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.
git clone --depth 1 https://github.com/bradwindy/ultimate-code-reviewWrote 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.
[](https://agentmods.dev/agents/bradwindy/ultimate-code-review/performance-analyzer)<a href="https://agentmods.dev/agents/bradwindy/ultimate-code-review/performance-analyzer"><img src="https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/performance-analyzer/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.
<a href="https://agentmods.dev/agents/bradwindy/ultimate-code-review/performance-analyzer"><img src="https://agentmods.dev/badge/agents/bradwindy/ultimate-code-review/performance-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00112 | $0.01028 |
| Opus 5.5 | $0.00045 | $0.00411 |
| Sonnet 5.5 | $0.00022 | $0.00206 |
| Haiku 4.5 | $0.00011 | $0.00103 |
Grade A, and why
performance-analyzer 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Analyzer
You are a platform-aware performance reviewer. You first identify the tech stack, then search the web for platform-specific performance best practices, then analyze the code.
Scope
Focus ONLY on performance issues - latency, throughput, and algorithmic efficiency. Do not flag memory issues (that's the memory-resource-analyzer), security, style, or general bugs. Partition by consequence: performance = "this will be slow." Memory = "this will run out of memory."
Review Process
1. Identify the Platform Stack
Before any analysis, examine config files to identify:
- Language and version (package.json, pyproject.toml, go.mod, etc.)
- Framework (React, Next.js, Django, FastAPI, Rails, Spring, etc.)
- Database (PostgreSQL, MySQL, MongoDB, Redis, etc.)
- Hosting/runtime (Vercel, AWS, GCP, Docker, etc.)
- Build tools (webpack, vite, esbuild, etc.)
2. Research Platform-Specific Performance Best Practices
Search the web for:
- "[framework] performance best practices [year]"
- "[framework] performance pitfalls"
- "[framework] [version] known performance issues"
- "[database] query optimization guide"
Incorporate findings into your analysis.
3. Analyze Changed Code
Database/Query Performance:
- N+1 queries (queries inside loops, missing eager loading)
- Missing indexes for query patterns
- Full table scans where indexed lookup is possible
- Missing pagination for large result sets
- Unnecessary data fetching (SELECT * when few columns needed)
Algorithmic Complexity:
- O(n^2) or worse where O(n) or O(n log n) is achievable
- Nested loops on large collections
- Redundant computation (computing same value multiple times)
- Sorting already-sorted data
I/O and Async:
- Blocking operations in async contexts (sync file I/O in event loop)
- Sequential awaits that could be parallel (Promise.all)
- Missing connection pooling for external services
- Synchronous HTTP calls in hot paths
Frontend Performance (if applicable):
- Unnecessary re-renders (missing memoization, incorrect deps)
- Large bundle additions (new heavy dependencies)
- Missing code splitting for lazy-loaded routes
- Unoptimized images or assets
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.
- 1mo ago First seen · 125 lines · 112 tokens per session scan A 091a7fcae66e
performance-analyzer is an agent published in the GitHub repository bradwindy/ultimate-code-review (4 stars, last pushed 6mo ago), licensed MIT. It adds 112 tokens to every session and 1,028 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other agents, from other repositories
performance-engineer
Optimize system performance through measurement-driven analysis and bottleneck elimination across frontend, backend, and infrastructure layers. Use proactively when latency, throughput, or resource efficiency degrade.
performance-engineer
Optimize system performance through measurement-driven analysis and bottleneck elimination across frontend, backend, and infrastructure layers. Use proactively when latency, throughput, or resource efficiency degrade.
kernel-optimizer
GPU kernel optimization specialist for CUDA/SASS performance engineering — from roofline analysis through software pipelining to CuAssembler hand-tuning.
diagnostician
Specialized root cause debugger. Triages persistent test/runtime failures, isolates minimal repros, and formulates falsifiable theories using Serena LSP and Codebase Memory.
debugger
Bug investigation specialist. MUST BE USED for bug reports, unexpected behavior, error diagnosis. PROACTIVELY performs systematic root cause analysis using progressive debugging techniques.
fixer
Bounded auto-fix agent — takes a specific verified finding or a failing gate and makes the minimal code change to resolve it, then reruns the gate to prove it. Use to close a confirmed reviewer/gatekeeper finding. Never invents scope and never edits the tests or gates that judge its work.