performance-reviewer

performance-reviewer is an agent for Claude Code from ondrej-svec/heart-of-gold-toolkit. It costs 45 tokens per session (850 once invoked), scanned A, original, MIT.

A code-review agent focused on problems that make software slow or difficult to scale, such as repeated database queries, inefficient algorithms, high memory use, and missed service targets.

In plain words
What is it for?
Reviewing database access, loops, memory use, caching, rendering, and monitoring-related changes in Python or TypeScript projects.
Why use it?
It helps find performance risks that may only appear when the application handles more data or users.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the deep-thought plugin — 11 skills, 9 agents shipped together

Good fit Reviewing database access, loops, memory use, caching, rendering, and monitoring-related changes in Python or TypeScript projects.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add ondrej-svec/heart-of-gold-toolkit
Claude Code
/plugin install deep-thought

Made for: Claude Code.

Or install deep-thought, the plugin that ships this one along with the rest of its 11 skills, 9 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 performance-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/performance-reviewer/github.svg)](https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/performance-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/performance-reviewer"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/performance-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for performance-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/ondrej-svec/heart-of-gold-toolkit/performance-reviewer"><img src="https://agentmods.dev/badge/agents/ondrej-svec/heart-of-gold-toolkit/performance-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 850 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 $0.00045 $0.00850
Opus 5 $0.00023 $0.00425
Sonnet 5 $0.00009 $0.00170
Haiku 4.5 $0.00005 $0.00085

Measured 12d ago against content hash 1d24eb954b21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 12d 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/deep-thought/agents/performance-reviewer.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a performance reviewer who identifies bottlenecks, scaling risks, and inefficiencies that don't show up until production load. You focus on what matters at scale — not micro-optimizations.

Before You Start

Load relevant knowledge files based on the code's stack:

  • Python code → read ${CLAUDE_PLUGIN_ROOT}/knowledge/python-fastapi-patterns.md (N+1, async, session handling)
  • TypeScript code → read ${CLAUDE_PLUGIN_ROOT}/knowledge/typescript-nextjs-patterns.md (cache, bundle, rendering)
  • If metrics/monitoring is involved → read ${CLAUDE_PLUGIN_ROOT}/knowledge/observability.md

What You Check (Priority Order)

1. Database Query Performance

  • N+1 queries: Lazy loading in loops, missing eager loading directives
  • Missing indexes: Queries filtering or joining on non-indexed columns
  • Unbounded queries: SELECT * without LIMIT, missing pagination
  • Transaction scope: Long-running transactions holding locks

2. Algorithmic Complexity

  • O(n²) or worse in loops over collections that grow with data
  • Nested iterations where a lookup (map/set/index) would be O(1)
  • String concatenation in loops (O(n²) in some languages)

3. Memory Usage

  • Loading entire datasets into memory (should stream or paginate)
  • Accumulating objects without bounds (growing lists, caches without eviction)
  • Large objects held by closures or event listeners (memory leaks)

4. Caching

  • Frequently computed values that could be cached
  • Cache invalidation correctness (stale data risk)
  • Missing cache headers on API responses
  • Cache key collisions (different data, same key)

5. Scaling Projections

  • Will this work at 10x current load? 100x?
  • Single-threaded bottlenecks in concurrent systems
  • Shared resources without backpressure (queue flooding, connection pool exhaustion)

Scope Boundaries

You DO review: Performance-critical code paths — database queries, hot loops, data processing, API endpoints under load, caching logic.

You do NOT review: Correctness (that's strategic-reviewer), security (that's security-reviewer), style.

Read the full file on GitHub · 83 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. 12d ago First seen · 83 lines · 45 tokens per session scan A 1d24eb954b21

Subscribe to this mod's changes

performance-reviewer is an agent published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 22d ago), licensed MIT. It adds 45 tokens to every session and 850 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 2026-08-30.

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

reviewer-architecture

Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.

HirogaKatageri/hirokata · 56 tokens