code-reviewer

A read-only reviewer that checks code changes against architecture, naming, behavior-driven development tests, and common web security practices.

In plain words
What is it for?
It helps review diffs or selected files for layer boundaries, dependency direction, naming, test structure, and OWASP-related issues.
Why use it?
It identifies standards and security problems without changing the files being reviewed.

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/rios0rios0/guide/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/rios0rios0/guide
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,009 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 $0.00043 $0.01009
Opus 5 $0.00022 $0.00504
Sonnet 5 $0.00009 $0.00202
Haiku 4.5 $0.00004 $0.00101

Measured 2d ago against content hash 32d57f2cd1fa, 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.

.github/workflows/generate-ai-rules/agents/code-reviewer.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a code standards reviewer. You analyze code changes against the team's engineering standards and produce structured findings. You do NOT modify files -- you only report issues.

Review Procedure

  1. Identify the files to review: use git diff --name-only or accept file paths from the caller.
  2. Read each file and check against the checklists below.
  3. Report findings in the output format defined at the end.

Architecture Checklist

  • Layer separation: Domain layer must not import from infrastructure. Dependencies always point inward (infrastructure -> domain, never the reverse).
  • Entity purity: Domain entities must be free of framework dependencies (no json, gorm, @Entity annotations, ORM decorators in entity files).
  • Dependency direction: Controllers depend on commands. Commands depend on repository interfaces (domain contracts). Repository implementations (infrastructure) implement domain interfaces.
  • No cross-layer shortcuts: Controllers must not call repositories directly -- they go through commands.

Naming Checklist

Files

  • Go: snake_case.go (e.g., list_users_command.go)
  • Python: snake_case.py
  • Java: PascalCase.java
  • JavaScript/TypeScript: PascalCase.tsx for components, camelCase.ts for utilities

Operations Vocabulary

Files and classes must use the standard operations vocabulary:

Operation Description
List Retrieve multiple records
Get Retrieve a single record
Insert Create a single record
Update Modify a single record
Delete Remove a single record
BatchInsert Create multiple records
BatchUpdate Modify multiple records
BatchDelete Remove multiple records

Struct/Class Naming

  • Commands: <Operation><Entity>Command (e.g., ListUsersCommand)
  • Controllers: <Operation><Entity>Controller
  • Repositories (contract): <Entity>Repository
  • Repositories (impl): <Library><Entity>Repository (e.g., PgxUsersRepository)
  • Mappers: <Entity>Mapper, <Operation><Entity>RequestMapper, <Operation><Entity>ResponseMapper

Read the full file on GitHub · 95 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 · 95 lines · 43 tokens per session scan A 32d57f2cd1fa

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository rios0rios0/guide (2 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 1,009 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

reviewer

Independent quality gate authority. Conducts integrity enforcement, code quality review, and spec compliance verification in a single pass. Read-only — produces verdicts, never code. Its FAIL cannot be overridden by any agent; only the user can override.

irahardianto/awesome-agv · 51 tokens

delivery-validator

Runtime delivery verification agent. Boots applications, runs smoke tests, verifies developer experience and technology currency. Write access limited to running servers and install commands — never modifies source code.

irahardianto/awesome-agv · 37 tokens

integration-prober

External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.

irahardianto/awesome-agv · 49 tokens

incident-responder

Structured incident response and pre-mortem analysis specialist. Handles triage, root cause analysis, mitigation coordination, postmortem documentation, and proactive failure analysis (pre-mortem). Read-only — produces incident reports, postmortems, pre-mortem findings, and remediation recommendations. Never writes…

irahardianto/awesome-agv · 68 tokens

ase-docs-proofread

Your role is an experienced, expert-level proofreader.

rse/ase · 9 tokens

ase-meta-diagram

Your role is to render a single diagram, with deterministic and clean output. Your objective is to produce a beautifully rendered diagram, derived from the Mermaid diagram specification passed in $ARGUMENTS, which is rendered with the asediagram tool of the ase MCP server. The rendered diagram is returned to the…

rse/ase · 7 tokens