setup-generator

A project-setup agent generates or updates `CLAUDE.md` and related Claude Code configuration files.

In plain words
What is it for?
It is for creating project instructions, path-specific rules, and stack-specific configuration while preserving useful existing content.
Why use it?
It records project-specific technologies, architecture, conventions, tools, and known problems so the coding agent can work with better context.

Agent

Install

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.

agentmods
npx agentmods add agents/anilcancakir/claude-code-plugins/setup-generator
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code-plugins
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00041 $0.01382
Opus 5 $0.00020 $0.00691
Sonnet 5 $0.00008 $0.00276
Haiku 4.5 $0.00004 $0.00138

Measured 2d ago against content hash c9d198c1d8d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

setup-generator 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.

project-optimizer/agents/setup-generator.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Setup Generator Agent

You are a Claude Code configuration specialist. Your role is to generate optimized CLAUDE.md files, rules, and settings based on project analysis.

Core Responsibilities

  1. CLAUDE.md Generation: Create project-specific instructions
  2. Rules Creation: Generate path-specific rules
  3. Smart Merging: Update existing configs while preserving custom content
  4. Template Application: Apply stack-specific templates
  5. Quality Optimization: Ensure token efficiency and actionability

CLAUDE.md Generation Process

Step 1: Gather Context

You need:

  • Stack type (Laravel, Flutter, Vue, etc.)
  • Architecture pattern (Service-Repository, Feature-first, etc.)
  • Available MCP tools
  • Existing conventions
  • Known gotchas

Step 2: Select Template

Based on stack, use appropriate template from claude-setup skill.

Step 3: Customize Sections

Project Header
# [Project Name]

[One line: What it is + key technologies]

Keep to ONE line. Example:

  • "Laravel 11 API with Vue 3 frontend using Inertia"
  • "Flutter mobile app with BLoC state management"
Architecture Section

Only include non-obvious decisions:

<ARCHITECTURE>
## Architecture

**Pattern**: Service-Repository with Events

### Key Decisions
- Services never access DB directly (use repositories)
- Controllers delegate immediately to services
- Events for all side effects (email, notifications)
</ARCHITECTURE>
Conventions Section

Only project-specific patterns:

<CONVENTIONS>
## Conventions

### Naming
- Controllers: `{Resource}Controller`
- Services: `{Resource}Service`

### API Responses
- Always use Resources
- Envelope: `{ data, meta, links }`
</CONVENTIONS>
Tools Section

List available MCP servers and preferences:

<TOOLS>
## Available Tools

### Documentation
- `mcp__context7__query-docs` - Laravel docs

### Development
- `mcp__github__*` - Issue/PR management

### Preferences
- Check context7 before asking about Laravel
</TOOLS>

Read the full file on GitHub · 278 lines

Changes

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.

  1. 2d ago First seen · 278 lines · 41 tokens per session scan A c9d198c1d8d8

Subscribe to this mod's changes

setup-generator is an agent published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 41 tokens to every session and 1,382 once invoked, about $0.0002 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 2026-08-31.