What is skills AGENTS.md?

A set of contribution instructions for a repository whose files define executable behavior for AI agents. It explains the repository's purpose, how to classify changes, and when a change should be treated like a code change even if it is written in Markdown.

Use it when changing files under the skills directory or shared agent rules, especially when deciding whether a change is a new feature, a fix, a refactor, a performance improvement, a test, or documentation.

It prevents behavior-changing instructions from being mislabeled as ordinary documentation. This makes the effect of changes clearer when reviewing or recording them in version control.

skills AGENTS.md — Instructions file by QuentinHsu

Install

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.

agentmods

npx agentmods add instructions/quentinhsu/skills/agents-md

Clone the repo

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

Made for: Codex, OpenCode.

Per session 359 This file is loaded in full into every session.

When invoked 359 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00359	$0.00359
Opus 5	$0.00179	$0.00179
Sonnet 5	$0.00072	$0.00072
Haiku 4.5	$0.00036	$0.00036

Measured 2d ago against content hash 33c9b7fcea66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

AGENTS.md · 33 lines

What it actually says

AGENTS

Repository intent

This repository stores agent skills as executable behavior definitions. Files under skills/**/SKILL.md and their shared rule files are part of shipped capability, not passive reference docs. Treat these Markdown files as behavior code: changes to prompts, rules, decision logic, examples that constrain output, or invocation guidance should be classified by behavior impact, not by file extension.

Commit type guidance

When changes modify skill behavior, output constraints, invocation rules, decision logic, reusable rules, or examples that shape delivered behavior, classify them like code changes:

prefer feat for new or expanded skill capability
prefer fix for correcting incorrect skill behavior or output
prefer refactor for structural rewrites without behavior change
prefer perf only when the change clearly improves execution efficiency, token usage, or latency
use test for evaluation or verification artifacts that validate skill behavior
use docs only for repository-facing explanatory content that does not change delivered skill behavior
reserve docs for repository-facing explanatory content such as README* and docs/**

Bilingual output rule

For bilingual output requirements:

content under 中文 must be written in Simplified Chinese
content under English must be written in English
the two versions must be composed independently in their respective languages
do not copy one version and merely relabel it as the other language

Scope note for git-change-writing skills

In skills/git-change-writing/**, changes to prompts, rules, examples, or shared output constraints usually affect delivered skill behavior. Do not default to docs just because the file extension is .md; classify them by behavior impact first.

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.

2d ago First seen · 33 lines · 359 tokens per session scan A 33c9b7fcea66

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository QuentinHsu/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 359 tokens to every session, about $0.0018 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.

Git and workflow Testing Writing and docs

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.

github/spec-kit · 7,104 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 · 6,785 tokens

skills AGENTS.md