setup

setup is a command for Claude Code from Marcel-Bich/marcel-bich-claude-marketplace. It costs 12 tokens per session (6,268 once invoked), scanned B, original, MIT.

A setup command for configuring Claude Code with recommended tools, instructions, and project files.

In plain words
What is it for?
Use it to initialize the credo framework and check project instructions, documentation, codebase mapping, and roadmap files.
Why use it?
It checks what is already configured and asks only about missing parts of the project setup.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the credo plugin — 26 skills, 15 commands, 6 hooks shipped together

Good fit Use it to initialize the credo framework and check project instructions, documentation, codebase mapping, and roadmap files.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace
Claude Code
/plugin install credo

Made for: Claude Code.

Or install credo, the plugin that ships this one along with the rest of its 26 skills, 15 commands, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for setup

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/setup/github.svg)](https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/setup)
Your own site
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/setup"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/setup/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for setup

Your own site · 80×15
<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/setup"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,268 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00012 $0.06268
Opus 5 $0.00006 $0.03134
Sonnet 5 $0.00002 $0.01254
Haiku 4.5 $0.00001 $0.00627

Measured 10d ago against content hash a3365baf246a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

setup scanned grade B with 1 finding 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 10d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- The limit plugin is installed: `grep -q '"limit@marcel-bich-claude-marketplace"' "$HOME/.claude/plugins/installed_plugins.json"` succeeds (same installed-plugins file the setup check reads for dogma/gsd).
plugins/credo/commands/setup.md · 585 lines

How it starts

The opening of the file, as written. The whole thing — 585 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Credo Setup

Set up Claude Code with the preacher's recommended tools, instructions, and project structure. credo is the core; everything else is recommended or optional and slots in around it.

Goal: Only ask about things that are NOT yet done. Skip everything already configured.

Step 1: Run Setup Check

Run the setup check script to gather all information at once:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/check-setup.sh"

This outputs structured results for all checks. Parse the output to determine:

  • plugins.dogma - Is the recommended dogma plugin installed?
  • plugins.gsd - Is the optional get-shit-done plugin installed?
  • directories.claude - Are Claude instructions present?
  • files.project_md - Does PROJECT.md exist? (only relevant if GSD is used)
  • directories.codebase_map - Is codebase mapped? (only relevant if GSD is used)
  • files.roadmap - Does ROADMAP.md exist? (only relevant if GSD is used)
  • project.state - Overall state (needs_setup, needs_mapping, needs_project, needs_roadmap, ready)

If project.state = ready: Skip directly to "Setup Complete" section. Do NOT ask any questions.

Step 2: Initialize the credo Framework (Core)

This is the real first step - credo's own state tree. It is self-contained and needs no other plugin.

Run the init script (idempotent - safe to run again):

bash "${CLAUDE_PLUGIN_ROOT}/scripts/credo-init.sh"

This creates the .credo/ structure (items, process, screenshots, checklists, config, id-counter) and adds the git-exclude lines. .credo/** stays local by default. For teams that want items and process versioned in the repo, run it with CREDO_VERSION_TRACKED=1 instead (per-project config and screenshots/ stay local either way).

Handling the target guard (fail-safe)

credo-init is fail-safe: it never creates .credo/ in the wrong place. If the current directory is a launch hub, or is ambiguous (no .credo/ yet and no explicit target given), the script exits non-zero (code 4) with a message like:

Read the full file on GitHub · 585 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. 10d ago First seen · 585 lines · 12 tokens per session scan B a3365baf246a

Subscribe to this mod's changes

setup is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 6,268 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.