Borrowing it
Nothing to install: this file belongs to reopt-ai/reopt-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/reopt-ai/reopt-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/reopt-ai/reopt-skillsWrote 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/reopt-ai/reopt-skills/agents-md)<a href="https://agentmods.dev/instructions/reopt-ai/reopt-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/reopt-ai/reopt-skills/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.
<a href="https://agentmods.dev/instructions/reopt-ai/reopt-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/reopt-ai/reopt-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01705 | $0.01705 |
| Opus 5 | $0.00852 | $0.00852 |
| Sonnet 5 | $0.00341 | $0.00341 |
| Haiku 4.5 | $0.00170 | $0.00170 |
Grade A, and why
reopt-skills 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 9d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository packages reusable skills for AI coding agents working on reopt. It is the canonical agent-facing guide — CLAUDE.md imports this file for Claude Code compatibility.
Repository Overview
- Mirror the high-level structure of
vercel-labs/agent-skills. - Keep each distributable skill under
skills/<skill-name>/. - Distribution is via the
skillsCLI (npx skills add reopt-ai/reopt-skills), which pulls directly from git. No zip artifacts are committed. - Use root scripts for validation and syncing instead of ad hoc shell one-liners.
What a skill in this repo does (v2)
A reopt skill has two jobs:
- Pin an agent-rules marker block into the consumer project's
AGENTS.md(fallbackCLAUDE.md) —<!-- BEGIN:reopt/<pkg>-agent-rules -->…<!-- END:reopt/<pkg>-agent-rules -->. Markers are idempotent: a re-install replaces the block content, leaving everything outside untouched. The block source of truth is the module's own agent-rules file once it ships one — no@reopt-ai/*package ships one yet, so the skill's bundled fallbackagent-rules.mdis currently authoritative. Skills that share a marker (install + review of the same package) must ship byte-identical fallbacks;pnpm validateenforces this. - Trigger matching + docs routing — detect the user's intent and route to the right doc file in the installed package. Doc layout varies per package —
dist/docs/(opt-ui / opt-datagrid / opt-editor, numeric-prefixed tree +index.md), top-leveldocs/(brandapp-sdk, flat files), orREADME.md/shell-llms.txt(cli, opt-chat, opt-shell, which ship no docs dir). Confirm the real path + filename before routing — skills point at literal paths. SKILL.md does not duplicate API surface; module docs are pinned to the installed version, the skill is not.
What stays in SKILL.md: consumer-project setup that cannot live inside the module (legacy registry cleanup, env-namespace rules, peer deps, requires chains, destructive guardrails, security rules). Everything else routes to the package's docs (wherever it ships them).
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.
- 9d ago First seen · 113 lines · 1,705 tokens per session scan A 80142f133f94
reopt-skills AGENTS.md is an instructions file published in the GitHub repository reopt-ai/reopt-skills (1 stars, last pushed 4d ago), licensed MIT. It adds 1,705 tokens to every session, about $0.0085 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.