setup

A command that checks a repository's Claude Code setup or creates one when it is missing. Claude Code configuration can include instructions, rules, settings, and reusable skills for the coding agent.

In plain words
What is it for?
Use it to audit existing .claude files, create an initial configuration, or force regeneration when needed.
Why use it?
It helps find missing or weak project guidance without replacing a developed setup unnecessarily.

Command

Part of the ce plugin — 17 skills, 1 command, 4 agents shipped together

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/rileyhilliard/claude-essentials/setup
Clone the repo
git clone --depth 1 https://github.com/rileyhilliard/claude-essentials

Or install ce, the plugin that ships this one along with the rest of its 17 skills, 1 command, 4 agents.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,978 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 $0.00009 $0.01978
Opus 5 $0.00005 $0.00989
Sonnet 5 $0.00002 $0.00396
Haiku 4.5 $0.00001 $0.00198

Measured 3d ago against content hash 72d3296286ac, 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 3d 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.

plugins/ce/commands/setup.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit an existing .claude/ configuration, or bootstrap one for a repository that has none.

Audit-first: Most repos this command runs in already have a .claude/ setup. When the existing configuration is already developed (CLAUDE.md with real content plus rules or settings), bail out early with a short summary of what exists and only the suggestions that are genuinely high-value — report what actually matters, don't pad the list — do NOT regenerate or restructure a working setup. Full generation only happens on repos with no .claude/ or with --force.

Before generating or auditing any files, review the project's existing .claude/ structure and follow Claude Code best practices for writing rules, CLAUDE.md, and skills.

Arguments:

  • $ARGUMENTS: Optional flags
    • --audit: Only analyze existing config, report improvements
    • --force: Overwrite existing files without confirmation

Mode Detection

  1. Check if .claude/ directory exists
  2. If exists AND no --force: Run Audit Mode
    • If the config is developed (non-trivial CLAUDE.md and rules/ or settings.json), summarize and stop after Step 3's report — apply fixes only if the user asks
  3. If not exists OR --force: Run Fresh Init Mode

Note: this command was previously /ce:init. It was renamed to /ce:setup to avoid colliding with Claude Code's built-in /init.


Configuration Best Practices

All generated files (rules, CLAUDE.md, skills) should follow these principles:

  • Rules reference ce:* skills rather than duplicating skill content
  • Main files stay concise; split large content into references/ subdirectories
  • References are always one level deep (no nested references)

Fresh Init Mode

Step 1: Detect Stack

Check for manifest files in the repository root:

File Stack Test Framework
pyproject.toml or requirements.txt Python pytest
package.json Node.js/TypeScript vitest, jest
Cargo.toml Rust cargo test
go.mod Go go test
pom.xml or build.gradle Java/Kotlin JUnit
Gemfile Ruby RSpec

Read the full file on GitHub · 239 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. 3d ago First seen · 239 lines · 9 tokens per session scan A 72d3296286ac

Subscribe to this mod's changes

setup is a command published in the GitHub repository rileyhilliard/claude-essentials (128 stars, last pushed 15d ago), licensed MIT. It adds 9 tokens to every session and 1,978 once invoked, about $0.0000 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 2026-08-30.