What is skills AGENTS.md?

Repository guidance for maintaining an Agent Skill package. It explains where skill instructions, shared assets, hooks, manifests, and validation scripts belong.

Use it when adding or updating skills, changing plugin metadata, rebuilding manifests, or validating the structure of the skills repository.

It helps contributors edit the source files rather than generated files and keep app-specific manifests consistent. It also describes how to validate links and metadata.

How onehorizonai/skills configures Claude Code and Codex

Reuse

Borrowing it

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

Clone the repo

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

Made for: Claude Code, 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/onehorizonai/skills/agents-md.svg)](https://agentmods.dev/instructions/onehorizonai/skills/agents-md)

Your own site

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

Per session 791 This file is loaded in full into every session.

When invoked 791 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	$0.00791	$0.00791
Opus 5	$0.00396	$0.00396
Sonnet 5	$0.00158	$0.00158
Haiku 4.5	$0.00079	$0.00079

Measured 6d ago against content hash 36d966010c61, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 6d 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 · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide

This repo contains one plugin. skills/ is the source of truth for skill instructions. App-specific manifests live at the repo root and are generated from plugin.json. Do not edit generated files directly.

Structure

skills/
  {skill-name}/
    SKILL.md
    agents/openai.yaml
    assets/

assets/                             # Shared plugin assets
hooks/                              # Shared hook scripts
scripts/
  build-manifests.mjs               # Regenerates app-specific manifests
  validate.mjs                      # Validates manifests and skill metadata
  validate-links.mjs                # Validates local refs and external URLs

plugin.json                         # Canonical plugin manifest
.mcp.json                           # Shared MCP server config
copilot-hooks.json                  # Shared hook manifest
.cursor-plugin/plugin.json          # Generated Cursor manifest
.codex-plugin/plugin.json           # Generated Codex manifest
.claude-plugin/marketplace.json     # Claude marketplace
.agents/plugins/marketplace.json    # Local Codex marketplace
.github/plugin/marketplace.json     # GitHub/Copilot marketplace

Working with skills

Each skill lives at skills/{skill-name}/SKILL.md with frontmatter and agent instructions.

SKILL.md format

---
name: {skill-name}          # Matches the folder name; no plugin prefix
description: {One sentence with trigger phrases like "prep my standup" or "list blockers".}
---

# Skill title

What this skill does, when to use it, and which nearby skill owns adjacent work.

## Instructions

Step-by-step instructions for the agent to follow when this skill is invoked.

Rules

name must match the folder name exactly; do not add a plugin namespace prefix
The slash command is built automatically: /{plugin-name}:{skill-name}
Keep SKILL.md short because the full file loads into context on every invocation
description controls when the agent picks up the skill; write it with concrete trigger phrases
Edit skills in skills/ only
Don't edit generated app manifests unless you're also updating scripts/build-manifests.mjs

Read the full file on GitHub · 105 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.

6d ago First seen · 105 lines · 791 tokens per session scan A 36d966010c61

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository onehorizonai/skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 791 tokens to every session, about $0.0040 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 · 5,182 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 Claude Code