Borrowing it
Nothing to install: this file belongs to Milktang0128/myskills. 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/Milktang0128/myskills/main/CLAUDE.mdgit clone --depth 1 https://github.com/Milktang0128/myskillsWrote 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/milktang0128/myskills/claude-md)<a href="https://agentmods.dev/instructions/milktang0128/myskills/claude-md"><img src="https://agentmods.dev/badge/instructions/milktang0128/myskills/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 5.1 | $0.02093 | $0.02093 |
| Opus 5 | $0.01046 | $0.01046 |
| Sonnet 5 | $0.00419 | $0.00419 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
myskills 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 8d 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 — 85 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.
Project
MySkills — an Electron desktop app (macOS-only for MVP) that aggregates AI agent skills across Claude Code, Codex, and a user-maintained shared pool into a single searchable, scenario-organized hub. The authoritative product spec is SPEC.md (Chinese) — any implementation that diverges from it should update the spec first.
Current state: MVP-A is built (read-only inventory + scenarios + Discover via skills.sh + optional BYOK AI). MVP-B (writes: sync, enable/disable) is partially in place — electron/sync/ and the sync:* IPC channels exist, but the renderer-visible UI is gated behind plan-confirm flows. See README.md for the user-facing feature list.
Commands
npm run dev # Runs Next dev (port 4477) + Electron concurrently, with wait-on
npm run dev:next # Next.js renderer only
npm run dev:electron # Electron main process only (tsx, waits for tcp:4477)
npm run build # next build → out/, then tsc electron → dist-electron/
npm run package # build, then electron-builder --mac (DMG)
npm run rebuild # electron-rebuild for better-sqlite3 (run after npm install fails native build)
No test runner or linter is wired up yet — don't claim "tests pass" without first wiring one in.
Architecture
Two TypeScript projects, one repo
The renderer and main process are compiled by separate tsconfig.json files, and the root tsconfig.json explicitly excludes electron/. Don't import renderer code from electron/ or vice versa — only shared/ is allowed across the boundary.
tsconfig.json(root) — Next.js renderer.module: esnext,jsx: preserve,noEmit. Path aliases:@/*→src/*,@shared/*→shared/*.- electron/tsconfig.json — Main process.
module: CommonJS, emits todist-electron/.rootDir: ..soshared/compiles in too. Excludesdev.ts(run via tsx in dev).
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.
- 8d ago First seen · 85 lines · 2,093 tokens per session scan A 81f16386b1b2
myskills CLAUDE.md is an instructions file published in the GitHub repository Milktang0128/myskills (58 stars, last pushed 2mo ago), licensed MIT. It adds 2,093 tokens to every session, about $0.0105 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
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 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.
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).
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.