setup

A project setup guide for Claude Code that examines a codebase and creates project-specific instructions in a CLAUDE.md file.

In plain words
What is it for?
Use it when beginning Claude Code work on a project or when you want to initialise or improve its project instructions.
Why use it?
It removes guesswork about the project’s language, framework, commands, structure, tests, and configuration.

Skill for Claude CodeCodex

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 skills/huzaifa525/claude-code-optimizer/setup
Any agent
npx skills add huzaifa525/claude-code-optimizer --skill setup
Clone the repo
git clone --depth 1 https://github.com/huzaifa525/claude-code-optimizer

Made for: Claude Code, Codex.

Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,151 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 $0.00026 $0.01151
Opus 5 $0.00013 $0.00575
Sonnet 5 $0.00005 $0.00230
Haiku 4.5 $0.00003 $0.00115

Measured 2d ago against content hash 6f5010cb4ac0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

templates/.claude/skills/setup/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Set up Claude Code optimization for this project. Analyze the codebase and generate project-specific files.

Steps

1. Detect Project Stack

Read these files (skip if not found):

  • package.json → Node.js/JS/TS project
  • pyproject.toml or requirements.txt → Python
  • go.mod → Go
  • Cargo.toml → Rust
  • Gemfile → Ruby
  • pom.xml or build.gradle → Java
  • docker-compose.yml → Docker setup
  • turbo.json or pnpm-workspace.yaml → Monorepo

2. Find Entry Points

# Look for main/index files
Glob("**/index.{ts,js,tsx,jsx,py}")
Glob("**/main.{ts,js,py,go,rs}")
Glob("**/app.{ts,js,py}")
Glob("**/server.{ts,js}")

3. Find Route/API Registration

Grep("router|app\.(get|post|put|delete|use)|@(Get|Post|Controller)|urlpatterns|HandleFunc")

4. Detect Test Framework

Glob("**/*.test.*")
Glob("**/*.spec.*")
Glob("**/tests/**")
Glob("**/__tests__/**")

5. Detect Config Files

Glob("**/.eslintrc*")
Glob("**/.prettierrc*")
Glob("**/tsconfig.json")
Glob("**/ruff.toml")
Glob("**/.editorconfig")

6. Check Git Info

git log --oneline -5
git branch --show-current

7. Generate CLAUDE.md

Write CLAUDE.md to the project root with:

# Project: [detected name or $ARGUMENTS]

## Commands
- Build: [detected from package.json scripts or Makefile]
- Test: [detected test command]
- Lint: [detected lint command]
- Dev: [detected dev command]

## Entry Points
- [detected entry files with descriptions]

## Request Flow
[detected from framework: e.g., Client → Express → Middleware → Route → Controller → Service → DB]

## Data Flow
[detected from ORM/database setup]

## Key Decisions
- [fill in — prompt user to complete this section]

## Things That Look Wrong But Aren't
- [fill in — prompt user to complete this section]

## Conventions
- [detected from linter config, existing code patterns]
- [detected test conventions]

## Code Annotations
- Search `@claude-entry` for system entry points
- Search `@claude-pattern` for examples to follow
- Search `@claude-warning` for files not to modify

## Workflow
- New feature → /plan first, then /smart-edit to implement
- Bug fix → /debug-error or /fix-issue [number]
- Before editing unfamiliar code → /explore-area [dir]
- After all changes → /review then /commit
- Ready to merge → /create-pr
- New developer → /onboard

Read the full file on GitHub · 160 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 · 160 lines · 26 tokens per session scan A 6f5010cb4ac0

Subscribe to this mod's changes

setup is a skill published in the GitHub repository huzaifa525/claude-code-optimizer (9 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 1,151 once invoked, about $0.0001 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.