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/robotbird/skillkit/claude-mdgit clone --depth 1 https://github.com/robotbird/skillkitWhat 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 | $0.02722 | $0.02722 |
| Opus 5 | $0.01361 | $0.01361 |
| Sonnet 5 | $0.00544 | $0.00544 |
| Haiku 4.5 | $0.00272 | $0.00272 |
Grade B, and why
skillkit CLAUDE.md scanned grade B 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.
Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
- Installed skills: each tool's user-level dir under `~` (`~/.claude/skills`, `~/.codex/skills`, `~/.cursor/skills`, `~/.trae/skills`, …) How it starts
The opening of the file, as written. The whole thing — 95 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.
What this is
Skillkit — manage "skills" across AI coding tools (Claude Code, Codex, Cursor, Trae, Workbuddy): browse the skills.sh marketplace, install/uninstall from market/GitHub/zip, and share installed skills via short links. A pnpm-workspace monorepo with two parts:
apps/desktop— Electron desktop client (React 18 + TypeScript + Vite + better-sqlite3). This is what's open-sourced here.packages/types—@skillkit/types: cross-process shared types & constants (single source of truth).
The server (share short-link API + web 个人中心, Next.js 16) used to live here as apps/server but has moved to a separate repo at ../skillkit.net (the product 官网 + backend). The desktop client talks to it over HTTPS at https://skillkit.net (share + auth endpoints; login = https://skillkit.net/login, no account. subdomain). packages/types is mirrored (vendored) into that repo so the wire contract stays in sync — when you change share/auth types or the tool list here, update the vendored copy in skillkit.net/lib/shared-types.ts too.
Commands
Run from the repo root.
pnpm install # workspace install (links @skillkit/types, installs apps/desktop deps)
# Desktop (apps/desktop)
pnpm --filter desktop run rebuild # REQUIRED: rebuilds better-sqlite3 against Electron's ABI. Run after install / Electron bumps.
# ⚠️ Must use `run rebuild` — `pnpm rebuild` is a pnpm built-in that reruns install scripts against the *system* Node ABI (→ NODE_MODULE_VERSION mismatch); only the `scripts.rebuild` entry (`electron-rebuild -f -w better-sqlite3`) compiles against Electron's headers.
pnpm --filter desktop dev # Full Electron app in dev (vite-plugin-electron launches Electron + watches all 3 bundles)
pnpm --filter desktop build # tsc -p both tsconfigs (typecheck, noEmit) + vite build
pnpm --filter desktop pack # build + electron-builder --dir (unpacked, for debugging)
pnpm --filter desktop dist # build + electron-builder → release/ (mac dmg/zip, win nsis)
# Repo-wide (turbo)
pnpm dev # turbo dev — runs desktop dev
pnpm build # turbo build
pnpm typecheck # turbo typecheck
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 · 95 lines · 2,722 tokens per session scan B fdfa69bc961b
skillkit CLAUDE.md is an instructions file published in the GitHub repository robotbird/skillkit (56 stars, last pushed 9d ago), licensed MIT. It adds 2,722 tokens to every session, about $0.0136 per session on Opus 5. A static security scan graded it B with 1 finding (enumerates other installed skills). 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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.