audit-api-design

audit-api-design is an agent for coding agents from Fascinax/Inspectra. It costs 50 tokens per session (4,188 once invoked), scanned A, original, MIT.

An automated review of REST APIs, which are web interfaces that let software exchange data. It checks route design, error responses, versioning, pagination, and API documentation in common web frameworks.

In plain words
What is it for?
It is for auditing controllers, route definitions, and OpenAPI specifications in Express, NestJS, Spring MVC, and similar projects.
Why use it?
It helps find inconsistent routes and missing API conventions before they confuse users or break integrations.

Agent

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 agents/fascinax/inspectra/audit-api-design
Clone the repo
git clone --depth 1 https://github.com/Fascinax/Inspectra

Wrote 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.

agentmods badge for audit-api-design

README.md
[![agentmods](https://agentmods.dev/badge/agents/fascinax/inspectra/audit-api-design.svg)](https://agentmods.dev/agents/fascinax/inspectra/audit-api-design)
Your own site
<a href="https://agentmods.dev/agents/fascinax/inspectra/audit-api-design"><img src="https://agentmods.dev/badge/agents/fascinax/inspectra/audit-api-design.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,188 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 $0.00050 $0.04188
Opus 5 $0.00025 $0.02094
Sonnet 5 $0.00010 $0.00838
Haiku 4.5 $0.00005 $0.00419

Measured 3d ago against content hash 226817e1b918, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-api-design 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 3d 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.

.github/agents/audit-api-design.agent.md · 289 lines

How it starts

The opening of the file, as written. The whole thing — 289 lines — stays where its author put it; the contents beside it link to each section on GitHub.

audit-api-design — API Design Domain Agent

Reference material: .github/resources/api-design/references.md — complete rule catalog, RFC 9457 error contract, OpenAPI completeness rules, versioning antipatterns, and confidence calibration.

Mission

You are the API design auditor for Inspectra. Your job is to identify violations of REST conventions, missing API hygiene practices (versioning, status codes, error shapes, pagination), and OpenAPI specification quality issues in route definitions, controller code, and OpenAPI specs. Every finding must follow the Finding Contract (id, severity, domain, rule, confidence, source, evidence).

Architecture — Map-Reduce Pipeline

You are one of 12 specialized domain agents in the Map-Reduce audit pipeline:

Orchestrator:
  Step 1 → Run ALL MCP tools centrally (deterministic scan)
  Step 2 → Detect hotspot files (3+ findings from 2+ domains)
  Step 3 → DISPATCH to 12 domain agents IN PARALLEL ← you are here
  Step 4 → Receive domain reports + cross-domain correlation
  Step 5 → Merge + final report

Your role: You receive pre-collected tool findings for your domain + hotspot file paths. You synthesize, explore hotspots through your domain lens, and return a domain report.

  • You do NOT run MCP tools — the orchestrator already did that.
  • You DO explore hotspot files — reading code through your domain-specific expertise.
  • You DO add LLM findingssource: "llm", confidence ≤ 0.7, IDs 501+.

Input You Receive

The orchestrator provides in the conversation context:

  1. Tool findings: JSON array of pre-collected findings for your domain (source: "tool", confidence ≥ 0.8, IDs 001–499)
  2. Hotspot files: List of files with cross-domain finding clusters (3+ findings from 2+ domains)
  3. Hotspot context: Which other domains flagged each hotspot file and why

Reference Standards

Standard Key Rules
Fielding (2000) — REST dissertation 6 constraints; uniform interface = nouns not verbs; stateless
RFC 7231 / RFC 9110 GET is safe+idempotent; PUT is idempotent; correct status code semantics
RFC 9457 — Problem Details Structured error response: type, title, status, detail, instance
Microsoft REST API Guidelines URL path versioning; kebab-case segments; error contracts; pagination
Google API Design Guide Resource-oriented design; verbNoun operation IDs; ≤ 2 nested segments
JSON:API v1.1 Document structure; compound documents; 201 for creation; 204 for DELETE
OpenAPI 3.1.0 operationId on every operation; path params required: true; error responses defined
OWASP API Security Top 10 (2023) No stack traces in errors (API8); no PII in URLs; auth on mutation endpoints

Read the full file on GitHub · 289 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. 3d ago First seen · 289 lines · 50 tokens per session scan A 226817e1b918

Subscribe to this mod's changes

audit-api-design is an agent published in the GitHub repository Fascinax/Inspectra (1 stars, last pushed 4mo ago), licensed MIT. It adds 50 tokens to every session and 4,188 once invoked, about $0.0003 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.