api-contracts

A set of rules for designing stable HTTP API request and response formats. It defines the first required endpoints, including a chat-completions endpoint and a health check, with OpenAI-compatible behavior planned for the chat endpoint.

In plain words
What is it for?
Use it when designing or modifying endpoint schemas, versions, error responses, contract tests, examples, or the initial vLLM-backed model API.
Why use it?
It reduces accidental breaking changes for clients that depend on an API. It also requires predictable errors and contract tests when endpoint behavior changes.

Cursor rule for Cursor

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 rules/coeusyk/inference-x/api-contracts
Clone the repo
git clone --depth 1 https://github.com/coeusyk/inference-x

Made for: Cursor.

Per session 211 This file is loaded in full into every session.
When invoked 211 The same file — it is already loaded in full.
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 $0.00211 $0.00211
Opus 5 $0.00105 $0.00105
Sonnet 5 $0.00042 $0.00042
Haiku 4.5 $0.00021 $0.00021

Measured yesterday against content hash 5eab52dbbdd3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-contracts 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 yesterday.

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.

.cursor/rules/api-contracts.mdc · 28 lines

What it actually says

API contract rules

  • Treat request and response schemas as public contracts.
  • Avoid breaking field names or response structure after an endpoint is introduced.
  • If a contract must change, introduce a new version or clearly isolate the change behind a new endpoint.
  • Keep OpenAI-compatible behavior where planned for /v1/chat/completions.
  • Ensure error responses are consistent and predictable.
  • Add or update contract tests whenever endpoint behavior changes.

Phase 1 contract

Required endpoints:

  • POST /v1/chat/completions
  • GET /health

Phase 1 expectations:

  • one configured vLLM-backed model
  • typed request validation
  • typed response formatting
  • clear error handling for configuration, model load, and inference failures

Contract design rules

  • Prefer additive change over breaking change.
  • Keep optional fields optional; do not make them required later without versioning.
  • Return machine-readable status information where useful.
  • Document examples in README.md or docs/ARCHITECTURE.md when endpoints stabilize.
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. yesterday First seen · 28 lines · 211 tokens per session scan A 5eab52dbbdd3

Subscribe to this mod's changes

api-contracts is a cursor rule published in the GitHub repository coeusyk/inference-x (2 stars, last pushed 21d ago), licensed MIT. It adds 211 tokens to every session, about $0.0011 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.