agent-skills AGENTS.md

agent-skills AGENTS.md is an instructions file for Codex, OpenCode from jdrhyne/agent-skills. It costs 603 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding agents working on a collection of agent skills and prompts. They explain the folder layout and how to add a skill, prompt, or Clawdbot skill.

In plain words
What is it for?
Use it when adding or updating skills, prompts, helper scripts, templates, examples, or repository documentation.
Why use it?
It gives contributors one set of rules for where new content belongs and what files it needs. This reduces misplaced files and inconsistent additions.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

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/jdrhyne/agent-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/jdrhyne/agent-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.

agentmods badge for agent-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jdrhyne/agent-skills/agents-md.svg)](https://agentmods.dev/instructions/jdrhyne/agent-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jdrhyne/agent-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/jdrhyne/agent-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 603 This file is loaded in full into every session.
When invoked 603 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00603 $0.00603
Opus 5 $0.00302 $0.00302
Sonnet 5 $0.00121 $0.00121
Haiku 4.5 $0.00060 $0.00060

Measured 6d ago against content hash f125b6a43890, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

agent-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 · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI agents working on this repository.

Repository Structure

agent-skills/
├── skills/      # Skills with tooling, scripts, or workflows
├── prompts/     # Pure instruction prompts (text only)
├── clawdbot/    # Clawdbot-specific skills
├── scripts/     # Repo maintenance scripts
├── README.md    # Main documentation (auto-generated sections)
└── AGENTS.md    # This file

Adding Content

Adding a Skill (with tooling)

  1. Create folder in /skills:

    mkdir -p skills/my-skill
    
  2. Create SKILL.md with frontmatter:

    ---
    name: my-skill
    description: What this skill does
    ---
    
    # My Skill
    
    Instructions, scripts, templates...
    
  3. Add supporting files:

    • scripts/ — Helper scripts
    • templates/ — Template files
    • examples/ — Example inputs/outputs

Adding a Prompt (pure guidance)

  1. Create folder in /prompts:

    mkdir -p prompts/my-prompt
    
  2. Create SKILL.md with frontmatter:

    ---
    name: my-prompt
    description: Guidance for X
    ---
    
    # My Prompt
    
    Instructions and guidelines...
    

Prompts should be self-contained — no external dependencies or scripts.

Adding Clawdbot Skills

Same as skills, but in /clawdbot:

mkdir -p clawdbot/my-clawdbot-skill

SKILL.md Requirements

Required frontmatter:

  • name: Identifier (lowercase, hyphens)
  • description: One-line description

Good SKILL.md structure:

  1. Quick usage examples at the top
  2. Detailed instructions
  3. Edge cases / troubleshooting
  4. References to supporting files

Validation

Before committing:

./scripts/validate-skills.sh

Sync Rule (Required)

If you add or update a skill locally, you must also:

  1. Add/update the corresponding skill folder in this repo
  2. Update the README skill list (Skills + Clawdbot-specific)
  3. Run ./scripts/validate-skills.sh
  4. Open a draft PR with a clear What/Why/How/Testing description

Read the full file on GitHub · 107 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.

  1. 6d ago First seen · 107 lines · 603 tokens per session scan A f125b6a43890

Subscribe to this mod's changes

agent-skills AGENTS.md is an instructions file published in the GitHub repository jdrhyne/agent-skills (241 stars, last pushed 7d ago), licensed MIT. It adds 603 tokens to every session, about $0.0030 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 2026-08-30.