coderifts-api-governance

Instructions for governing changes to API contracts before they are merged, deployed, published, or exposed to agents. A contract defines the fields, operations, and responses that other software may rely on.

In plain words
What is it for?
Reviewing changes to OpenAPI, GraphQL, gRPC, AsyncAPI, MCP manifests, and agent-tool schemas, then obtaining and using the required governance result.
Why use it?
They help determine whether a contract change is allowed, needs a warning or approval, or must be blocked before it reaches users or other systems.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/coderifts/api-governance/coderifts-api-governance
Any agent
npx skills add coderifts/api-governance --skill coderifts-api-governance
Clone the repo
git clone --depth 1 https://github.com/coderifts/api-governance

Made for: Claude Code, Codex.

Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,609 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00144 $0.01609
Opus 5 $0.00072 $0.00805
Sonnet 5 $0.00029 $0.00322
Haiku 4.5 $0.00014 $0.00161

Measured 2d ago against content hash 2122a9ea3ea6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coderifts-api-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 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.

plugins/api-governance-cursor/skills/coderifts-api-governance/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeRifts API governance

Before quoting field names, enums, thresholds, or response shapes, retrieve the current contract from the Decision Spec and the decision-result consumer schema. The schemas are the source of truth; this file tells you when and how to call.

When to load this skill

Load it when all of the following hold:

  1. You are about to merge, push, deploy, publish, or register/expose agent tools.
  2. The change includes at least one contract artifact: openapi, graphql, grpc, asyncapi, mcp_manifest, or agent_tools.
  3. You can supply both before and after for every changed artifact in the set.

Do not load it for documentation-only changes, or when you merely want to re-check a receipt you already hold (that is one specific call, below, not a governance run).

Two modes — the distinction that matters

preflight_mode is required. Passing the wrong one is the most common integration error.

Mode What you get What it is NOT
analyze analysis_outcome, may_execute: false, risk fields Not permission. No decision, no execution_action, no safe_for_agent, no receipt.
authorize decision, execution_action, safe_for_agent, and a signed chain_receipt when issued Requires context.operation (merge | deploy | publish | tool_call).

An analyze response never authorizes anything. If you are going to act, call authorize.

How to branch

Branch on execution_action — a closed set:

  • CONTINUE — proceed.
  • CONTINUE_WITH_MONITORING — proceed only if you actually have a monitoring sink wired; otherwise treat as a halt.
  • REQUEST_APPROVAL — stop and get a human.
  • STOP — stop this attempt; remediate and request a new decision.

Rules that are not optional:

  • An unrecognised execution_action is not permission — fail closed.
  • Do not branch on safe_for_agent. It exists for legacy dashboards.
  • Unknown additive fields are not permission either; tolerate them and ignore them for control flow.
  • A known continue-valued execution_action is a necessary condition, never a sufficient one. You may add your own conjunctive checks and halt where the contract would permit execution.

Read the full file on GitHub · 119 lines

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. 2d ago First seen · 119 lines · 144 tokens per session scan A 2122a9ea3ea6

Subscribe to this mod's changes

coderifts-api-governance is a skill published in the GitHub repository coderifts/api-governance (0 stars, last pushed 2d ago), licensed MIT. It adds 144 tokens to every session and 1,609 once invoked, about $0.0007 per session on Opus 5. 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.