What is myskills CLAUDE.md?

Project instructions for MySkills, a macOS Electron app that collects AI-agent skills into one searchable desktop hub. A monorepo is one code repository containing multiple related projects; here it includes the app’s main process and interface.

It helps develop, run, test, type-check, build, and package the Electron app, including its skill inventory and synchronization features.

It explains the current product boundaries, development commands, package manager, and which features are complete or still being added.

How Milktang0128/myskills configures Claude Code

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/Milktang0128/myskills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Milktang0128/myskills

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/milktang0128/myskills/claude-md/github.svg)](https://agentmods.dev/instructions/milktang0128/myskills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/milktang0128/myskills/claude-md"><img src="https://agentmods.dev/badge/instructions/milktang0128/myskills/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/milktang0128/myskills/claude-md"><img src="https://agentmods.dev/badge/instructions/milktang0128/myskills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,093 This file is loaded in full into every session.

When invoked 2,093 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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 5.5	$0.00837	$0.00837
Sonnet 5.5	$0.00419	$0.00419
Haiku 4.5	$0.00209	$0.00209

Measured 2mo ago against content hash 81f16386b1b2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

CLAUDE.md · 85 lines

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 to dist-electron/. rootDir: .. so shared/ compiles in too. Excludes dev.ts (run via tsx in dev).

Read the full file on GitHub · 85 lines

Changes

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.

2mo ago First seen · 85 lines · 2,093 tokens per session scan A 81f16386b1b2

Subscribe to this mod's changes

myskills CLAUDE.md is an instructions file published in the GitHub repository Milktang0128/myskills (61 stars, last pushed 4mo ago), licensed MIT. It adds 2,093 tokens to every session, about $0.0084 per session on Opus 5.5. 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.

myskills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
myskills CLAUDE.mdMilktang0128/myskills	Instructions file	61	4mo ago	MIT	A	2,093	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

myskills: Instructions file for Claude Code