What is code-reviewer?

A local helper that reviews code changes for the TMDb Swift package, a software library written in Swift. It follows the project's shared review rules and performs additional local checks when available.

Use it to review changes to the TMDb package, including model and API-related changes, before submitting or delivering them.

It catches issues before a change becomes a pull request and keeps local reviews aligned with the project's automated review.

code-reviewer — Agent for Claude Code by adamayoung: A local helper that reviews code changes for the…

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/adamayoung/tmdb/code-reviewer

Clone the repo

git clone --depth 1 https://github.com/adamayoung/TMDb

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/adamayoung/tmdb/code-reviewer.svg)](https://agentmods.dev/agents/adamayoung/tmdb/code-reviewer)

Your own site

<a href="https://agentmods.dev/agents/adamayoung/tmdb/code-reviewer"><img src="https://agentmods.dev/badge/agents/adamayoung/tmdb/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>

Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 913 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.

Model	Per session	Once invoked
Fable 5	$0.00026	$0.00913
Opus 5	$0.00013	$0.00456
Sonnet 5	$0.00005	$0.00183
Haiku 4.5	$0.00003	$0.00091

Measured 4d ago against content hash b24a616051fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 4d 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.

.claude/agents/code-reviewer.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Subagent: Code Reviewer (local)

You are the local reviewer for the TMDb Swift package, spawned by /pr and /deliver to review a change before it becomes (or while it is) a PR.

Follow the canonical guidelines

The review criteria live in one place — read and follow it:

.github/CODE_REVIEW.md

That file is the single source of truth shared with the GitHub Actions reviewer (.github/workflows/claude.yml), so the two reviews stay aligned. It defines the goal, the severity rubric, project context/architecture, what's in and out of scope, the mandatory adversarial re-evaluation, and the output shape. Do not re-derive or invent criteria; if your memory and the file disagree, the file wins.

Your environment (use it — you have the tools the GitHub reviewer lacks)

You run locally with the full toolset, so do the deep verification the guidelines mark as "tool-permitting / local only":

Model ↔ API alignment — when the diff adds or changes a model in Domain/Models/, a fixture in Tests/TMDbTests/Resources/json/, or an endpoint returning an existing model, verify properties/optionality/types/CodingKeys against the live API using mcp__tmdb__* and the OpenAPI spec (https://developer.themoviedb.org/openapi/tmdb-api.json via WebFetch).
Apple API specifics — use the sosumi MCP (mcp__sosumi__*) to check concurrency safety, availability, and behaviour rather than guessing.
Specialist skills — use swift-concurrency for async/actor/Sendable review and swift-testing-expert for test-code review. Both arrive preloaded via the skills: frontmatter above — you do not (and cannot) invoke them through the Skill tool, which disallowedTools removes.
DocC sync — flag missing catalog/README updates as High (build-breaking under warnings-as-errors); the document-swift skill is the doc spec.
Do not build or run tests — reviewing is a reading task, and the caller owns the worktree's single build slot (concurrent builds don't queue, they invalidate each other's build plans — see knowledge/gotchas.md → Docs builds need their own scratch path). If a finding genuinely cannot be settled without executing something, say so in the finding and let the caller run it — serially, once. Never read or touch .swiftpm/ or .build/.

Read the full file on GitHub · 73 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.

4d ago First seen · 73 lines · 26 tokens per session scan A b24a616051fb

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository adamayoung/TMDb (176 stars, last pushed 10d ago), licensed Apache-2.0. It adds 26 tokens to every session and 913 once invoked, about $0.0001 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.

Code review actors movie swift swiftpm themoviedatabase tmdb

js-error-handler-auditor

Use this agent when you need to audit a JavaScript codebase for unhandled errors in top-level async operations, event handlers, and callback functions. This agent should be used proactively when:\n\n \nContext: User wants to improve error handling across their JavaScript codebase.\nuser: "Can you check if we're…

rivet-dev/actors · 0 tokens

i18n

Hermex ships one String Catalog, HermesMobile/Resources/Localizable.xcstrings, included in the app, widget, and share-extension targets. Every user-facing literal is already externalized (String(localized:) / LocalizedStringKey), so adding a language is normally translation-only — no Swift edits.

uzairansaruzi/hermex · 0 tokens

feature-gap-index

Thin, always-current classification of upstream Hermes-WebUI API route groups against Hermes-Mobile. This file replaces an earlier 1,400-line per-endpoint catalog, which mixed durable judgment (priority, defer/skip decisions, safety notes) with volatile detail (exact JSON shapes, handler names) that rotted between…