Borrowing it
Nothing to install: this file belongs to ericfitz/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.
curl -O https://raw.githubusercontent.com/ericfitz/skills/main/CLAUDE.mdgit clone --depth 1 https://github.com/ericfitz/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/ericfitz/skills/claude-md)<a href="https://agentmods.dev/instructions/ericfitz/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ericfitz/skills/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/ericfitz/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/ericfitz/skills/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00866 | $0.00866 |
| Opus 5.5 | $0.00346 | $0.00346 |
| Sonnet 5.5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade C, and why
skills CLAUDE.md scanned grade C with 1 finding 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 10d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- **Skills never dump credentials.** A skill may record that a secret is referenced, its name, and where it is read — never its value. How it starts
The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — efitz-skills marketplace
A dual-harness agent-skills marketplace. Each top-level directory is a plugin bundling one or more skills, installable into Claude Code or OpenAI Codex CLI. Skills are invoked as /<plugin>:<skill>.
Exit criteria
Run all four CI checks (.github/workflows/ci.yml) before calling any change complete, whatever the change was:
uv run ruff check .
uv run pytest -q
uv run scripts/gen_codex_manifests.py --check
bash scripts/verify-marketplace.sh
This is a non-package uv project: uv run everything; never invoke python, pytest, or ruff directly. ruff is the sole linter.
Tests live in a flat tests/ directory; tests/repobuilder.py builds fixture repositories and tests/schema_check.py is the stdlib-only schema validator.
Derived artifacts (update in the same commit)
Several files are derived from the plugin/skill tree; editing the tree without them leaves verify-marketplace.sh failing on main for whoever lands next.
Adding, removing, or renaming a plugin:
<plugin>/.claude-plugin/plugin.json—nameequals the directory name;versionis semverX.Y.Z.claude-plugin/marketplace.json— add the entry, with acategorydeclared inscripts/verify-marketplace.shscripts/verify-marketplace.sh— thePLUGINSarray, format"plugin:category:skill1,skill2,...", skills in directory-listing orderuv run scripts/gen_codex_manifests.py— regenerate the Codex manifests and commit the outputREADME.md— the plugin-count sentence in the opening paragraph, and a### <plugin>section under## Pluginsdocs/ARCHITECTURE.md— a node in the dependency graph and a row in the skill catalog, if the plugin produces or consumes anything another plugin reads<plugin>/requirements.json— every CLI tool, config file, and auth session the plugin needs, each marked required or optional (/env:checkdiscovers these by glob; no change to theenvplugin is needed)
Adding, removing, or renaming a skill: items 3, 4, and 5, plus the skill's SKILL.md frontmatter name must equal its directory name and the directory must live under <plugin>/skills/.
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.
- 10d ago Changed · +4 lines · +40 tokens per session 339e9b81fe0f
- 20d ago Changed · -58 lines · -273 tokens per session cf460029154b
- 1mo ago First seen · 106 lines · 1,099 tokens per session scan C a6859824057e
skills CLAUDE.md is an instructions file published in the GitHub repository ericfitz/skills (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 866 tokens to every session, about $0.0035 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.