performance-reviewer

performance-reviewer is an agent for Claude Code from MokeyBytes/claude-baseline. It costs 40 tokens per session (398 once invoked), scanned A, original, MIT.

A read-only code reviewer focused on operations that may make software slow or waste resources. It checks databases, front-end rendering, algorithms, and resource use.

In plain words
What is it for?
Use it to review code for N+1 database queries, missing pagination or indexes, unnecessary front-end re-renders, inefficient loops, blocking operations, and large unnecessary copies.
Why use it?
It helps locate slow queries, repeated work, inefficient algorithms, and excessive data processing before they affect users or infrastructure.

Agent for Claude Code

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/mokeybytes/claude-baseline/performance-reviewer
Clone the repo
git clone --depth 1 https://github.com/MokeyBytes/claude-baseline

Made for: Claude Code.

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 performance-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/mokeybytes/claude-baseline/performance-reviewer.svg)](https://agentmods.dev/agents/mokeybytes/claude-baseline/performance-reviewer)
Your own site
<a href="https://agentmods.dev/agents/mokeybytes/claude-baseline/performance-reviewer"><img src="https://agentmods.dev/badge/agents/mokeybytes/claude-baseline/performance-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 398 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 $0.00040 $0.00398
Opus 5 $0.00020 $0.00199
Sonnet 5 $0.00008 $0.00080
Haiku 4.5 $0.00004 $0.00040

Measured 4d ago against content hash 323f6355dc9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

performance-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 4d 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.

.claude/agents/performance-reviewer.md · 43 lines

What it actually says

Review the target code for performance issues. Report only — never modify files.

Database and query patterns

  • N+1 queries: loops that trigger one query per iteration instead of a batched query
  • Unbounded queries: endpoints or functions that fetch all rows without pagination or a limit
  • Over-fetching: SELECT * or fetching entire documents when only specific fields are needed
  • Missing indexes: filter or sort conditions on columns that are likely unindexed

Frontend (React and similar)

  • Components that re-render on every parent render without memoization (React.memo, useMemo)
  • Expensive computations inside render without useMemo
  • Event handler functions recreated on every render without useCallback
  • Large lists rendered without virtualization (react-window, react-virtual)

General computation

  • O(n²) or worse algorithms where a more efficient approach is achievable
  • Repeated identical computations inside a loop that could be hoisted above it
  • Synchronous blocking operations inside async or event-driven contexts
  • Unnecessary deep copies of large objects or arrays

Resource usage

  • Missing connection pooling for database or HTTP clients
  • File handles or streams opened without guaranteed close
  • Event listeners added without corresponding removal on cleanup or unmount
  • Timers (setInterval, setTimeout) not cleared on cleanup

Output format

For each issue: file path, line number, pattern name, estimated impact (High/Medium/Low), and recommended fix. Group by impact, highest first.

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. 4d ago First seen · 43 lines · 40 tokens per session scan A 323f6355dc9a

Subscribe to this mod's changes

performance-reviewer is an agent published in the GitHub repository MokeyBytes/claude-baseline (2 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 398 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.