What is skills AGENTS.md?

Repository instructions for maintaining reusable AI-agent skills. They describe the source of truth, folder layout, required files, and documentation rules.

Use them when adding or updating a skill package, deciding where its instructions and supporting files belong, or checking repository conventions.

They give contributors consistent rules for creating and organizing skills, reducing misplaced files and conflicting documentation.

How sebastianwessel/skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to sebastianwessel/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/sebastianwessel/skills/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/sebastianwessel/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/sebastianwessel/skills/agents-md.svg)](https://agentmods.dev/instructions/sebastianwessel/skills/agents-md)

Your own site

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

Per session 833 This file is loaded in full into every session.

When invoked 833 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	$0.00833	$0.00833
Opus 5	$0.00417	$0.00417
Sonnet 5	$0.00167	$0.00167
Haiku 4.5	$0.00083	$0.00083

Measured 8d ago against content hash 2fd579ac4096, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Instructions

This repository maintains reusable AI agent skills. Treat skills as small, self-contained capability packages, not as application code.

Source of Truth

Root conventions live in this file and .agent/IMPLEMENTATION.md.
Claude-compatible agents should read this file through CLAUDE.md.
Skill authoring follows Anthropic's Agent Skills best practices: https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices

Repository Layout

.
├── AGENTS.md
├── CLAUDE.md
├── README.md
├── .agent/
│   └── IMPLEMENTATION.md
├── scripts/
│   └── update-readme.py
└── skills/
    └── <skill-name>/
        └── SKILL.md

Skill Rules

Store every skill in skills/<skill-name>/.
Every skill must include SKILL.md at the skill root.
Optional skill resources should stay inside that skill directory, typically scripts/, references/, assets/, and agents/.
Do not put a README.md, changelog, installation guide, or unrelated docs inside individual skill directories.
Human-facing skill documentation belongs in docs/skills/<skill-name>.md. Keep executable skill packages focused on agent-loaded instructions and resources.
Every human-facing skill doc must include an Installation section with the package command:
```
npx skills add sebastianwessel/skills
```
Keep SKILL.md concise. Move detailed reference material into one-level-deep files referenced directly from SKILL.md.
Every skill must make agents self-audit before completion when the task involves judgment, generated artifacts, specs, plans, or implementation. Self-audit means: reflect on assumptions, judge whether decisions are backed by approved sources, identify gaps or contradictions, and report uncertainty honestly instead of inventing missing information.
Self-audit must not replace verification. A skill should still require deterministic checks, tests, scripts, or explicit evidence where those are available.
Spec-driven workflow skills must preserve enterprise reliability guarantees: unhappy paths, security/privacy, data classification, log redaction, data integrity, recovery, performance budgets, production readiness, release/rollback, supply-chain integrity, and no-leak/no-data-loss behavior must be specified, planned, implemented, or reviewed explicitly.
Regex or keyword checks are smoke tests only. If a skill uses English prose-matching checks, the checked specs/plans/tickets must declare or require English, and semantic approval must come from structured gates, review, or a judge pass with evidence.
Do not commit secrets, credentials, private data exports, local model caches, or generated archives.

Read the full file on GitHub · 106 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.

8d ago First seen · 106 lines · 833 tokens per session scan A 2fd579ac4096

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository sebastianwessel/skills (5 stars, last pushed 23d ago), licensed Apache-2.0. It adds 833 tokens to every session, about $0.0042 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.

Building agents

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 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: Instructions file for Codex