api-reviewer

api-reviewer is a skill for Claude Code, Codex from lfyxhappy/lfcode. It costs 53 tokens per session (330 once invoked), scanned A, original, MIT.

An API review guide for checking an existing interface and its callers. An API is a published way for software to communicate, including its inputs, outputs, errors, permissions, and version rules.

In plain words
What is it for?
It helps review or carefully change HTTP, RPC, event, command-line, and SDK interfaces, including routes, schemas, clients, status codes, pagination, retries, and versioning.
Why use it?
It finds broken assumptions, unsafe authorization, invalid responses, and compatibility problems before changing a shared interface. It verifies behavior with focused tests and real request or generated-output checks when possible.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps review or carefully change HTTP, RPC, event, command-line, and SDK interfaces, including routes, schemas, clients, status codes, pagination, retries, and versioning.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lfyxhappy/lfcode/api-reviewer
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.

Any agent
npx skills add lfyxhappy/lfcode --skill api-reviewer
Clone the repo
git clone --depth 1 https://github.com/lfyxhappy/lfcode

Made for: Claude Code, Codex.

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 api-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/lfyxhappy/lfcode/api-reviewer.svg)](https://agentmods.dev/skills/lfyxhappy/lfcode/api-reviewer)
Your own site
<a href="https://agentmods.dev/skills/lfyxhappy/lfcode/api-reviewer"><img src="https://agentmods.dev/badge/skills/lfyxhappy/lfcode/api-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 330 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00053 $0.00330
Opus 5 $0.00026 $0.00165
Sonnet 5 $0.00011 $0.00066
Haiku 4.5 $0.00005 $0.00033

Measured yesterday against content hash 75a652180bf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

packages/lfcode/src/skill/lfcode/.bundle/api-reviewer/SKILL.md · 28 lines

What it actually says

API Reviewer

Review an interface as a contract shared by callers, operators, and persisted data.

Workflow

  1. Locate the route or exported operation, schema definitions, authentication and permission checks, serializers, errors, documentation, and tests.
  2. Trace representative callers and generated or handwritten clients. Record current method, path or operation name, input, output, status or error behavior, ordering, and limits.
  3. Check validation, defaults, pagination, idempotency, retries, versioning, backward compatibility, sensitive fields, and observability.
  4. Separate a review finding from an implementation recommendation. For a requested change, update the narrow contract and its consumers together.
  5. Add focused contract tests for success, invalid input, authorization, not-found, conflict, and failure paths that apply.
  6. Verify the real request and response or generated artifact when possible, then run package typecheck and build checks for shared interfaces.

Boundaries

  • Do not silently change public names, wire formats, status codes, or authorization semantics.
  • Do not call live endpoints with real secrets or destructive payloads unless the target and authorization are explicit.
  • Never include credentials or unredacted user data in examples, logs, or documentation.

Completion check

Report compatibility impact, affected consumers, tests, and any contract behavior that could not be exercised.

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 · 53 tokens per session scan A 75a652180bf2

Subscribe to this mod's changes

api-reviewer is a skill published in the GitHub repository lfyxhappy/lfcode (2 stars, last pushed 4d ago), licensed MIT. It adds 53 tokens to every session and 330 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 2026-09-05.