coderifts

A plugin configuration for CodeRifts API governance in Claude Code. It provides checks for API or tool-contract changes, records the resulting decisions, and verifies receipts through a hosted MCP server.

In plain words
What is it for?
Use it before merging or releasing changes to OpenAPI, GraphQL, gRPC, AsyncAPI, MCP manifests, or agent-tool schemas, and to review past governance decisions.
Why use it?
Changes to an API contract can break clients or tools that depend on it. The plugin adds a pre-release check and a way to inspect the decision and verification results before shipping.

Plugin for Claude Code

Install

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.

Claude Code
/plugin marketplace add coderifts/api-governance
agentmods
npx agentmods add plugins/coderifts/api-governance/marketplace
Clone the repo
git clone --depth 1 https://github.com/coderifts/api-governance

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

coderifts 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 today.

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.

.claude-plugin/marketplace.json · 34 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "coderifts",
  "description": "CodeRifts API governance plugins for Claude Code — preflight contract changes, verify receipts, and inspect past decisions via the hosted MCP server.",
  "owner": {
    "name": "CodeRifts",
    "email": "[email protected]"
  },
  "plugins": [
    {
      "name": "api-governance",
      "source": "./plugins/api-governance",
      "description": "CodeRifts API governance: hosted MCP (preflight_change_set, verify_receipt, get_decision_details) plus a skill that runs before merging or shipping API/tool-contract changes.",
      "version": "1.0.0",
      "author": {
        "name": "CodeRifts",
        "email": "[email protected]"
      },
      "homepage": "https://coderifts.com",
      "repository": "https://github.com/coderifts/api-governance",
      "license": "MIT",
      "keywords": [
        "api-governance",
        "breaking-change",
        "openapi",
        "mcp",
        "preflight",
        "contract-safety"
      ],
      "category": "development"
    }
  ]
}
Changes

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.

  1. today First seen · 34 lines scan A 2e16427a26b9

Subscribe to this mod's changes

coderifts is a plugin published in the GitHub repository coderifts/api-governance (0 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 2026-08-31.