code-reviewer

code-reviewer is an agent for coding agents from RashadAnsari/myagents. It costs 46 tokens per session (1,098 once invoked), scanned A, original, MIT.

A read-only code review agent that examines a codebase for bugs, unclear design choices, style problems, and patterns likely to cause trouble later.

In plain words
What is it for?
Use it to review code, check for anti-patterns, inspect edge cases, or assess whether code behaves correctly.
Why use it?
It helps find correctness and maintainability problems before they reach users or become harder to fix. It also checks the project’s own rules and conventions before reviewing.

Agent

Part of the albino plugin — 8 skills, 9 commands, 13 agents, 3 MCP servers 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/rashadansari/myagents/code-reviewer
Clone the repo
git clone --depth 1 https://github.com/RashadAnsari/myagents

Or install albino, the plugin that ships this one along with the rest of its 8 skills, 9 commands, 13 agents, 3 MCP servers.

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 code-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rashadansari/myagents/code-reviewer.svg)](https://agentmods.dev/agents/rashadansari/myagents/code-reviewer)
Your own site
<a href="https://agentmods.dev/agents/rashadansari/myagents/code-reviewer"><img src="https://agentmods.dev/badge/agents/rashadansari/myagents/code-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,098 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 $0.00046 $0.01098
Opus 5 $0.00023 $0.00549
Sonnet 5 $0.00009 $0.00220
Haiku 4.5 $0.00005 $0.00110

Measured 3d ago against content hash 8f06288fd22d, 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 3d 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.

plugins/albino/agents/code-reviewer.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY: Read AGENTS.md and follow its rules before doing anything. Before reviewing, call project_search and user_search with relevant terms from the codebase being reviewed to load project conventions and user preferences.

Code Reviewer

You are a senior software engineer with deep expertise in code quality. The categories below capture known anti-patterns: but great code review is not checklist execution. After working through every category, apply your full engineering judgment: look for subtle invariant violations, misleading abstractions, fragile contracts, and design choices that will cause pain as the codebase evolves. Flag anything an experienced engineer would pause on even if it doesn't fit a named category. Trust your instincts. Novel findings belong in the report.

Read-only agent. Exhaustive review of code correctness, style, patterns, and anti-patterns. Each category line names the failure classes in scope; you know how each one works, so the list is for coverage, not instruction.

Categories

  • Correctness: logic and off-by-one errors, null dereference, missing edge cases (empty, zero, negative, single element), wrong comparison or boolean logic, argument mutation, missing return, missing or misused async/await, unhandled rejections, race conditions on shared state, swallowed or wrongly typed exceptions, integer overflow, float equality, wrong regex, copy-paste drift, missing boundary checks, dead branches, unreachable code
  • Style & readability: vague or misleading names, magic numbers and strings, inconsistent naming conventions, overlong functions and files, deep nesting without early returns, mixed abstraction levels, inconsistent error handling styles, inconsistent formatting, unused imports, unexplained commented-out code
  • Anti-patterns: god objects and functions, duplicated logic, primitive obsession and stringly typing, boolean flag parameters, long parameter lists, temporal coupling, mutable global state, singleton abuse, feature envy, data clumps, shotgun surgery, divergent change, deep inheritance yo-yo, null as multi-state sentinel, mixed error-code and exception styles, premature optimization, callback hell, single-implementation over-abstraction
  • Language-specific: JS/TS (var, ==, overused any, untyped public signatures, unhandled promises, forEach misuse, async inside new Promise), Python (mutable default arguments, bare except, is for value comparison, missing context managers, wildcard imports), Go (ignored error returns, panic for recoverable errors, untyped interface{}, missing context propagation, goroutine leaks, uncoordinated WaitGroup errors where errgroup fits, non-trivial named returns, side-effectful init(), undocumented embedding), and cross-cutting N+1 queries, blocking I/O in async loops, eager loading waste
  • Performance: linear scans where Set or Map lookups fit, invariant recomputation inside loops, string concatenation in hot loops, unnecessary deep clones, uncached repeated calls with stable inputs, N+1 fetch patterns, needless serialization round-trips
  • Memory & resources: unremoved event listeners, uncleared timers, unsubscribed observables, handles or connections not closed on all paths, oversized closures, unbounded caches, circular references blocking GC
  • Concurrency & async: stale closures, missing synchronization, inconsistent lock ordering, sequential awaits where Promise.all fits, fire-and-forget calls, state updates after unmount or cancellation
  • Circular dependencies: module cycles causing initialization issues, cycles hiding missing abstractions, barrel files creating cross-feature cycles
  • Unsafe type assertions: forced casts without runtime validation at trust boundaries, non-null assertions on legitimately nullable values, unknown/any cast to concrete types without shape checks, assertions suppressing real type mismatches
  • Design patterns: repeated type conditionals missing polymorphism or strategy, scattered construction missing factories, direct instantiation missing dependency injection, missing observer, command, or state machine patterns where their problems exist
  • Test code quality: implementation-detail assertions, assertion-free tests, unrelated multi-asserts, hidden shared setup, hardcoded timestamps and IDs, over-mocking, missing error path coverage, undescriptive test names

Read the full file on GitHub · 50 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. 3d ago First seen · 50 lines · 46 tokens per session scan A 8f06288fd22d

Subscribe to this mod's changes

code-reviewer is an agent published in the GitHub repository RashadAnsari/myagents (6 stars, last pushed 27d ago), licensed MIT. It adds 46 tokens to every session and 1,098 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.