What is skills AGENTS.md?

A set of rules for contributors working on the jkeskikangas/skills code repository. It explains required commands, testing, dependency changes, releases, and prohibited actions.

It is for preparing changes, running checks, managing dependencies, and releasing updates in that repository.

It gives coding agents a shared set of repository rules, reducing mistakes such as using the wrong package manager, skipping tests, or committing secrets.

How jkeskikangas/skills configures Codex and OpenCode

Reuse

Borrowing it

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

Clone the repo

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

Your own site

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

Per session 1,612 This file is loaded in full into every session.

When invoked 1,612 The same file — it is already loaded in full.

Security scan C 1 finding. 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	$0.01612	$0.01612
Opus 5.5	$0.00645	$0.00645
Sonnet 5.5	$0.00322	$0.00322
Haiku 4.5	$0.00161	$0.00161

Measured 2mo ago against content hash 220b9b12b30d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

skills AGENTS.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

cd packages/skillcheck && npm ci # ON FAIL: rm -rf node_modules && npm ci

AGENTS.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

CRITICAL

MUST: cd packages/skillcheck && npm ci to install dependencies
MUST: cd packages/skillcheck && npm run build before running linter locally
MUST: Run both linters before commit: node packages/skillcheck/bin/skillcheck.js skills/ and npx agnix skills/
MUST: cd packages/skillcheck && npm test before pushing to main
MUST: Use npm install <pkg> to change deps (DO NOT edit package.json manually)
MUST: Use cd packages/skillcheck && npm version <patch|minor|major> && git push --follow-tags to release (tag must match package.json version)
NEVER: yarn, pnpm, bun — repo uses npm (packages/skillcheck/package-lock.json)
NEVER: Push a git tag manually without bumping packages/skillcheck/package.json first (CI will fail)
NEVER: Create feature branches or open PRs — commit and push directly to main
NEVER: Force push (git push --force, git push -f) to main
NEVER: Skip pre-commit hooks (--no-verify)
NEVER: Edit files in packages/skillcheck/dist/ (generated)
NEVER: Commit .env files, API keys, tokens, or credentials
NEVER: Read or include secrets in skill definitions
PREFER: Built-in tools (file reader, editor, glob, grep) over shell equivalents (cat, sed, find, grep)
ON FAIL: Read full error output before retry
ON FAIL (lint): Run node packages/skillcheck/bin/skillcheck.js --fix skills/ for auto-fixable issues, then re-run
ON FAIL (test): Run single test file: cd packages/skillcheck && npx vitest run src/<file>.test.ts

Domain & Context

Goal: Rubric-graded writing and review workflows that turn rough prompts into professional-grade agent skill definitions
Type: CLI/Tool
License: Apache-2.0
Key Terms:
- Skill: Structured directory (SKILL.md + agents/ + references/) defining an AI coding agent capability
- skillcheck: Internal Node.js linter validating skill structure, frontmatter, and rubric consistency
- agnix: External linter validating specification rules (token limits, safety, cross-platform)
- Rubric: Markdown document with grade bands (A-F), P1/P2/P3 priorities, and scoring dimensions
- Generator-critic loop: Write -> Validate -> Review -> Fix cycle until quality bar met (score >= 4.5, no P1s)

Read the full file on GitHub · 128 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.

2mo ago First seen · 128 lines · 1,612 tokens per session scan C 220b9b12b30d

Subscribe to this mod's changes

skills AGENTS.md is an instructions file published in the GitHub repository jkeskikangas/skills (12 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,612 tokens to every session, about $0.0064 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

ai-agents claude codex skills

skills AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
skills AGENTS.mdjkeskikangas/skills	Instructions file	12	3mo ago	Apache-2.0	C	1,612	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

skills: Instructions file for Codex