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.
npx agentmods add instructions/martinemde/skillet/agents-mdgit clone --depth 1 https://github.com/martinemde/skilletWrote 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.
[](https://agentmods.dev/instructions/martinemde/skillet/agents-md)<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>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 | $0.01010 | $0.01010 |
| Opus 5 | $0.00505 | $0.00505 |
| Sonnet 5 | $0.00202 | $0.00202 |
| Haiku 4.5 | $0.00101 | $0.00101 |
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.
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
resolverpackage - 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
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.
- 5d ago First seen · 110 lines · 1,010 tokens per session scan A eda7b9cefac4
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.
Other instructions, from other repositories
ai-toolkit AGENTS.md
AGENTS.md instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).
superpowers-reasonix AGENTS.md
Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.
ai-mind AGENTS.md
AGENTS.md instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.
vvvv-skills CLAUDE.md
Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.
pi AGENTS.md
AGENTS.md instructions for counterposition/pi, covering agents.md, commands, pattern: pnpm --filter @counterposition/pi-web-search run, single test file and single test by name.
SciCrucible CLAUDE.md
Claude Code instructions for Xinyang-Li666/SciCrucible, covering 科学知识库, 知识库结构, 可用命令, 项目目录 and 工作原则.