What is skills AGENTS.md?

Repository instructions for maintaining portable AI-agent skill packages and the catalogue information used to install them.

Use them when changing a skill's instructions, linked references, examples, evaluation files, or marketplace metadata.

They clarify which files own activation rules, references, examples, tests, and release details, helping changes stay in the right place.

How buYoung/skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to buYoung/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.

Copy the file

curl -O https://raw.githubusercontent.com/buYoung/skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/buYoung/skills

Made for: 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/buyoung/skills/agents-md/github.svg)](https://agentmods.dev/instructions/buyoung/skills/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/buyoung/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/buyoung/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.

Your own site · 80×15

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

Per session 1,966 This file is loaded in full into every session.

When invoked 1,966 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	$0.01966	$0.01966
Opus 5.5	$0.00786	$0.00786
Sonnet 5.5	$0.00393	$0.00393
Haiku 4.5	$0.00197	$0.00197

Measured 2mo ago against content hash 6514459600cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

1. Overview

This repository maintains portable AI agent skill packages and the release/catalog metadata that makes those packages installable across agent runtimes. Each skill owns its own activation contract, domain references, examples, validators, and revision evidence.

2. Ownership Map

Stable Ownership Boundaries

Skill package contract: Start in skills/<skill-name>/SKILL.md when changing a skill's trigger, workflow, output contract, or guardrails. It owns the public activation surface consumed by README catalog entries and marketplace bundles, and must preserve package-local routing into references/, scripts/, examples/, evals/, or updates/; verify by checking the skill entry point plus any linked package-local artifacts.
Reference and artifact boundary: Start in the owning package's references/, examples/, evals/, or updates/ when changing detailed domain rules, sample outputs, regression material, or design notes. These files extend the owning SKILL.md without becoming shared repository policy; verify that relative links from the entry point still resolve and that examples/evals still match the documented output shape.
Structural validator boundary: Start in the owning package's scripts/ directory when changing machine-checkable document shape. Validators use standard-library Python with constants, regex contracts, explicit exit codes, and Report objects, and they must remain structural checks rather than semantic judges; verify through the script's own usage contract and representative fixture or target document.
Release and marketplace boundary: Start in scripts/release/, .release-it.json, .claude-plugin/marketplace.json, README availability tables, and both changelogs when changing published bundle membership, package versioning, or release notes. These files form one metadata chain, so bundle paths, advertised availability, generated changelog sections, and tag workflow checks must stay aligned.
Repository guidance boundary: Start in root AGENTS.md, fable5.md, and docs/ when changing agent-facing repository policy or operating guidance. Repository-level guidance applies across skill packages, while package-specific rules stay beside the owning skill; verify that generated or managed sections preserve custom user sections and do not duplicate package-owned details.

Read the full file on GitHub · 60 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.

2mo ago Changed · +58 tokens per session 6514459600cb
2mo ago First seen · 60 lines · 1,908 tokens per session scan A 1fb01ea84c95

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository buYoung/skills (21 stars, last pushed 13d ago), licensed MIT. It adds 1,966 tokens to every session, about $0.0079 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 2026-08-30.

skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills AGENTS.mdbuYoung/skills	Instructions file	21	13d ago	MIT	A	1,966	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

skills: Instructions file for Codex