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/ericfitz/skills/claude-mdgit clone --depth 1 https://github.com/ericfitz/skillsWhat 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 | $0.01099 | $0.01099 |
| Opus 5 | $0.00549 | $0.00549 |
| Sonnet 5 | $0.00220 | $0.00220 |
| Haiku 4.5 | $0.00110 | $0.00110 |
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 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.
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, How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — efitz-skills marketplace
Instructions for agents working in this repository.
What this repo is
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
No task in this repo is complete until every check that applies has been run and its output confirmed. Do not report work as done on the strength of having made the edits. Run the commands, read the output, then report.
Always — the four CI checks
These are the jobs in .github/workflows/ci.yml. Run all four 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.
Derived artifacts must be updated in the same commit
Several files are derived from the plugin and skill tree. Editing that tree without
updating them leaves the repo in a state where verify-marketplace.sh fails on
main for whoever lands next.
When adding, removing, or renaming a plugin:
<plugin>/.claude-plugin/plugin.json—namemust equal the directory name;versionmust be semverX.Y.Z.claude-plugin/marketplace.json— add the entry, with acategorymatching the one declared inscripts/verify-marketplace.shscripts/verify-marketplace.sh— thePLUGINSarray, format"plugin:category:skill1,skill2,...", skills in the array order the directory listing givesuv run scripts/gen_codex_manifests.py— regenerate the Codex manifests, then commit what it wroteREADME.md— the plugin-count sentence in the opening paragraph, and a### <plugin>section in## 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— declare every CLI tool, config file, and auth session the plugin needs, marking each required or optional./env:checkdiscovers these by glob; no change to theenvplugin is needed
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 · 106 lines · 1,099 tokens per session scan C a6859824057e
skills CLAUDE.md is an instructions file published in the GitHub repository ericfitz/skills (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 1,099 tokens to every session, about $0.0055 per session on Opus 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).
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.