project-setup

A project-setup command that creates or updates a CLAUDE.md file, which records the rules and conventions an agent should follow in a code project. It detects the project type and asks a few focused questions.

In plain words
What is it for?
Use it to start project conventions, update them, or check whether the existing CLAUDE.md is outdated or incomplete.
Why use it?
It gives the agent a shared reference for project-specific practices instead of making you repeat them in every request.

Command

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 commands/adilkalam/orca/project-setup
Clone the repo
git clone --depth 1 https://github.com/adilkalam/orca
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,834 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 $0.00011 $0.02834
Opus 5 $0.00005 $0.01417
Sonnet 5 $0.00002 $0.00567
Haiku 4.5 $0.00001 $0.00283

Measured yesterday against content hash 044b73457c19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-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 yesterday.

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.

commands/project-setup.md · 480 lines

How it starts

The opening of the file, as written. The whole thing — 480 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/project-setup - Project Conventions Wizard

Guide users through project structure decisions and generate a CLAUDE.md file tailored to their project type. Command: $ARGUMENTS

You are a project setup orchestrator that:

  • Detects project type automatically
  • Observes existing project patterns
  • Asks focused questions (4 total: 2 shared + 2 type-specific)
  • Generates actionable CLAUDE.md rules

1. Determine Subcommand

Parse $ARGUMENTS to determine mode:

Subcommand Behavior
init or empty Full initialization flow
update Update existing CLAUDE.md with new conventions
audit Check CLAUDE.md health and staleness

2. Detect Project Type

Run project type detection (inspect package.json / requirements.txt / pyproject.toml / go.mod / Gemfile / Cargo.toml and framework markers):

# iOS/Swift
if ls *.xcodeproj >/dev/null 2>&1 || ls *.xcworkspace >/dev/null 2>&1; then
  PROJECT_TYPE="ios"
# Next.js
elif [ -f "package.json" ] && grep -q '"next"' package.json 2>/dev/null; then
  PROJECT_TYPE="nextjs"
# React
elif [ -f "package.json" ] && grep -q '"react"' package.json 2>/dev/null; then
  PROJECT_TYPE="react"
# Python
elif [ -f "requirements.txt" ] || [ -f "pyproject.toml" ]; then
  PROJECT_TYPE="python"
# Flutter
elif [ -f "pubspec.yaml" ]; then
  PROJECT_TYPE="flutter"
# React Native
elif [ -f "package.json" ] && [ -d "ios" ] && [ -d "android" ]; then
  PROJECT_TYPE="react-native"
# Generic
else
  PROJECT_TYPE="generic"
fi

Output: "Detected project type: {PROJECT_TYPE}"


3. Observe Project Structure (Always On)

BEFORE asking questions, scan for existing patterns:

# Archive-like folders
find . -maxdepth 2 -type d \( -name ".archived" -o -name "_deprecated" -o -name "old" -o -name "archive" \) 2>/dev/null | head -5

# Working/temp folders
find . -maxdepth 2 -type d \( -name ".claude" -o -name ".tmp" -o -name "temp" -o -name "scratch" \) 2>/dev/null | head -5

# Documentation folders
find . -maxdepth 2 -type d \( -name "docs" -o -name "documentation" -o -name "wiki" \) 2>/dev/null | head -5

# Check for existing CLAUDE.md
ls -la CLAUDE.md 2>/dev/null

Read the full file on GitHub · 480 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. yesterday First seen · 480 lines · 11 tokens per session scan A 044b73457c19

Subscribe to this mod's changes

project-setup is a command published in the GitHub repository adilkalam/orca (2 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 2,834 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.