Borrowing it
Nothing to install: this file belongs to kevyder/banrepco_mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kevyder/banrepco_mcp/master/.agents/skills/web-perf/SKILL.mdgit clone --depth 1 https://github.com/kevyder/banrepco_mcpWrote 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/skills/kevyder/banrepco_mcp/web-perf)<a href="https://agentmods.dev/skills/kevyder/banrepco_mcp/web-perf"><img src="https://agentmods.dev/badge/skills/kevyder/banrepco_mcp/web-perf.svg" alt="Measured on agentmods" 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 | $0.00096 | $0.02051 |
| Opus 5 | $0.00048 | $0.01026 |
| Sonnet 5 | $0.00019 | $0.00410 |
| Haiku 4.5 | $0.00010 | $0.00205 |
Grade A, and why
web-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 8d 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.
This is a copy
100% identical to web-perf — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Performance Audit
Your knowledge of web performance metrics, thresholds, and tooling APIs may be outdated. Prefer retrieval over pre-training when citing specific numbers or recommendations.
Retrieval Sources
| Source | How to retrieve | Use for |
|---|---|---|
| web.dev | https://web.dev/articles/vitals |
Core Web Vitals thresholds, definitions |
| Chrome DevTools docs | https://developer.chrome.com/docs/devtools/performance |
Tooling APIs, trace analysis |
| Lighthouse scoring | https://developer.chrome.com/docs/lighthouse/performance/performance-scoring |
Score weights, metric thresholds |
FIRST: Verify MCP Tools Available
Run this before starting. Try calling navigate_page or performance_start_trace. If unavailable, STOP—the chrome-devtools MCP server isn't configured.
Ask the user to add this to their MCP config:
"chrome-devtools": {
"type": "local",
"command": ["npx", "-y", "chrome-devtools-mcp@latest"]
}
Key Guidelines
- Be assertive: Verify claims by checking network requests, DOM, or codebase—then state findings definitively.
- Verify before recommending: Confirm something is unused before suggesting removal.
- Quantify impact: Use estimated savings from insights. Don't prioritize changes with 0ms impact.
- Skip non-issues: If render-blocking resources have 0ms estimated impact, note but don't recommend action.
- Be specific: Say "compress hero.png (450KB) to WebP" not "optimize images".
- Prioritize ruthlessly: A site with 200ms LCP and 0 CLS is already excellent—say so.
Quick Reference
| Task | Tool Call |
|---|---|
| Load page | navigate_page(url: "...") |
| Start trace | performance_start_trace(autoStop: true, reload: true) |
| Analyze insight | performance_analyze_insight(insightSetId: "...", insightName: "...") |
| List requests | list_network_requests(resourceTypes: ["Script", "Stylesheet", ...]) |
| Request details | get_network_request(reqid: <id>) |
| A11y snapshot | take_snapshot(verbose: true) |
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.
- 8d ago First seen · 202 lines · 96 tokens per session scan A 94c5cb377666
web-perf is a skill published in the GitHub repository kevyder/banrepco_mcp (9 stars, last pushed 27d ago), licensed MPL-2.0. It adds 96 tokens to every session and 2,051 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to web-perf, differing in 10 lines, and is treated as a copy.
Other skills, from other repositories
design-system
Explains the Aurora Fluid design system — OKLCH colors, physics animations, motion levels, weight tiers, CSS architecture, and theming. Use when the user asks about design tokens, colors, animations, theming, or how the design system works.
tier-guide
Helps choose the right weight tier (Lite/Standard/Premium) based on project requirements. Use when the user asks about bundle size, performance optimization, which tier to use, or import paths.
openclaw-color-palette
Design-grade color processing suite — generate harmonious palettes from any seed color, check WCAG 2.1 AA/AAA contrast accessibility, convert between hex/RGB/HSL/HSV/CMYK, simulate 8 color blindness types, and extract dominant colors from images. Use when: (1) user says 'generate a color palette' or 'give me a color…
generate-component
Generate production-ready React code using UI Kit components. Use when the user asks to "build", "create", "make", "generate" a UI, page, form, dashboard, or component composition. Produces working TSX with correct imports, props, and Aurora Fluid styling.
audit-accessibility
Audit React components for accessibility compliance with UI Kit conventions. Use when the user asks to "check accessibility", "audit a11y", "review for screen readers", or "test keyboard navigation". Checks ARIA, contrast, touch targets, motion, and keyboard patterns.
component-finder
Find UI Kit components by name, feature, or use case. Use when the user asks "what component for...", "is there a...", "show me components", "find a widget", or describes UI they want to build. Covers all 147 components across Lite/Standard/Premium tiers.