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/delimit-ai/delimit-mcp-serverWrote 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/delimit-ai/delimit-mcp-server/claude-plugin-governance)<a href="https://agentmods.dev/plugins/delimit-ai/delimit-mcp-server/claude-plugin-governance"><img src="https://agentmods.dev/badge/plugins/delimit-ai/delimit-mcp-server/claude-plugin-governance/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/delimit-ai/delimit-mcp-server/claude-plugin-governance"><img src="https://agentmods.dev/badge/plugins/delimit-ai/delimit-mcp-server/claude-plugin-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
delimit-governance 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 9d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- delimit-panel — 91% identical, 14 lines differ
What it actually says
{
"name": "delimit-governance",
"displayName": "Delimit Governance",
"version": "1.0.0",
"description": "Catch breaking API changes before you merge, locally.",
"author": {
"name": "Delimit",
"url": "https://delimit.ai",
"email": "[email protected]"
},
"homepage": "https://github.com/delimit-ai/delimit-mcp-server/tree/main/claude-plugin-governance",
"repository": "https://github.com/delimit-ai/delimit-mcp-server",
"license": "MIT",
"keywords": ["openapi", "api-governance", "breaking-changes", "semver", "mcp"],
"documentationUrl": "https://github.com/delimit-ai/delimit-mcp-server/blob/main/claude-plugin-governance/README.md",
"privacyPolicyUrl": "https://github.com/delimit-ai/delimit-mcp-server/blob/main/claude-plugin-governance/PRIVACY.md",
"termsOfServiceUrl": "https://delimit.ai/terms",
"supportUrl": "https://github.com/delimit-ai/delimit-mcp-server/issues"
}
What it installs
The manifest is a name and a version. 3 skills, 1 MCP server travel with it, and installing the plugin installs all of them — 59 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- 9d ago First seen · 20 lines scan A e1d32d1bf2a4
delimit-governance is a plugin published in the GitHub repository delimit-ai/delimit-mcp-server (24 stars, last pushed yesterday), 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 2026-10-08.
Other plugins, from other repositories
coderifts-api-governance
Signed, offline-verifiable authorization for AI-agent contract changes. Cursor asks before a contract change proceeds; only a granted change can proceed. The verdict is deterministic — the same change set yields the same verdict, not a model's judgement — and branching is fail-closed: an unrecognised executionaction i.
ring-dev-team
24 specialized developer agents + 35 development skills. Backend (Go/TypeScript) and frontend (React/Next.js) dev cycles, DevOps, QA, SRE, and the parallel code-review pool.
backend-architecture
Small, opinionated architecture guide for production backend services across languages and frameworks.
coderifts
Signed, offline-verifiable authorization for AI-agent contract changes. Gemini CLI loads the hosted MCP; only a granted change can proceed.
orleans-dev
Microsoft Orleans patterns, best practices, and code review for virtual actor model applications — covers grain design, concurrency, cross-grain communication, streams, and serialization.
code-quality
Code quality and review for production systems. Bundles a strict distributed-systems code reviewer (PRs, diffs, plans) with a disciplined BLOCKER/HIGH/MEDIUM/LOW/QUESTION severity model, TypeScript quality patterns (typed clients, Zod validation, structured errors, no-any, structured logging, OpenTelemetry, PII…