review-perf

review-perf is a skill for Claude Code from chrisallenlane/claude-swe-workflows. It costs 28 tokens per session (1,524 once invoked), scanned A, original, MIT.

A performance review that checks a project for speed and resource problems in its code, website, or both. It measures the project’s structure and gives recommendations without changing files.

In plain words
What is it for?
Finding likely performance issues, deciding what to measure, and receiving suggested fixes before implementing them.
Why use it?
It separates computing concerns such as CPU, memory, and algorithms from website concerns such as network delays, caching, and asset delivery.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the claude-swe-workflows plugin — 17 skills, 40 agents shipped together

Good fit Finding likely performance issues, deciding what to measure, and receiving suggested fixes before implementing them.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chrisallenlane/claude-swe-workflows/review-perf
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.

Any agent
npx skills add chrisallenlane/claude-swe-workflows --skill review-perf
Clone the repo
git clone --depth 1 https://github.com/chrisallenlane/claude-swe-workflows

Made for: Claude Code.

Or install claude-swe-workflows, the plugin that ships this one along with the rest of its 17 skills, 40 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 review-perf

README.md
[![agentmods](https://agentmods.dev/badge/skills/chrisallenlane/claude-swe-workflows/review-perf/github.svg)](https://agentmods.dev/skills/chrisallenlane/claude-swe-workflows/review-perf)
Your own site
<a href="https://agentmods.dev/skills/chrisallenlane/claude-swe-workflows/review-perf"><img src="https://agentmods.dev/badge/skills/chrisallenlane/claude-swe-workflows/review-perf/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 review-perf

Your own site · 80×15
<a href="https://agentmods.dev/skills/chrisallenlane/claude-swe-workflows/review-perf"><img src="https://agentmods.dev/badge/skills/chrisallenlane/claude-swe-workflows/review-perf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,524 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 $0.00028 $0.01524
Opus 5 $0.00014 $0.00762
Sonnet 5 $0.00006 $0.00305
Haiku 4.5 $0.00003 $0.00152

Measured 11d ago against content hash 5f1233ecc1f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-perf 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.

skills/review-perf/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Performance Review

Advisory-only performance review. Detects whether the project contains web content, non-web source code, or both, and dispatches the appropriate performance reviewer(s). No changes are made.

Philosophy

Measure, don't guess. Performance intuitions are unreliable. The reviewers identify structural issues and recommend what to measure, not just what to optimize.

Two domains, one workflow. Compute performance (algorithms, memory, CPU) and web performance (network latency, caching, asset delivery) are fundamentally different disciplines. This skill dispatches the right specialist(s) for the project rather than applying one lens to everything.

Diagnostic, not therapeutic. This skill identifies performance problems and recommends fixes. It does not implement them. Ask for changes directly after reviewing the findings, or use /implement with the review as context.

Workflow Overview

┌──────────────────────────────────────────────────────┐
│                 PERFORMANCE REVIEW                   │
├──────────────────────────────────────────────────────┤
│  1. Detect project type (web, non-web, or both)      │
│  2. Determine scope                                  │
│  3. Dispatch performance reviewer(s)                 │
│  4. Present consolidated report                      │
└──────────────────────────────────────────────────────┘

Workflow Details

1. Detect Project Type

Scan the project for source files to determine what performance domains apply.

Web indicators (any of these → dispatch web reviewer):

Indicator Signal
.html, .htm, .jsx, .tsx, .vue, .svelte Strong
package.json with web framework (react, vue, next, nuxt, astro, etc.) Strong
webpack.config.*, vite.config.*, next.config.* Strong
.css, .scss, .less files (more than a few) Moderate
_headers, _redirects, vercel.json, netlify.toml Moderate
Service worker files (sw.js, service-worker.js) Strong

Read the full file on GitHub · 191 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 191 lines · 28 tokens per session scan A 5f1233ecc1f0

Subscribe to this mod's changes

review-perf is a skill published in the GitHub repository chrisallenlane/claude-swe-workflows (18 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 1,524 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 2026-08-30.