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 skills add MadAppGang/claude-code --skill setupgit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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.
[](https://agentmods.dev/skills/madappgang/claude-code/setup)<a href="https://agentmods.dev/skills/madappgang/claude-code/setup"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/setup/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.
<a href="https://agentmods.dev/skills/madappgang/claude-code/setup"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00016 | $0.01925 |
| Opus 5.5 | $0.00006 | $0.00770 |
| Sonnet 5.5 | $0.00003 | $0.00385 |
| Haiku 4.5 | $0.00002 | $0.00193 |
Grade A, and why
setup 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 1mo 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plugin: conductor updated: 2026-01-20
<resume_capability>
Check for conductor/setup_state.json FIRST.
If exists with status != "complete":
1. Load saved answers
2. Resume from last incomplete section
3. Show user what was already collected
</resume_capability>
<question_protocol>
- Ask questions SEQUENTIALLY (one at a time)
- Maximum 5 questions per section
- Always include "Type your own answer" option
- Use AskUserQuestion with appropriate question types
- Save state after EACH answer (for resume)
</question_protocol>
<validation_first>
Before any operation:
1. Check if conductor/ already exists
2. If complete setup exists, ask: "Re-initialize or abort?"
3. Respect .gitignore patterns
</validation_first>
</critical_constraints>
<core_principles> Never ask multiple questions at once. Wait for answer before asking next question.
<principle name="State Persistence" priority="critical">
Save progress after each answer.
Enable resume from any interruption point.
</principle>
<principle name="Context Quality" priority="high">
Gather enough context to be useful.
Don't overwhelm with excessive questions.
</principle>
</core_principles>
<phase number="2" name="Project Type Detection">
<step>Check for existing code files (src/, package.json, etc.)</step>
<step>Ask user: Greenfield (new) or Brownfield (existing)?</step>
<step>For Brownfield: Scan existing code for context</step>
</phase>
<phase number="3" name="Product Context">
<step>Ask: What is this project about? (1-2 sentences)</step>
<step>Ask: Who is the target audience?</step>
<step>Ask: What are the 3 main goals?</step>
<step>Ask: Any constraints or requirements?</step>
<step>Generate product.md from answers</step>
</phase>
<phase number="4" name="Technical Context">
<step>Ask: Primary programming language(s)?</step>
<step>Ask: Key frameworks/libraries?</step>
<step>Ask: Database/storage preferences?</step>
<step>Ask: Deployment target?</step>
<step>Generate tech-stack.md from answers</step>
</phase>
<phase number="5" name="Guidelines">
<step>Ask: Any specific coding conventions?</step>
<step>Ask: Testing requirements?</step>
<step>Generate product-guidelines.md</step>
<step>Generate code_styleguides/general.md (always)</step>
<step>Generate language-specific styleguides based on tech stack:
- TypeScript/JavaScript → typescript.md, javascript.md
- Web projects → html-css.md
- Python → python.md
- Go → go.md
</step>
</phase>
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.
- 1mo ago First seen · 241 lines · 16 tokens per session scan A 8477e4912e04
setup is a skill published in the GitHub repository MadAppGang/claude-code (287 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 1,925 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
project-init
Sets up the 4-file AI memory system for any project.
scaffold
Use when starting hyperflow in a new project, refreshing the .hyperflow/ cache, or installing auto-detection shims (AGENTS.md, CLAUDE.md). One-shot project setup; does not start the spec → scope → dispatch chain. Trigger with /hyperflow:scaffold, "init hyperflow", "set up hyperflow", "refresh hyperflow", "install…
mindos-views
Manage shared local people and project tasks, generate reusable tables or boards, and compose/customize multi-source MindOS work pages with isolated custom HTML. Use when the user asks to maintain contacts, follow-ups or tasks, build a personal dashboard, or adjust a page with AI.
workspace-manager
Registers, lists, removes, and assigns workspaces (project directories) for Anima work. Use when: binding project paths to Anima, managing aliases, or switching workspace roots.
frontmcp-setup
Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…
project-planner
Detailed implementation plans and spec-driven development.