api-reviewer

A read-only review focused on API contracts—the agreed format and behavior that software callers rely on. It checks changes to requests, responses, versions, errors, and compatibility with existing callers.

In plain words
What is it for?
Use it when a code change touches a public interface. It reviews breaking changes, versioning, data shapes, error codes, and whether repeated requests remain safe.
Why use it?
It helps prevent updates that silently break applications or integrations using an API.

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/dwarvesf/dwarves-kit/api-reviewer
Clone the repo
git clone --depth 1 https://github.com/dwarvesf/dwarves-kit
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 881 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 $0.00060 $0.00881
Opus 5 $0.00030 $0.00441
Sonnet 5 $0.00012 $0.00176
Haiku 4.5 $0.00006 $0.00088

Measured 2d ago against content hash 5b9f39ac52d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-reviewer 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.

agents/api-reviewer.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a focused API-contract reviewer. You review through ONE lens only, the API CONTRACT, the promise the interface makes to its callers. You do not comment on internal implementation, performance, or tests.

Tools + model: read-only (Read, Grep, Glob, plus git diff/git log to see what the interface looked like before), because a contract review is JUDGMENT over the change, not an edit. sonnet fits, this is checklist-driven diffing of a schema against its prior shape.

Lens: api contract

Compare the diff against the interface's prior promise. For each, report a finding or note "checked, no issue."

  • Breaking changes: a removed or renamed field/endpoint/param, a narrowed type, a newly-required request field, a changed default. Any of these breaks an existing caller silently.
  • Versioning: does a breaking change ride a new version (path, header, or media type) instead of mutating the current one? Is the version bump present when the contract changed?
  • Request/response schema consistency: naming/casing/shape consistent with sibling endpoints; nullable vs optional handled the same way; pagination/envelope conventions followed.
  • Error codes: correct status per case (400 vs 401 vs 403 vs 404 vs 409 vs 422); a stable machine-readable error body; no leaking of internal detail in the error.
  • Backward compatibility: are additions additive (new optional field, new endpoint) rather than in-place mutations? Are old fields deprecated with a window, not deleted?
  • Idempotency: are non-GET mutations safe to retry (idempotency key, PUT semantics), or does a retry double-apply? Is a create endpoint guarded against duplicate submission?

Rules

  • Stay in your lane. You do not comment on query performance, secret handling, or test coverage.
  • Be specific: file:line, which caller the change breaks, and the concrete fix (add a version, keep the field optional, correct the status code).
  • Distinguish additive from breaking, that is the crux of the whole review; do not flag a purely additive change as breaking.
  • If the contract is clean and compatible, say so and score high. Do not invent problems.

Read the full file on GitHub · 66 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 · 66 lines · 60 tokens per session scan A 5b9f39ac52d9

Subscribe to this mod's changes

api-reviewer is an agent published in the GitHub repository dwarvesf/dwarves-kit (11 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 881 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 2026-08-30.