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/compozy/skeeper/claude-mdgit clone --depth 1 https://github.com/compozy/skeeperWhat 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 | $0.03290 | $0.03290 |
| Opus 5 | $0.01645 | $0.01645 |
| Sonnet 5 | $0.00658 | $0.00658 |
| Haiku 4.5 | $0.00329 | $0.00329 |
Grade A, and why
skeeper CLAUDE.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 2d 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.
This is a copy
100% identical to skeeper AGENTS.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides project guidance for coding agents working in this repository.
HIGH PRIORITY
- IF YOU DON'T CHECK SKILLS your task will be invalidated and we will generate rework
- YOU CAN ONLY finish a task if
make verifypasses at 100% (runsfmt + lint + test + build). No exceptions — failing any of these commands means the task is NOT COMPLETE make linthas zero tolerance. Zero issues allowed — any golangci-lint issue is a blocking failure- ALWAYS check dependent package APIs before writing integration code or tests to avoid writing wrong code
- NEVER use workarounds — always use the
no-workaroundsskill for any fix/debug task +testing-anti-patternsfor tests - ALWAYS use the
no-workaroundsandsystematic-debuggingskills when fixing bugs or complex issues - NEVER use web search tools to search local project code — for local code, use Grep/Glob instead
- YOU SHOULD NEVER add dependencies by hand in
go.mod— always usego getinstead
MANDATORY REQUIREMENTS
- MUST run
make verifybefore completing ANY subtask - ALWAYS USE the
golang-proskill before writing any Go code - ALWAYS USE the
systematic-debugging+no-workaroundsskills before fixing any bug - ALWAYS USE the
testing-anti-patternsskill before writing or modifying tests - ALWAYS USE the
verification-before-completionskill before claiming any task is done - Skipping any verification check will result in IMMEDIATE TASK REJECTION
Project Overview
skeeper is a single-binary Go command-line interface built with production-grade patterns and agent-ready tooling. The CLI is structured around cobra and exposes subcommands wired through internal/cli.
Toolchain pin: Go 1.26.2 (managed via mise.toml + .go-version), Bun 1.3.4 (.bun-version), golangci-lint v2.11.4, gotestsum v1.13.0, gopls/modernize v0.21.1, goreleaser v2.6.1. Run mise install to provision everything.
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.
- 2d ago First seen · 232 lines · 3,290 tokens per session scan A 1edb092b300c
skeeper CLAUDE.md is an instructions file published in the GitHub repository compozy/skeeper (85 stars, last pushed 3mo ago), licensed MIT. It adds 3,290 tokens to every session, about $0.0164 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to skeeper AGENTS.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.