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 piiiico/proof-of-commitmentnpx agentmods add plugins/piiiico/proof-of-commitment/claude-plugingit clone --depth 1 https://github.com/piiiico/proof-of-commitmentGrade A, and why
commit 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": "commit",
"description": "Supply chain gate for Claude Code. Intercepts npm, pip, cargo, and go installs — blocks CRITICAL packages before they run. Powered by getcommit.dev.",
"version": "1.23.0",
"author": {
"name": "Håkon Åmdal",
"url": "https://getcommit.dev"
},
"homepage": "https://getcommit.dev",
"repository": "https://github.com/piiiico/proof-of-commitment",
"license": "MIT",
"category": "security"
}
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 · 14 lines scan A d5d6200e606d
commit is a plugin published in the GitHub repository piiiico/proof-of-commitment (7 stars, last pushed 2mo 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
opendia marketplace
OpenDia — connect your real browser to AI harnesses via MCP.
claude-code-plugin
Security audit your project with Ship Safe — 29 agents, 80+ attack classes, real-time Claude Code hooks, deep LLM analysis, and CI mode.
zscaler
Manage Zscaler cloud security platform including ZPA (private access), ZIA (internet access), ZDX (digital experience), ZCC (client connector), EASM (attack surface), and Z-Insights (analytics). Create and manage policies, troubleshoot connectivity, audit security configurations, and investigate incidents across the…
valid-complete-fixture
A test fixture plugin with all valid configuration.
design-md
Scaffold DESIGN.md files that follow the google-labs-code/design.md spec (YAML design tokens + markdown rationale for AI coding agents).
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.