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/plugins/marcel-bich/marcel-bich-claude-marketplace/credo)<a href="https://agentmods.dev/plugins/marcel-bich/marcel-bich-claude-marketplace/credo"><img src="https://agentmods.dev/badge/plugins/marcel-bich/marcel-bich-claude-marketplace/credo/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/plugins/marcel-bich/marcel-bich-claude-marketplace/credo"><img src="https://agentmods.dev/badge/plugins/marcel-bich/marcel-bich-claude-marketplace/credo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
credo 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 6d 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.
What it actually says
{
"name": "credo",
"version": "0.46.0",
"description": "The mentor framework for Claude Code: a self-contained process layer with per-session modes, a work-item lifecycle with a hard Definition of Done, budget-aware autonomy, visual verification, and safety rules that travel into every subagent",
"keywords": [
"workflow",
"process",
"framework",
"session-modes",
"work-items",
"definition-of-done",
"autonomy",
"budget",
"verification",
"safety",
"subagents",
"best-practices"
],
"license": "MIT"
}
What it installs
The manifest is a name and a version. 26 skills, 15 commands, 6 hooks travel with it, and installing the plugin installs all of them — 3,899 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill session-autonomous A 342 tokens
- Skill items A 143 tokens
- Skill budget A 142 tokens
- Skill session-active A 126 tokens
- Skill audit A 129 tokens
- Skill pr-vetting A 83 tokens
- Skill verify A 129 tokens
- Skill skill-capture A 170 tokens
- Skill issue-triage A 97 tokens
- Skill wsl-env A 146 tokens
- Skill requirements-verbatim A 101 tokens
- Skill rules A 179 tokens
- Skill diag A 118 tokens
- Skill disable A 142 tokens
- Skill role-plan A 199 tokens
- Skill role-task A 196 tokens
- Skill enable A 121 tokens
- Skill role-clear A 123 tokens
- Skill migrate A 123 tokens
- Skill orchestration A 102 tokens
- Skill sandbox A 189 tokens
- Skill session-passive A 138 tokens
- Skill cross-cutting-checklist-generator A 94 tokens
- Skill explain A 0 tokens
- Skill compact-plus B 164 tokens
- Skill safety C 113 tokens
- Command psalm A 10 tokens
- Command session-init A 10 tokens
- Command project A 21 tokens
- Command sandbox-promote A 24 tokens
- Command migrate A 15 tokens
- Command session-autonomous A 24 tokens
- Command session-active A 20 tokens
- Command session-passive A 22 tokens
- Command setup B 12 tokens
- Command explain A 16 tokens
- Command role-plan A 30 tokens
- Command disable A 23 tokens
- Command role-task A 26 tokens
- Command enable A 17 tokens
- Command role-clear A 20 tokens
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
- Hook Stop A not measured
- Hook SubagentStart A not measured
- Hook UserPromptSubmit A not measured
- Hook PostToolUse A not measured
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.
- 6d ago Changed bfc0ad0111c0
- 10d ago First seen · 21 lines scan A 5a1ce4cdb4d1
credo is a plugin published in the GitHub repository Marcel-Bich/marcel-bich-claude-marketplace (13 stars, last pushed today), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
hades
Unity-aware AI infrastructure for Claude Code: a queryable knowledge graph of your Unity project, plus observability, project memory, and 22 skills. Connects to the standalone Hades app for macOS and Windows (Windows is beta), which serves 32 MCP tools.
create-pr
Streamlines pull request creation by handling the entire workflow: creating a new branch, committing changes, formatting modified files with Biome, and submitting the PR.
pr-review
Reviews pull request changes to provide feedback, check for issues, and suggest improvements before merging into the main codebase.
canvas-design
Create beautiful visual art in PNG and PDF documents using design philosophy. Use for posters, art pieces, designs, or other static visual works with museum-quality craftsmanship.
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use proactively when encountering any issues.
security-guidance
Security reminder hook that warns about potential security issues when editing files, including command injection, XSS, and unsafe code patterns.