my_setup

A command that creates or updates CLAUDE.md, a file containing instructions and project context for Claude Code.

In plain words
What is it for?
Use it to create the main configuration file, generate rules for specific paths, or run the full setup workflow.
Why use it?
It combines project details, brand guidance, and codebase findings so the coding assistant has clearer instructions.

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/anilcancakir/claude-code-plugins/my_setup
Clone the repo
git clone --depth 1 https://github.com/anilcancakir/claude-code-plugins
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,031 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 $0.00049 $0.02031
Opus 5 $0.00024 $0.01015
Sonnet 5 $0.00010 $0.00406
Haiku 4.5 $0.00005 $0.00203

Measured 2d ago against content hash ce4fa717c029, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

my_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.

project-optimizer/commands/my_setup.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/my_setup - Claude Code Configuration

Create optimized CLAUDE.md and Claude Code configuration by combining project context (project.md), brand guidelines (brand.md), and technical codebase analysis.

1. /my_project → Creates project.md (project brief)
2. /my_brand   → Creates brand.md (brand guidelines)
3. /my_setup   → Creates CLAUDE.md (technical config)

Arguments

  • No arguments: Full setup workflow
  • --claude-md-only: Only create/update CLAUDE.md
  • --rules-only: Only generate path-specific rules
  • --full: Complete setup including rules and hooks

Workflow

Phase 1: Context Discovery

Check for existing project context:

# Check for project.md (project brief)
ls -la project.md PROJECT.md 2>/dev/null

# Check for brand.md (brand guidelines)
ls -la brand.md BRAND.md 2>/dev/null

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

# Check .claude directory
ls -la .claude/ 2>/dev/null

Present findings:

CONTEXT DISCOVERY
=================

Project Context:
- project.md: [Found / Not found]
- brand.md: [Found / Not found]
- CLAUDE.md: [Found / Not found]

[If project.md or brand.md missing:]

RECOMMENDATION:
For best results, create project.md and brand.md first:

1. Run /my_project - Define project identity and goals
2. Run /my_brand - Define brand guidelines
3. Then run /my_setup - Create CLAUDE.md

Continue anyway?
1. Yes, proceed with technical analysis only
2. Run /my_project first
3. Run /my_brand first

Phase 2: Extract Context

If project.md exists, extract:

  • Project name and description
  • Target audience (for tone calibration)
  • Core features (for architecture context)
# Read project.md for context
cat project.md 2>/dev/null

If brand.md exists, extract:

  • Brand archetype (for voice/tone)
  • Color palette (for design rule generation)
  • Typography (for style consistency)
# Read brand.md for context
cat brand.md 2>/dev/null

Read the full file on GitHub · 387 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 · 387 lines · 49 tokens per session scan A ce4fa717c029

Subscribe to this mod's changes

my_setup is a command published in the GitHub repository anilcancakir/claude-code-plugins (6 stars, last pushed 7mo ago), licensed MIT. It adds 49 tokens to every session and 2,031 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.