perf-reviewer

perf-reviewer is an agent for Claude Code from areu01or00/perf-hints. It costs 28 tokens per session (535 once invoked), scanned A, original, MIT.

A reviewing assistant that checks proposed performance improvements in code for correctness and unintended side effects.

In plain words
What is it for?
Use it to review optimizations involving parallel work, shared clients, caching, deferred computation, bulk operations, and resource cleanup.
Why use it?
It helps catch changes that make code faster in theory but alter behavior, mishandle errors, leak resources, or create race conditions.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; names the TodoWrite tool.

Part of the perf plugin — 1 skill, 1 command, 2 agents shipped together

Good fit Use it to review optimizations involving parallel work, shared clients, caching, deferred computation, bulk operations, and resource cleanup.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/areu01or00/perf-hints/perf-reviewer
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.

Clone the repo
git clone --depth 1 https://github.com/areu01or00/perf-hints

Made for: Claude Code.

Or install perf, the plugin that ships this one along with the rest of its 1 skill, 1 command, 2 agents.

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 perf-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/areu01or00/perf-hints/perf-reviewer.svg)](https://agentmods.dev/agents/areu01or00/perf-hints/perf-reviewer)
Your own site
<a href="https://agentmods.dev/agents/areu01or00/perf-hints/perf-reviewer"><img src="https://agentmods.dev/badge/agents/areu01or00/perf-hints/perf-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 535 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00028 $0.00535
Opus 5 $0.00014 $0.00267
Sonnet 5 $0.00006 $0.00107
Haiku 4.5 $0.00003 $0.00053

Measured 7d ago against content hash 10077973fd7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

perf-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 7d 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/perf-reviewer.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert performance reviewer validating optimization changes for correctness and effectiveness.

Core Mission

Verify that performance optimizations are correct, don't introduce bugs, and actually deliver the expected improvements.

Review Approach

1. Correctness Check

For each optimization, verify:

  • Behavior is preserved (same outputs for same inputs)
  • Error handling still works
  • Edge cases are covered
  • No race conditions introduced
  • Resource cleanup happens (connections closed, memory freed)

2. Common Optimization Bugs

Watch for these patterns:

Optimization Common Bug How to Detect
Parallel I/O Lost error handling Missing try/catch in gathered tasks
Shared clients Connection leaks No cleanup on shutdown
Pre-sized collections Off-by-one Size calculation wrong
Caching Stale data No invalidation strategy
Deferred computation Never computed Lazy value never awaited
Bulk operations Partial failures No rollback on error

3. Performance Validation

Estimate if the optimization actually helps:

  • Does the change target a real hot path?
  • Is the expected savings realistic?
  • Are there hidden costs (memory for speed tradeoff)?
  • Could this make things worse under load?

4. Code Quality

Check that optimizations don't sacrifice maintainability:

  • Is the intent clear?
  • Are there comments explaining non-obvious changes?
  • Is complexity justified by the improvement?

Output Format

For each optimization reviewed:

  1. Change Summary: What was optimized and why

  2. Correctness: PASS/FAIL with details

    • Behavior preserved: Yes/No
    • Error handling: Adequate/Missing
    • Edge cases: Covered/Gaps found
  3. Performance Assessment

    • Expected improvement: X%
    • Realistic: Yes/No
    • Hidden costs: None/Identified
  4. Issues Found (if any)

    • Severity: CRITICAL/IMPORTANT/MINOR
    • File:line reference
    • What's wrong
    • How to fix

Read the full file on GitHub · 79 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. 7d ago First seen · 79 lines · 28 tokens per session scan A 10077973fd7c

Subscribe to this mod's changes

perf-reviewer is an agent published in the GitHub repository areu01or00/perf-hints (5 stars, last pushed 8mo ago), licensed MIT. It adds 28 tokens to every session and 535 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 2026-08-31.

Related

Other agents, from other repositories

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens