skills: Instructions file for Codex

AGENTS.md

skills AGENTS.md is an instructions file for Codex, OpenCode from knocklabs/skills. It costs 1,292 tokens per session, scanned A, original, MIT.

Instructions for adding new skills and rules to the knocklabs/skills repository. A skill is a reusable set of guidance for an AI coding assistant.

In plain words
What is it for?
Use it when creating or documenting a skill, including its SKILL.md file and individual Markdown rule files.
Why use it?
It provides the required folder structure, file format, metadata, and naming rules for new additions.

Instructions file for CodexOpenCode

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

This is knocklabs/skills's own configuration. It tells Codex and OpenCode how to work on skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything skills configures →

Reuse

Borrowing it

Nothing to install: this file belongs to knocklabs/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/knocklabs/skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/knocklabs/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 skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/knocklabs/skills/agents-md/github.svg)](https://agentmods.dev/instructions/knocklabs/skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/knocklabs/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/knocklabs/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.

agentmods 80×15 button for skills AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/knocklabs/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/knocklabs/skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,292 This file is loaded in full into every session.
When invoked 1,292 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01292 $0.01292
Opus 5.5 $0.00517 $0.00517
Sonnet 5.5 $0.00258 $0.00258
Haiku 4.5 $0.00129 $0.00129

Measured 2mo ago against content hash f95b53720d6a, 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 2mo 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 · 214 lines

How it starts

The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.

How to add new skills and rules

This guide explains how to structure and add new skills to this repository.

Skill structure

Each skill should follow this structure:

skills/
└── knock-your-skill-name/
    ├── SKILL.md          # Human-readable guide (required)
    └── rules/            # Rule files directory (required)
        ├── rule-1.md
        ├── rule-2.md
        └── ...

Step-by-step guide

1. Create the skill directory

Create a new directory under skills/ with a descriptive name using the knock- prefix and kebab-case:

mkdir -p skills/knock-your-skill-name/rules

2. Create rule files

Add individual rule files in the rules/ directory. Each rule file should:

  • Use markdown format (.md)
  • Include frontmatter with metadata:
    ---
    title: Your rule title
    description: Brief description of the rule
    tags:
      - relevant-tag-1
      - relevant-tag-2
    category: knock-your-skill-name
    last_updated: YYYY-MM-DD
    ---
    
  • Use sentence case for all titles and headings
  • Be focused on a single topic or theme
  • Include examples and practical guidance

Example rule file structure:

---
title: Rule name in sentence case
description: What this rule covers
tags:
  - tag1
  - tag2
category: knock-your-skill-name
last_updated: 2026-01-23
---

# Rule name in sentence case

## Section heading

Content here...

### Subsection

More content...

3. Create SKILL.md

Create a SKILL.md file that serves as a human-readable guide. It should:

  • Provide an overview of the skill
  • Explain how to use the different rules
  • Reference rule files using relative paths (e.g., rules/rule-1.md)
  • Include quick reference sections
  • Use sentence case for all headings

Example SKILL.md structure:

---
name: knock-your-skill-name
description: Brief description of what this skill provides.
---

# Your skill name

Brief description of what this skill provides.

## Overview

List the rule files and what they cover.

## How to use this skill

### For specific use case 1

1. **Start with rule X** (`rules/rule-x.md`)
   - What to look for
   - Key principles

2. **Check rule Y** (`rules/rule-y.md`)
   - Additional considerations

## Rule files reference

- `rules/rule-1.md` - Description
- `rules/rule-2.md` - Description

## Quick reference

Key points and patterns...

Read the full file on GitHub · 214 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. 2mo ago First seen · 214 lines · 1,292 tokens per session scan A f95b53720d6a

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository knocklabs/skills (1 stars, last pushed yesterday), licensed MIT. It adds 1,292 tokens to every session, about $0.0052 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 2026-08-30.

Related

skills AGENTS.md compared with instructions from other repositories

skills AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
skills AGENTS.mdknocklabs/skillsInstructions file1yesterdayMITA1,292Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode