agentmods.dev

skills: Instructions file for Codex

AGENTS.md

skills AGENTS.md is an instructions file for Codex, OpenCode from cniska/skills. It costs 347 tokens per session, scanned A, original, MIT.

Project instructions for creating and maintaining reusable skills for AI coding agents. A skill is a self-contained set of instructions for handling a recurring kind of work.

In plain words
What is it for?
Use them when authoring or updating a skill, validating its files, testing it on different repositories, or preparing it for publication.
Why use it?
They provide consistent requirements for skill names, descriptions, structure, validation, testing, and references between skills.

Instructions file for CodexOpenCode

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

This is cniska/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 →

not rated 6repo changed 1mo ago A scan 347 tokens original MIT
View source ↗ cniska/skills
Reuse

Borrowing it

Nothing to install: this file belongs to cniska/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/cniska/skills/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/cniska/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/cniska/skills/agents-md/github.svg)](https://agentmods.dev/instructions/cniska/skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/cniska/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/cniska/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/cniska/skills/agents-md"><img src="https://agentmods.dev/badge/instructions/cniska/skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 347 This file is loaded in full into every session.
When invoked 347 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 $0.00347 $0.00347
Opus 5.5 $0.00139 $0.00139
Sonnet 5.5 $0.00069 $0.00069
Haiku 4.5 $0.00035 $0.00035

Measured 1mo ago against content hash d1651a5ca336, 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 1mo 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 · 24 lines

What it actually says

Skills

Self-contained engineering skills for AI coding agents — one per directory at skills/<name>/, with SKILL.md and any references/ it loads on demand. README.md is the reference for the full set, capability tiers, and principles.

Authoring a skill

  • Frontmatter name matches the directory; description starts with an imperative verb and states when to use the skill.
  • Self-contained: depend on nothing outside the skill's own directory, and reference other skills by bare name in ## See also, never by path — npx skills add copies only that directory.
  • End with a ## Red flags section (never ## Anti-patterns); keep the body terse and imperative.
  • Name capability tiers (fast / balanced / powerful), never specific models.
  • The validator enforces the mechanical rules — frontmatter, ## Red flags, every link resolving inside the skill's own directory.
  • Add guidance only for friction that repeats in real use; prefer trimming to growing.
  • After a material change to a skill, dry-run it on unlike real repos (the skill-test skill) before pushing.

Workflow

  • New skill: mise run new-skill <kebab-case> "<imperative description>" (or copy SKILL_TEMPLATE.md).
  • Validate: mise run validate. Test: mise run test. Lint: mise run lint.

Commits

  • Commit directly to main — no branch or PR.
  • Conventional Commits type(scope): description; single-line subject, no body, ASCII, under 50 characters.
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. 1mo ago Changed · +19 tokens per session d1651a5ca336
  2. 1mo ago Changed · +9 tokens per session 0d55c1f4e71f
  3. 1mo ago Changed · -6 tokens per session fc1307ec029a
  4. 2mo ago First seen · 24 lines · 325 tokens per session scan A 5929feca2a96

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository cniska/skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 347 tokens to every session, about $0.0014 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 2026-08-31.

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.mdcniska/skillsInstructions file61mo agoMITA347Codex, 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