skillet AGENTS.md

skillet AGENTS.md is an instructions file for Codex, OpenCode from martinemde/skillet. It costs 1,010 tokens per session, scanned A, original, MIT.

A set of instructions for Skillet, a Go command-line tool that runs Claude agent skills and shell commands. It explains the project's architecture and requires testing, formatting, and linting before finishing.

In plain words
What is it for?
Use it when developing Skillet, especially its command handling, skill-file parsing, execution flow, output formatting, or cancellation behavior.
Why use it?
It helps an agent follow the project's structure and quality checks instead of making changes without verifying them.

Instructions file for CodexOpenCode

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/martinemde/skillet/agents-md
Clone the repo
git clone --depth 1 https://github.com/martinemde/skillet

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 skillet AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/martinemde/skillet/agents-md.svg)](https://agentmods.dev/instructions/martinemde/skillet/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/martinemde/skillet/agents-md"><img src="https://agentmods.dev/badge/instructions/martinemde/skillet/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,010 This file is loaded in full into every session.
When invoked 1,010 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 $0.01010 $0.01010
Opus 5 $0.00505 $0.00505
Sonnet 5 $0.00202 $0.00202
Haiku 4.5 $0.00101 $0.00101

Measured 5d ago against content hash eda7b9cefac4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillet 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 5d 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 · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

Skillet is a CLI tool written in Go that executes Claude Agent Skills (from agentskills.io) and commands as shell scripts with formatted output. It parses SKILL.md and command.md files, extracts frontmatter configuration (allowed-tools, model, etc.), interpolates variables like {baseDir}, and invokes the Claude CLI with appropriate permissions in headless mode. Output is formatted using Charm libraries (glamour, lipgloss) for clean terminal rendering.

Always test, format and lint code before finishing

go test ./...
go fmt ./...
golangci-lint run

Architecture

Core Components

main.go (cmd/skillet/main.go): Entry point that orchestrates the execution flow:

  • Parses CLI flags using custom flag separation logic to support flags anywhere in args
  • Resolves skill/command name → file path via resolver package
  • Builds executor config from merged CLI flags + frontmatter
  • Runs executor and formatter concurrently using pipes
  • Handles signals and context cancellation

parser (internal/parser/): Parses SKILL.md files with YAML frontmatter

  • Extracts frontmatter (name, description, allowed-tools, model, etc.)
  • Interpolates {baseDir} variables in content
  • Validates skill structure and constraints (name format, field lengths)

command (internal/command/): Parses command .md files (similar to skills but simpler)

  • Derives command name from filename
  • Supports optional frontmatter (description can be auto-extracted from content)
  • Handles variable interpolation like skills

executor (internal/executor/): Builds and runs claude CLI commands

  • Constructs args from resolved config (model, allowed-tools, system-prompt, etc.)
  • Executes in headless mode with -p --verbose --output-format stream-json
  • Provides dry-run mode to show command without executing

formatter (internal/formatter/): Processes claude's stream-json output into readable markdown

Read the full file on GitHub · 110 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. 5d ago First seen · 110 lines · 1,010 tokens per session scan A eda7b9cefac4

Subscribe to this mod's changes

skillet AGENTS.md is an instructions file published in the GitHub repository martinemde/skillet (19 stars, last pushed 2mo ago), licensed MIT. It adds 1,010 tokens to every session, about $0.0051 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.