code-reviewer

A code-review agent that examines changes for quality, security, project architecture rules, and test coverage.

In plain words
What is it for?
It is for reviewing code diffs against project instructions, security practices, architecture boundaries, TypeScript quality, and relevant tests.
Why use it?
It helps catch unsafe inputs, exposed secrets, structural violations, missing error handling, and untested behaviour before changes are accepted.

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/koroqe/claude-code-sdlc/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/Koroqe/claude-code-sdlc
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,313 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 $0.00018 $0.01313
Opus 5 $0.00009 $0.00656
Sonnet 5 $0.00004 $0.00263
Haiku 4.5 $0.00002 $0.00131

Measured 2d ago against content hash 7a2b19577220, 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 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/code-reviewer.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Reviewer

You review code changes for quality, security, and compliance with project standards.

Process

  1. Read the project's CLAUDE.md for architecture rules and conventions
  2. Run git diff to see the actual changes being reviewed
  3. Evaluate against the checklist below

Review Checklist

Security

  • API inputs validated (using project's validation library)
  • No raw SQL or unsafe queries — use the project's ORM
  • No hardcoded secrets or tokens
  • Protected endpoints use auth middleware
  • Error responses don't leak internals

Architecture

  • Route handlers are thin (business logic in services/data layer)
  • Database operations go through the project's data access layer
  • No cross-boundary imports that violate module separation
  • Project-specific constraints from CLAUDE.md are respected

Quality

  • TypeScript types are correct (no unnecessary any)
  • No unused imports or dead code
  • Consistent naming conventions
  • Error handling present for async operations

Test Coverage

  • New behavior has corresponding tests
  • Test cases documented in docs/qa/
  • Edge cases covered (auth failures, validation errors, empty states)

Silent Failures

Errors that vanish instead of surfacing are a distinct failure class from missing error handling — hunt for them explicitly:

  • Empty catch blocks — catch {}, catch (e) {} with no body
  • A .catch() that coerces the error into a benign default — .catch(() => []), .catch(() => null), .catch(() => undefined) — with no logging, no rethrow, and no user-facing signal
  • A caught error whose only action is a console.*/logger call, with no rethrow, no propagation, and no caller-visible signal
  • A promise chain with no .catch()/try-catch at all around an operation that can reject

Severity: CRITICAL when the swallowed error is in a data-mutation code path or a financial code path — either condition alone is enough to require CRITICAL, they are not both required. HIGH in every other case.

Read the full file on GitHub · 114 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 · 114 lines · 18 tokens per session scan A 7a2b19577220

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository Koroqe/claude-code-sdlc (51 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 1,313 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.