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 skills/o0000-code/cc-workshop/cc-workshop-proposenpx skills add O0000-code/CC-Workshop --skill cc-workshop-proposegit 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 | $0.00070 | $0.03870 |
| Opus 5 | $0.00035 | $0.01935 |
| Sonnet 5 | $0.00014 | $0.00774 |
| Haiku 4.5 | $0.00007 | $0.00387 |
Grade A, and why
ensemble-propose 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 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.
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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CC Workshop Research & Propose
Overview
Act as a product-minded engineer for the CC Workshop Tauri 2 desktop application. Your role is NOT to find bugs (Patrol does that) or implement features (Implement does that). Your role is to deeply analyze the dual-language codebase, think about the product holistically, and propose well-researched improvements that a human can review and approve.
Core Philosophy: Depth over breadth. 1-2 thoroughly analyzed, actionable proposals are worth far more than 10 surface-level suggestions. Each proposal must demonstrate genuine code-level understanding across both the React frontend and Rust backend, and provide a concrete implementation path.
Project Context
- Frontend: React 18 + TypeScript 5.9 + Tailwind CSS 4 + Zustand 5
- Backend: Tauri 2.9 + Rust (edition 2021)
- Testing: Vitest + @testing-library/react (frontend), cargo test (backend)
- Key Frontend Directories:
src/pages/-- Page-level components (ProjectsPage, ScenesPage, SkillsPage, McpServersPage, ClaudeMdPage, SettingsPage, CategoryPage, TagPage, detail pages)src/components/-- Reusable components organized by domain (common/, layout/, sidebar/, scenes/, skills/, mcps/, claude-md/, projects/, modals/, launcher/)src/stores/-- Zustand stores (appStore, skillsStore, mcpsStore, scenesStore, projectsStore, claudeMdStore, settingsStore, launcherStore, pluginsStore, trashStore, importStore)src/types/-- TypeScript type definitions (index.ts, claudeMd.ts, trash.ts, plugin.ts)src/utils/-- Utility functions including Tauri IPC wrapper (tauri.ts)
- Key Backend Directories:
src-tauri/src/commands/-- Tauri command handlers (skills.rs, mcps.rs, claude_md.rs, data.rs, config.rs, classify.rs, symlink.rs, import.rs, plugins.rs, trash.rs, usage.rs, dialog.rs)src-tauri/src/utils/-- Utility modules (parser.rs, path.rs)src-tauri/src/types.rs-- Shared Rust type definitionssrc-tauri/src/lib.rs-- App setup and command registration
- Repo: https://github.com/O0000-code/CC-Workshop.git
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 · 260 lines · 70 tokens per session scan A 6ff69821c746
ensemble-propose is a skill published in the GitHub repository O0000-code/CC-Workshop (18 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 3,870 once invoked, about $0.0003 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 skills, from other repositories
papr-rss
Read, search and triage the user's Papr RSS subscriptions from the shell via the papr CLI. Use when the user wants to catch up on their feeds, find or summarize articles they've subscribed to, check what's unread, star/save articles, subscribe to a new feed, or pull new posts. Triggers on: "what's in my feeds", "any…
asc-ppp-pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.
release
Use when the maintainer wants to cut, prepare, or ship a code-by-wire release — e.g. says "bump version", "bump vX.Y.Z", "release it", "ship it", or "cut a release" — whether before the release (preparing the version bump and the changelog PR) or after the bump PR has merged (tagging and publishing).
vibeshell
Use the native VibeShell CLI to manage saved SSH servers, persistent sessions, remote commands, SFTP transfers, remote files, and SSH configuration imports without requiring the desktop UI.
project-structure
Use when orienting within the Hermes Agent CN Desktop codebase, locating source files, understanding the Tauri+React architecture, finding Rust commands or frontend modules, or navigating the monorepo. Triggers: project structure, 项目结构, where is, 在哪里, codebase overview, 代码概览, repository layout, how is this repo…
workspace-dispatch
Autonomous multi-agent mission orchestrator. Decomposes a mission into tasks, spawns sub-agents for each step, reviews output against exit criteria, and chains tasks automatically with retry. State persists to disk so missions survive context loss. Triggered by the Conductor UI or by direct user request.