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.
/plugin marketplace add Marcel-Bich/marcel-bich-claude-marketplace/plugin install credoWrote 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.
[](https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/setup)<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.
<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>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.
| Model | Per session | Once 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 | $0.00627 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- The limit plugin is installed: `grep -q '"limit@marcel-bich-claude-marketplace"' "$HOME/.claude/plugins/installed_plugins.json"` succeeds (same installed-plugins file the setup check reads for dogma/gsd). 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:
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.
- 10d ago First seen · 585 lines · 12 tokens per session scan B a3365baf246a
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.
Other commands, from other repositories
context-stats
Display context window usage and token statistics.
migrate
Generate and manage database migrations.
security-scan
Run security audit on codebase.
test-suite
Run comprehensive test suite with coverage analysis.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.