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 commands/thelobbi/claude/cc-setupgit clone --depth 1 https://github.com/TheLobbi/claudeWhat 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 | $0.00000 | $0.08660 |
| Opus 5 | $0.00000 | $0.04330 |
| Sonnet 5 | $0.00000 | $0.01732 |
| Haiku 4.5 | $0.00000 | $0.00866 |
Grade F, and why
cc-setup scanned grade F with 4 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
"sudo rm" Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
"Bash(curl * | sh)", Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"rm -rf /" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"curl.*| sh" How it starts
The opening of the file, as written. The whole thing — 1,013 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cc-setup — Full Repo Analysis & 4-Layer Claude Code Deployment
Analyze the current repository, detect its tech stack, and deploy a complete Claude Code configuration using the 4-layer extension stack: CLAUDE.md (routing OS), Skills (capability packs), Hooks (guardrails & automation), and Agents (specialized workers). Also configures MCP servers, LSP hints, memory architecture, and cost optimization.
Usage
/cc-setup # Full interactive setup
/cc-setup --auto # Non-interactive, best-guess defaults
/cc-setup --dry-run # Show what would be configured without writing
/cc-setup --mcp-only # Only detect and install MCP servers
/cc-setup --audit # Audit existing setup, score it, suggest improvements
/cc-setup --preset power-user # Use a curated preset
The 4-Layer Extension Stack
The most effective Claude Code setups use all four layers together. /cc-setup deploys all of them
based on detected project characteristics.
| Layer | What | Where | Loaded |
|---|---|---|---|
| CLAUDE.md | Routing OS — project rules, build commands, architecture constraints | CLAUDE.md + .claude/rules/*.md + per-directory CLAUDE.md |
Always (session start) |
| Skills | Modular capability packs — domain playbooks, workflow recipes | .claude/skills/*/SKILL.md |
Frontmatter always; body on activation |
| Hooks | Guardrails & automation — format, lint, notify, enforce, capture | .claude/settings.json → hooks + .claude/hooks/*.sh |
On lifecycle events |
| Agents | Specialized workers — distinct system prompts, models, tool access | .claude/agents/*.md |
On invocation or auto-trigger |
Phase 1: Repo Analysis (read-only)
Scan the repo to build a project fingerprint. All detection is non-destructive.
1.1 Language & Framework Detection
# Languages
DETECT_MAP=(
"package.json:Node.js"
"tsconfig.json:TypeScript"
"requirements.txt:Python"
"pyproject.toml:Python"
"Pipfile:Python"
"go.mod:Go"
"Cargo.toml:Rust"
"pom.xml:Java/Maven"
"build.gradle:Java/Gradle"
"build.gradle.kts:Kotlin/Gradle"
"Gemfile:Ruby"
"composer.json:PHP"
"*.csproj:C#/.NET"
"Package.swift:Swift"
"mix.exs:Elixir"
"deno.json:Deno"
"Makefile:Make"
)
# Frameworks
FRAMEWORK_MAP=(
"next.config.*:Next.js"
"nuxt.config.*:Nuxt.js"
"vite.config.*:Vite"
"angular.json:Angular"
"svelte.config.*:SvelteKit"
"remix.config.*:Remix"
"astro.config.*:Astro"
"gatsby-config.*:Gatsby"
"nest-cli.json:NestJS"
"manage.py:Django"
"app.py+flask:Flask"
"main.py+fastapi:FastAPI"
"config/routes.rb:Rails"
"src/main/+spring:Spring Boot"
"expo-env.d.ts:Expo/React Native"
"tauri.conf.json:Tauri"
"electron-builder.*:Electron"
)
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 · 1,013 lines · 0 tokens per session scan F 4e86ee3834af
cc-setup is a command published in the GitHub repository TheLobbi/claude (21 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 8,660 tokens. A static security scan graded it F with 4 findings (asks for root, downloads and executes remote code, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.