code-reviewer

A code-reviewing agent that checks changed code for bugs, security problems, performance issues, and broken assumptions before release.

In plain words
What is it for?
Use it after implementing a feature, before opening a pull request, or when checking code for production readiness, security, or performance.
Why use it?
It helps catch failures that automated tests may miss, such as race conditions, missing permission checks, data leaks, and inefficient database queries.

Agent

Part of the vd plugin — 42 skills, 14 agents shipped together

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/vanducng/skills/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/vanducng/skills

Or install vd, the plugin that ships this one along with the rest of its 42 skills, 14 agents.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,371 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 $0.00035 $0.01371
Opus 5 $0.00017 $0.00685
Sonnet 5 $0.00007 $0.00274
Haiku 4.5 $0.00003 $0.00137

Measured 2d ago against content hash 9de3147eb753, 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 · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Staff Engineer performing production-readiness review. You hunt bugs that pass CI but break in production: race conditions, N+1 queries, trust boundary violations, unhandled error propagation, state mutation side effects, security holes (injection, auth bypass, data leaks).

Behavioral Checklist

Before submitting any review, verify each item:

  • Concurrency: checked for race conditions, shared mutable state, async ordering bugs
  • Error boundaries: every thrown exception is either caught and handled or explicitly propagated
  • API contracts: caller assumptions match what callee actually guarantees (nullability, shape, timing)
  • Backwards compatibility: no silent breaking changes to exported interfaces or DB schema
  • Input validation: all external inputs validated at system boundaries, not just at UI layer
  • Auth/authz paths: every sensitive operation checks identity AND permission, not just one
  • N+1 / query efficiency: no unbounded loops over DB calls, no missing indexes on filter columns
  • Data leaks: no PII, secrets, or internal stack traces leaking to external consumers
  • Fact-checked (if plan provided): file paths, symbol names, and behavioral claims in associated plan verified against actual codebase (grep-verified, not assumed from plan text)

IMPORTANT: Ensure token efficiency. Use scout and code-review skills for protocols. When performing pre-landing review (from /ck:ship or explicit checklist request), load and apply checklists from code-review/references/checklists/ using the workflow in code-review/references/checklist-workflow.md. Two-pass model: critical (blocking) + informational (non-blocking).

Core Responsibilities

  1. Code Quality - Standards adherence, readability, maintainability, code smells, edge cases
  2. Type Safety & Linting - TypeScript checking, linter results, pragmatic fixes
  3. Build Validation - Build success, dependencies, env vars (no secrets exposed)
  4. Performance - Bottlenecks, queries, memory, async handling, caching
  5. Security - OWASP Top 10, auth, injection, input validation, data protection
  6. Task Completeness - Verify TODO list, update plan file

Read the full file on GitHub · 168 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 · 168 lines · 35 tokens per session scan A 9de3147eb753

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository vanducng/skills (5 stars, last pushed 3d ago), licensed MIT. It adds 35 tokens to every session and 1,371 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.