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/oscaner/skills/claude-mdgit clone --depth 1 https://github.com/Oscaner/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/oscaner/skills/claude-md)<a href="https://agentmods.dev/instructions/oscaner/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/oscaner/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 | $0.01176 | $0.01176 |
| Opus 5 | $0.00588 | $0.00588 |
| Sonnet 5 | $0.00235 | $0.00235 |
| Haiku 4.5 | $0.00118 | $0.00118 |
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 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 — 81 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.
Repository purpose
A multi-harness AI coding skills marketplace. Skills work across Claude Code, Cursor, Droid, Pi, Grok, Qoder, Codex, and Gemini. Personal skills are packaged as installable plugins consumed by AI coding harnesses.
Five plugins ship here:
- osuperpowers — first-party, in-tree at
packages/osuperpowers/. osuperpowers orchestration + cli-* family + CDD engine + gate. - osuperpowers-router — first-party, in-tree at
packages/osuperpowers-router/. Trigger router: no skill bodies, maps upstream triggers to osuperpowers/mattpocock targets. - superpowers — vendored submodule at
vendors/superpowers/. Upstream workflow skills read by osuperpowers orchestrators. - mattpocock-skills — vendored submodule at
vendors/mattpocock-skills/. Engineering precision skills (grilling, tdd, to-tickets, research). - impeccable — vendored submodule at
vendors/impeccable/. Frontend design skills.
Package-as-source architecture
The canonical registry marketplace/source.json is derived, not hand-edited. pnpm run emit rebuilds it from first-party package.json#oscaner-plugin fields and vendored assembly templates, then regenerates every harness-specific manifest (.claude-plugin/, .cursor-plugin/, .codex-plugin/, .qoder-plugin/, .agents/skills/, gemini-extension.json, hooks files).
Adding a new first-party plugin: create packages/<name>/package.json with oscaner-plugin field → pnpm run emit auto-discovers and generates all manifests.
Key commands
pnpm run emit # regenerate all harness manifests from package.json
pnpm run emit:check # verify emit output is fresh (no drift, exit 1 if stale)
pnpm run validate # full validation suite (emit check + plugin resolution + tests + version sync)
pnpm run changeset # create a changeset for versioning
pnpm run version # apply changesets to bump versions
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 · 81 lines · 1,176 tokens per session scan A 3ec05444a1ab
skills CLAUDE.md is an instructions file published in the GitHub repository Oscaner/skills (79 stars, last pushed today), licensed MIT. It adds 1,176 tokens to every session, about $0.0059 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
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.
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).
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.
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.