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/eagerworks/skills/claude-mdgit clone --depth 1 https://github.com/eagerworks/skillsWrote 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/eagerworks/skills/claude-md)<a href="https://agentmods.dev/instructions/eagerworks/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/eagerworks/skills/claude-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 | $0.01798 | $0.01798 |
| Opus 5 | $0.00899 | $0.00899 |
| Sonnet 5 | $0.00360 | $0.00360 |
| Haiku 4.5 | $0.00180 | $0.00180 |
Grade A, and why
skills 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 today.
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 — 67 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.
What this repo is
eagerworks/skills is a collection of portable markdown agent skills — not a runnable library. There is no build, lint, or compile step. The "product" is documentation that teaches coding agents (Claude Code, Cursor, Copilot, Codex, Amp, any skills.sh-compatible tool) how to do a specific job well. Contributions are almost always edits to markdown files.
Architecture
Two parallel trees, intentionally kept separate (see docs/decision-records/2026-06-30--evals-separate-from-skills.md):
skills/<name>/ # SHIPPED to users — the skills.sh CLI copies this whole dir
SKILL.md # agent entrypoint: frontmatter `description` (match trigger) + lean hub
references/*.md # in-depth docs, loaded by the agent ON DEMAND
assets/ # copyable starter files / templates (e.g. deploy.yml)
README.md # human-facing overview
evals/<name>/ # NOT shipped — repo-level test harness
evals.json # question/answer + expectations pairs that verify skill quality
The boundary is the rule: anything users should receive goes inside skills/<name>/; anything purely for developing or validating the skill stays out of it. evals/<name>/ mirrors the skill name. The skills.sh CLI ships the entire directory containing a SKILL.md, which is why evals must live outside it.
Progressive disclosure (the core design principle)
SKILL.md is loaded up front, so it must stay lean — it's a hub: when-to-use frontmatter, a version-detection step, a table pointing to references/*.md, and critical gotchas. Depth belongs in references/*.md, which the agent opens only when relevant. When editing, push detail down into references/ rather than growing SKILL.md.
The skills
kamal deploys Dockerized apps with Kamal. Version-aware: defaults to Kamal 2.x; all Kamal 1.9.x content lives exclusively in references/kamal-v1.md. SKILL.md opens with a version-detection step (kamal version, or infer from traefik:/.env → v1 vs proxy:/.kamal/secrets → v2). When adding version-specific examples, mark them (# Kamal 2.x only / # Kamal 1.x only) and never mix v1 syntax into the v2 references.
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.
- today Changed · +4 lines · +280 tokens per session 6be2365b292a
- 4d ago First seen · 63 lines · 1,518 tokens per session scan A df0c5a477a35
skills CLAUDE.md is an instructions file published in the GitHub repository eagerworks/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 1,798 tokens to every session, about $0.0090 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.
Other instructions, from other repositories
stewie-pixel guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
vanguard-frontier-agentic copilot-instructions.md
Copilot instructions for VincentChuWaiChow/vanguard-frontier-agentic, covering vanguard frontier agentic repository instructions, what to optimize for, repo structure, rules for changes and cross-platform asset rule.
skills CLAUDE.md
Instructions for mixedbread-ai/skills, covering mixedbread skills, repository structure, conventions, adding a new skill and testing a skill.
symphony AGENTS.md
Instructions for broomva/symphony, covering agents.md - symphony, repository purpose, architecture, key design decisions and gathering context from the knowledge graph.
agent-skills AGENTS.md
AGENTS.md instructions for racastellanosm/agent-skills, covering agents.md, 1. vision & architectural invariants, 2. repository architecture & layout, 3. harness support & installation paths and 4. scripting & tooling guardrails.
kleinanzeigen-reader CLAUDE.md
Instructions for its-me-prash/kleinanzeigen-reader, covering claude.md — kleinanzeigen-reader, what this repo is, auto-load instructions for claude code, quick command reference and fetch a listing.