swe-skills: Instructions file for Codex

AGENTS.md

swe-skills AGENTS.md is an instructions file for Codex, OpenCode from ckorhonen/swe-skills. It costs 545 tokens per session, scanned A, original, MIT.

A set of repository instructions for a collection of software-engineering skills and their evaluation tests. It explains the folder structure, skill naming, installation command, and the website that lists the skills.

In plain words
What is it for?
Use it when adding a skill, updating evaluation files, installing the collection, or synchronizing skill cards, schedules, counts, and page metadata in the marketing site.
Why use it?
It keeps new or changed skills consistent with the repository's naming, installation, and documentation rules. It also prevents the catalogue website from becoming out of date.

Instructions file for CodexOpenCode

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

This is ckorhonen/swe-skills's own configuration. It tells Codex and OpenCode how to work on swe-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 swe-skills configures →

Reuse

Borrowing it

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

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ckorhonen/swe-skills/agents-md.svg)](https://agentmods.dev/instructions/ckorhonen/swe-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ckorhonen/swe-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/ckorhonen/swe-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 545 This file is loaded in full into every session.
When invoked 545 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 $0.00545 $0.00545
Opus 5 $0.00272 $0.00272
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00055 $0.00055

Measured 8d ago against content hash 7f1028f8e7fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

swe-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 8d 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SWE Skills & Eval Suite

This repository stores AI skill files and evaluation suites for SWE workflows.

Repository scope

  • skills/ contains skill definitions.
  • evals/ contains evaluation suites and fixtures.
  • README.md is the primary overview and usage guide for the repository.

Naming convention

  • Every skill identifier/name must be prefixed with swe:.
  • Avoid creating new skill names that do not start with swe:.

Installation

  • Install skills with npx skills install ckorhonen/swe-skills.
  • Document install examples using npx skills install ckorhonen/swe-skills, not alternate commands.

Marketing site (site/)

  • site/ contains the static marketing website deployed to cdd.dev/skill/.
  • The site showcases all swe: skills with descriptions, example prompts, sample output, and suggested schedules.

Site sync rules

  • Adding a skill: Add a skill card to the appropriate category section in site/index.html. Include the skill name, one-line description, and an example prompt. Add it to the relevant schedule card in the Schedules section. Update the skill count in the hero lede, Framework section, and page title if the total changes.
  • Removing a skill: Remove the skill card, its schedule entry, and adjust counts accordingly.
  • Modifying a skill: After changing a skill's description, trigger conditions, or output format, review site/index.html for accuracy. Update the skill card description, example prompt, or sample output if they no longer reflect the skill's behavior.
  • Deploying changes: After editing site/, run wrangler deploy from this repo root. The site is served by the swe-skills-site Cloudflare Worker (configured in wrangler.toml).

Workflow notes

  • Keep additions narrowly scoped.
  • Keep files small and reviewable.
  • Before creating or revising anything under skills/ and the matching evals/ assets, use swe:create-skill first. It contains the repo-local, distilled authoring guidance adapted from Anthropic's skill-building guide.
  • Co-locate related skill and eval assets in their feature directories.
  • Update README.md whenever repository structure, install flow, or skill/eval workflows change.
  • Do not land changes that make README.md materially inaccurate.
  • Do not land changes to skills without checking site/index.html for accuracy.

Read the full file on GitHub · 55 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. 8d ago First seen · 55 lines · 545 tokens per session scan A 7f1028f8e7fa

Subscribe to this mod's changes

swe-skills AGENTS.md is an instructions file published in the GitHub repository ckorhonen/swe-skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 545 tokens to every session, about $0.0027 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.

Related

Other instructions, from other repositories

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 · 5,153 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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens