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/o0000-code/cc-workshop/claude-mdgit clone --depth 1 https://github.com/O0000-code/CC-WorkshopWhat 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 | $0.02584 | $0.02584 |
| Opus 5 | $0.01292 | $0.01292 |
| Sonnet 5 | $0.00517 | $0.00517 |
| Haiku 4.5 | $0.00258 | $0.00258 |
Grade B, and why
CC-Workshop 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Claude Code reads MCP config from `~/.claude.json` (NOT `~/.claude/settings.json`). The `ClaudeJson` type in `types.rs` models this: user-scope MCPs at `mcpServers`, project-scope at `projects[path].mcpServers`. Project- How it starts
The opening of the file, as written. The whole thing — 135 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
CC Workshop is a macOS desktop app for managing Claude Code configurations (Skills, MCP Servers, CLAUDE.md files, Rules). Built with Tauri 2 (Rust backend) + React/TypeScript frontend. It imports configs from ~/.claude/ and ~/.claude.json, organizes them with categories/tags, bundles them into Scenes, and deploys Scenes to projects via symlinks and .mcp.json files.
Commands
# Development (runs Vite frontend + Rust backend concurrently)
npm run tauri dev
# Production build (outputs .app to src-tauri/target/release/bundle/macos/)
npm run tauri build
# Frontend-only dev server (no Tauri IPC — limited functionality)
npm run dev
# Tests
npm test # Frontend (vitest)
npm run test:watch # Frontend watch mode
cd src-tauri && cargo test # Rust backend
npm run test:all # Both frontend + backend
# Lint
npx eslint src/ # ESLint (flat config)
Architecture
IPC Boundary
Frontend calls Rust via safeInvoke() (src/utils/tauri.ts), which wraps Tauri's invoke() with environment detection. All backend commands are registered in src-tauri/src/lib.rs via tauri::generate_handler![]. The Rust command modules live in src-tauri/src/commands/ — one file per domain (skills, mcps, config, data, etc.).
Types must stay in sync across the boundary:
- Rust:
src-tauri/src/types.rs(all types use#[serde(rename_all = "camelCase")]) - TypeScript:
src/types/index.ts,src/types/claudeMd.ts,src/types/rule.ts,src/types/plugin.ts,src/types/trash.ts
State Management
Each domain has its own Zustand store (src/stores/). Stores call safeInvoke() for persistence and apply optimistic updates. The appStore handles categories, tags, and cross-cutting UI state; domain stores (skillsStore, mcpsStore, scenesStore, etc.) handle their respective entities.
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 · 135 lines · 2,584 tokens per session scan B a9def92e128d
CC-Workshop CLAUDE.md is an instructions file published in the GitHub repository O0000-code/CC-Workshop (18 stars, last pushed 3mo ago), licensed MIT. It adds 2,584 tokens to every session, about $0.0129 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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-switch AGENTS.md
AGENTS.md instructions for ChArLiEdance/codex-switch, covering repository agents and platform isolation.
Ataru AGENTS.md
Instructions for lovstudio/Ataru, covering agents.md, design system, quick rules, color palette and common patterns.
Ataru CLAUDE.md
Instructions for lovstudio/Ataru, covering claude.md, design system, quick rules, color palette and common patterns.
ship-studio AGENTS.md
Instructions for ship-studio/ship-studio, covering agent instructions for ship studio, non-negotiables and layout in one breath.
DeepSeek-Harness-Desktop AGENTS.md
Instructions for web-casa/DeepSeek-Harness-Desktop, covering agents.md — dsh desktop, 项目本质, 不可违背的安全不变量, 版本单一事实源(改动版本时必须同时改全部) and harness 升级启动契约(bump pin 前必读).
codex-trace AGENTS.md
Instructions for PixelPaw-Labs/codex-trace, covering claude.md, commands, dev, lint and format.