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.
git clone --depth 1 https://github.com/Marcel-Bich/marcel-bich-claude-marketplaceWrote 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/psalm)<a href="https://agentmods.dev/commands/marcel-bich/marcel-bich-claude-marketplace/psalm"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/psalm/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/psalm"><img src="https://agentmods.dev/badge/commands/marcel-bich/marcel-bich-claude-marketplace/psalm.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 | $0.00010 | $0.03995 |
| Opus 5 | $0.00005 | $0.01997 |
| Sonnet 5 | $0.00002 | $0.00799 |
| Haiku 4.5 | $0.00001 | $0.00400 |
Grade A, and why
psalm 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Credo - The Preacher's Guide
credo is the mentor: a self-contained process framework. This guide starts with credo's own teachings and only then points to the wider marketplace. The other plugins are recommended or optional and slot in around credo.
Step 0: Run Setup (Recommended)
Before the faithful walk the path, ensure the project is set up.
Invoke /credo:setup via Skill tool.
This handles:
- Initializing the credo framework (
.credo/tree) - the core, self-contained. - Optional companions: dogma (recommended), get-shit-done (optional, spec-driven alternative to credo items).
- Claude instructions sync (
/dogma:sync, if dogma is installed). - Choosing a task system (credo items by default).
- Autonomy preferences and, when the limit plugin is present, wiring its auto-compact trigger to
credo:compact-plus.
After setup completes, continue to Entry Point.
Entry Point
After setup, help the user discover topics. credo's own capabilities come first.
If user runs /credo:psalm without arguments:
Use AskUserQuestion to show available topics:
What would you like to explore?
- The credo workflow: how a piece of work flows end to end
- Session Modes: active / passive / autonomous working modes
- Item Lifecycle: work items with a hard Definition of Done
- Budget and Autonomy: unattended work within 5h and weekly caps
- Verify and Safety: visual verify, filesystem protection, subagent priming
- The Wider Marketplace: hydra, dogma, import, limit and more (optional)
- Something else: Ask your own question
If arguments provided: The user already has a question. Answer it directly using this guide, or navigate to the most relevant section.
Credo's Own Teachings
These are the heart of the framework. Everything below lives inside credo - no foreign plugin required.
Topic: The credo workflow (end to end)
How one piece of work flows through credo, tying the topics below into one path:
- Set up once:
/credo:setup- framework, optional companions, autonomy and compact preferences. - Pick a session mode for how present you are: active / passive / autonomous (see Session Modes).
- Capture the work as an item: requirement verbatim, plus observable success criteria (the Definition of Done). Clarify first; nothing is built before an explicit GO (see Item Lifecycle).
- On GO, build - delegation-first via subagents (load
/credo:session-initfor the main-agent workflow), wiring new code so a caller actually reaches it. - Pass the hard Definition of Done gate: an independent audit subagent (not the builder), visual verify for any runtime surface, docs updated in the same change. Findings are dispositioned, not dropped.
- Only the user files the item as verified.
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.
- 11d ago First seen · 352 lines · 10 tokens per session scan A 8eb5834b39a3
psalm is a command published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 3,995 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 2026-08-30.
Other commands, from other repositories
migrate
Generate and manage database migrations.
context-stats
Display context window usage and token statistics.
security-scan
Run security audit on codebase.
test-suite
Run comprehensive test suite with coverage analysis.
assemble-team
Assemble a pre-built agent team for parallel work - review, feature, debug, cross-platform, full-stack, or research.
run
Execute prompt(s) from ./prompts/ with automatic archiving - for structured prompt-based work.