What is review-performance?

A workflow for checking and improving the speed of a specific application page. It selects a page, maps its URL to the project’s code, and performs performance testing and review.

Use it to review a supplied URL or a page selected from the site map, then identify and fix page-performance problems.

It helps find slow parts of a page and identify bottlenecks that make the application feel less responsive.

How P2ERGmbH/agentic-coding configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to P2ERGmbH/agentic-coding. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/P2ERGmbH/agentic-coding/main/.agents/skills/review-performance/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/P2ERGmbH/agentic-coding

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/review-performance/github.svg)](https://agentmods.dev/skills/p2ergmbh/agentic-coding/review-performance)

Your own site

<a href="https://agentmods.dev/skills/p2ergmbh/agentic-coding/review-performance"><img src="https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/review-performance/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/p2ergmbh/agentic-coding/review-performance"><img src="https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/review-performance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,316 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.01316
Opus 5.5	$0.00008	$0.00526
Sonnet 5.5	$0.00004	$0.00263
Haiku 4.5	$0.00002	$0.00132

Measured 2mo ago against content hash e643c2733863, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

review-performance 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 2mo 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.

.agents/skills/review-performance/SKILL.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.

Performance Review Workflow

This workflow guides you through standardizing the performance testing and review of specific pages in the application.

Role & Persona

You are an expert performance engineer and autonomous agent.

Trigger

Use this workflow whenever the user asks to "run the review-performance workflow", "review performance for [URL]", or as a subsequent step during the github-issue-test workflow.

Phase 1: URL Selection and Route Resolution

URL Identification:
- If a URL is provided by the user (e.g., https://www.your-domain.com/de/product/some-product or http://localhost:6767/de/provider/...), use it.
- If NO URL is provided, fetch http://localhost:6767/sitemap.xml, parse it, and pick a random URL from the sitemap to test.
Route Pattern Matching:
- Extract the locale (e.g., de, en, fr) and the remaining path from the selected URL.
- Map the path to the corresponding route pattern. Inspect the configuration for paths.src (e.g. src/ or .) and search for any i18n pathnames files (paths.src/i18n/pathnames.ts or equivalent i18n configurations). If i18n configurations do not exist, map directly to the route segments.
- Example: .../de/provider/provider-1/product/item-9 maps to the pattern /provider/[slug]/product/[productSlug].
File Resolution:
- Translate the mapped route pattern into the corresponding Next.js file path within the configured app pages directory (e.g. paths.app or src/app).
- Example: The pattern /provider/[slug]/product/[productSlug] resolves to <paths.app>/[locale]/provider/[slug]/product/[productSlug]/page.tsx (or <paths.app>/provider/[slug]/product/[productSlug]/page.tsx if non-localized).
- Identify this file as the starting point for fixing performance issues. If the path does not exist, search dynamically using codebase tools to locate the page component.

Phase 2: Automated Performance Analysis

Initialize Browser & Trace:
- Ensure the chrome-devtools MCP is available.
- Use navigate_page to go to the target URL.
- Wait for the page to visually stabilize.
- Use performance_start_trace with reload: true to begin capturing frontend performance issues, Core Web Vitals (LCP, INP, CLS), and page load speed.
Stop Trace & Gather Insights:
- After the page has fully loaded, use performance_stop_trace.
- Analyze the generated trace file. Look for specific Performance Insights returned by the DevTools.
- If necessary, use performance_analyze_insight on specific blocking issues or layout shifts to get detailed information on what caused them.
- Holistic Quality Audit: Do not use Lighthouse as a fallback for performance traces. Instead, use lighthouse_audit as a complementary check to generate a structured report specifically targeting Accessibility (a11y), SEO, and web Best Practices regressions.

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.

2mo ago First seen · 83 lines · 19 tokens per session scan A e643c2733863

Subscribe to this mod's changes

review-performance is a skill published in the GitHub repository P2ERGmbH/agentic-coding (9 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 1,316 once invoked, about $0.0001 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.

Analytics and metrics Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

agentic-coding: Skill for Claude Code