What is skills AGENTS.md?

Repository instructions for authoring coding-agent add-ons such as skills and plugins. They explain the directory layout, required metadata and where optional files such as references, scripts and tests belong.

Use it when creating or updating a plugin or skill in this repository. It covers component placement, plugin metadata, skill folders and optional resources such as commands, workflows and evaluations.

A contributor unfamiliar with the repository could create an invalid package structure or add framework-specific files that the project does not support. These rules provide the expected shape before implementation begins.

How zero-lab-ai/skills configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to zero-lab-ai/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/zero-lab-ai/skills/main/AGENTS.md

Clone the repo

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

Your own site

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

Per session 1,617 This file is loaded in full into every session.

When invoked 1,617 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	$0.01617	$0.01617
Opus 5.5	$0.00647	$0.00647
Sonnet 5.5	$0.00323	$0.00323
Haiku 4.5	$0.00162	$0.00162

Measured yesterday against content hash bce625259aa1, 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 yesterday.

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 · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Authoring plugins and skills

This repository follows the same marketplace conventions used by established Claude Code and Codex plugin repositories. Familiarity is a feature: someone who already uses another skills marketplace should not need to learn a Zero Lab runtime, vocabulary, or packaging model.

Repository layout

plugins/
  <plugin-name>/
    .claude-plugin/
      plugin.json
    skills/
      <skill-name>/
        SKILL.md
        agents/
          openai.yaml
        references/        # optional
        scripts/           # optional
        assets/            # optional
    commands/              # optional
    agents/                # optional
    hooks/                 # optional
    workflows/             # optional dynamic workflows
    evals/                 # optional behavioral evaluations
    tests/                 # optional code tests
    README.md

Only create component and resource directories that the plugin uses. Plugins may contain one skill, several related skills, or another supported marketplace component such as a command or workflow.

Keep plugin components at the plugin root. Only plugin.json belongs inside .claude-plugin/. Do not add duplicate .codex/, .agents/plugins/, or other vendor-specific sidecars; Codex reads the Claude marketplace metadata directly.

Skill frontmatter

---
name: network-recon
description: "Plans authorized network reconnaissance and audits scan coverage. Use when mapping hosts, services, or network exposure inside an agreed scope."
allowed-tools: Read Grep Glob Bash
---

name is kebab-case, matches the directory, and is at most 64 characters.
description states what the skill does and when it applies, using language a practitioner would naturally type.
Quote descriptions containing a colon.
allowed-tools is optional. Use the smallest set the workflow needs.
Do not require custom metadata to use a skill. Repository catalog categories belong in the root README, not in the runtime interface.

Read the full file on GitHub · 222 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.

yesterday First seen · 222 lines · 1,617 tokens per session scan A bce625259aa1

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository zero-lab-ai/skills (283 stars, last pushed 12d ago), licensed Apache-2.0. It adds 1,617 tokens to every session, about $0.0065 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 2026-10-26.

Project management agent-skills ai-security blue-team codex penetration-testing

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

skills: Instructions file for Codex

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Authoring plugins and skills

Repository layout

Skill frontmatter

What this file has done since we first saw it

Other instructions, from other repositories

vscode buildNext.instructions.md

next.js AGENTS.md

vscode oss-third-party-notices.instructions.md

langchain AGENTS.md

vscode copilot-instructions.md

vscode model-prompts.instructions.md