5	$0.00522	$0.00522
Sonnet 5.5	$0.00261	$0.00261
Haiku 4.5	$0.00130	$0.00130

Measured 1mo ago against content hash 077356d46ee8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-agents-md 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 1mo 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.

AGENTS.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agents-md — Agent Instructions

Claude Code plugin that loads AGENTS.md files so cross-tool project instructions (Cursor, Codex, Windsurf, Continue.dev) work in Claude Code, which natively reads only CLAUDE.md. This repo dogfoods its own feature: this file is the source of truth; CLAUDE.md is generated/gitignored, never committed.

Layout

hooks/scan-agents-md.sh — the hook: find AGENTS.md, link/inject as CLAUDE.md, dedupe per session.
hooks/hooks.json — registers the hook on SessionStart + UserPromptSubmit.
.claude-plugin/plugin.json — plugin manifest.
tests/ — Bun PTY tests. scan-script.test.ts is pure script unit tests (no API); session-start.test.ts / file-changed.test.ts spawn a real Claude session (~60s, burns credits).

Dev

bun install
bun test                       # all
bun test tests/scan-script.test.ts   # fast, no API

Conventions

Hook is POSIX-ish bash; keep it dependency-light and fast — it runs on every UserPromptSubmit.
Runtime knobs are CLAUDE_AGENTS_MD_* env vars (see README).
Any bug fix ships with a regression test in tests/scan-script.test.ts.

Branches

main — v2 (Bun-preload VFS mode) in progress; replaces the symlink hook as default.
v1 — symlink/inject hook release line (maintenance).

Beads Issue Tracker

This project uses bd (beads) for issue tracking. Run bd prime to see full workflow context and commands.

Quick Reference

bd ready              # Find available work
bd show <id>          # View issue details
bd update <id> --claim  # Claim work
bd close <id>         # Complete work

Rules

Use bd for ALL task tracking — do NOT use TodoWrite, TaskCreate, or markdown TODO lists
Run bd prime for detailed command reference and session close protocol
Use bd remember for persistent knowledge — do NOT use MEMORY.md files

Architecture in one line: issues live in a local Dolt DB; sync uses refs/dolt/data on your git remote; .beads/issues.jsonl is a passive export. See https://github.com/gastownhall/beads/blob/main/docs/SYNC_CONCEPTS.md for details and anti-patterns.

Read the full file on GitHub · 114 lines

Changes

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.

1mo ago First seen · 114 lines · 1,304 tokens per session scan A 077356d46ee8

Subscribe to this mod's changes

claude-agents-md AGENTS.md is an instructions file published in the GitHub repository hexsprite/claude-agents-md (5 stars, last pushed 3mo ago), licensed MIT. It adds 1,304 tokens to every session, about $0.0052 per session on Opus 5.5. 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.

Building agents Claude Code agents-md ai-coding claude codex cursor

ai-agent-rules-generator ui-design.instructions.md

Glitch Payment Gateway admin UI design rules — mandatory element & component reference for WooCommerce settings.

savedpixel/ai-agent-rules-generator · 701 tokens

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).

microsoft/vscode · 9,715 tokens

claude-agents-md: Instructions file for Claude Code