perf-plan

perf-plan is a command for coding agents from kensaurus/cursor-kenji. It costs 16 tokens per session (142 once invoked), scanned A, original, MIT.

A performance review that measures real web vitals, JavaScript bundle size, and database queries before proposing optimizations. It produces a ranked, phased plan without applying fixes.

In plain words
What is it for?
Use it to investigate slow pages, large bundles, or inefficient queries, record where the problems occur, and plan improvements based on measurements.
Why use it?
Performance problems are easy to guess incorrectly and optimize in the wrong place. Measurement shows which issues have the greatest observed impact before changes are approved.

Command

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 commands/kensaurus/cursor-kenji/perf-plan
Clone the repo
git clone --depth 1 https://github.com/kensaurus/cursor-kenji

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-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/kensaurus/cursor-kenji/perf-plan.svg)](https://agentmods.dev/commands/kensaurus/cursor-kenji/perf-plan)
Your own site
<a href="https://agentmods.dev/commands/kensaurus/cursor-kenji/perf-plan"><img src="https://agentmods.dev/badge/commands/kensaurus/cursor-kenji/perf-plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 142 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 $0.00016 $0.00142
Opus 5 $0.00008 $0.00071
Sonnet 5 $0.00003 $0.00028
Haiku 4.5 $0.00002 $0.00014

Measured 3d ago against content hash 249334a75565, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

perf-plan 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 3d 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.

commands/perf-plan.md · 17 lines

What it actually says

Performance Audit Plan

Run the plan-perf-audit skill: measure performance (Core Web Vitals, bundle, queries) and produce an optimization plan grounded in measurements, not guesses. Audit and plan only — optimize nothing until the plan is approved.

Emit findings ranked by measured impact with locations and a phased checklist. After approval, execute with audit-performance, backend-db-performance, and workflow-refactor.

The full playbook lives in the plan-perf-audit skill.

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. 3d ago First seen · 17 lines · 16 tokens per session scan A 249334a75565

Subscribe to this mod's changes

perf-plan is a command published in the GitHub repository kensaurus/cursor-kenji (9 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 142 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.