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.
/plugin marketplace add commitshow/production-auditnpx agentmods add plugins/commitshow/production-audit/marketplacegit clone --depth 1 https://github.com/commitshow/production-auditGrade A, and why
commitshow-production-audit marketplace 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 2d 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": "commitshow-production-audit",
"owner": {
"name": "commitshow",
"url": "https://commit.show"
},
"plugins": [
{
"name": "production-audit",
"source": ".",
"description": "Audit a shipped repo for the production-readiness gaps that ~70% of AI-coded projects miss. Companion to in-session security skills.",
"version": "0.1.0",
"homepage": "https://github.com/commitshow/production-audit"
}
]
}
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.
- 2d ago First seen · 17 lines scan A 0de16d20bd4b
commitshow-production-audit marketplace is a plugin published in the GitHub repository commitshow/production-audit (5 stars, last pushed 4mo ago), 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 2026-08-31.
Other plugins, from other repositories
microsoft-agent-skills marketplace
Plugin marketplace listing 1 plugin: azure-agent-skills.
azure-agent-skills
A curated collection of production-ready agentic skills for Microsoft Azure development. Installs 193+ skills covering Azure compute, data, AI/ML, networking, security, and management services. Built from Microsoft Learn documentation and following the Agent Skills open standard.
abogado-del-diablo
ES: Vuelve a Claude en tu contra para criticar a fondo una idea, un plan o un proyecto entero — sin validar ni suavizar — por ocho ángulos, con investigación de fracasos reales y un veredicto priorizado de qué arreglar. EN: Turn Claude against you to harshly critique an idea, plan, or whole project across eight angles.
major-ai-skills
Major AI Skills - product-depth agentic SKILL.md library for Claude Code.
mas-common-sense-pack
MAS Common Sense Pack - Major AI Skills specialized plugin.
mas-design-knowledge
MAS Design & Knowledge - Major AI Skills specialized plugin.