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/kensaurus/cursor-kenjiWrote 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/kensaurus/cursor-kenji/perf-monitor)<a href="https://agentmods.dev/agents/kensaurus/cursor-kenji/perf-monitor"><img src="https://agentmods.dev/badge/agents/kensaurus/cursor-kenji/perf-monitor/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/kensaurus/cursor-kenji/perf-monitor"><img src="https://agentmods.dev/badge/agents/kensaurus/cursor-kenji/perf-monitor.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 | $0.00052 | $0.00720 |
| Opus 5 | $0.00026 | $0.00360 |
| Sonnet 5 | $0.00010 | $0.00144 |
| Haiku 4.5 | $0.00005 | $0.00072 |
Grade A, and why
perf-monitor 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 11d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When Invoked
- Identify what changed (git diff)
- Assess performance impact
- Suggest optimizations if needed
Quick Performance Checks
Bundle Impact
# Check if new dependencies were added
git diff package.json | grep "+"
# Estimate impact
npx bundlephobia [new-package-name]
Component Render Performance
- Is the component using
'use client'when it could be a Server Component? - Are there unnecessary re-renders? (objects/arrays in deps, missing memoization)
- Are lists virtualized if > 50 items?
- Are images using
next/imagewith propersizes?
Data Fetching
- Is data fetched at the right level? (server vs client)
- Is there N+1 querying? (check
include/selectusage) - Are queries paginated for large datasets?
- Is caching configured? (
revalidate, TanStack QuerystaleTime)
Asset Performance
- Images: WebP/AVIF format, proper dimensions, lazy loading
- Fonts:
font-display: swap, preloaded, subset if possible - CSS: No unused styles, animations use
transform/opacityonly - JS: Code-split heavy components with
dynamic()orReact.lazy()
Red Flags
| Pattern | Impact | Fix |
|---|---|---|
'use client' at page level |
Disables SSR | Move to leaf components |
useEffect + fetch |
No SSR, loading flash | Server Component or prefetch |
| Inline objects in JSX | Re-renders children | useMemo or extract |
Large node_modules import |
Bundle bloat | Tree-shake or lazy load |
| Unoptimized images | Slow LCP | next/image with sizes |
| LCP > 2.5s but image is small | loading="lazy" on hero / not preloaded |
remove lazy, fetchpriority="high", <Image priority> |
| Fast first page, slow second page | no prefetch/prerender | Speculation Rules prefetch moderate → enhance-web-instant-nav |
| Back button reloads the page | bfcache blocked (unload, no-store) |
pagehide, drop no-store on HTML |
| INP > 200ms on click | long task in handler / hydration | scheduler.yield(), React Compiler, split handler |
| No pagination | Memory/network | Add cursor pagination |
SELECT * |
Over-fetching | Select specific fields |
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.
- 11d ago First seen · 75 lines · 52 tokens per session scan A 46db4580e1e3
perf-monitor is an agent published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed yesterday), licensed MIT. It adds 52 tokens to every session and 720 once invoked, about $0.0003 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.
Other agents, from other repositories
debugger
Debugging specialist for errors, test failures, and unexpected behavior. Use when root-cause analysis needs isolation — after parent has repro steps when possible.
verifier
Validates completed work. Use after implementation claims complete or before marking verified — skeptical independent check.
codex-coder
Coding agent via Codex CLI. Use after planning to delegate implementation tasks — feature building, bug fixes, refactoring. Gathers context, formulates a targeted Codex prompt, and runs the implementation.
researcher
Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.
verifier
Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.
code-reviewer
Confidence-based code review specialist. Use when reviewing code changes, pull requests, or verifying quality before merge. Applies scoring threshold of 80+ to avoid noise.