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.
npx agentmods add skills/rampstackco/claude-skills-starter/performance-optimizationnpx skills add rampstackco/claude-skills-starter --skill performance-optimizationgit clone --depth 1 https://github.com/rampstackco/claude-skills-starterWrote 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/rampstackco/claude-skills-starter/performance-optimization)<a href="https://agentmods.dev/skills/rampstackco/claude-skills-starter/performance-optimization"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills-starter/performance-optimization.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 | $0.00141 | $0.02345 |
| Opus 5 | $0.00071 | $0.01172 |
| Sonnet 5 | $0.00028 | $0.00469 |
| Haiku 4.5 | $0.00014 | $0.00234 |
Grade A, and why
performance-optimization 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.
How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Optimization
Diagnose web performance issues and produce a remediation plan. Stack-agnostic. Anchored to Core Web Vitals and standard browser performance patterns.
This skill goes deeper than the performance checks in qa-testing and seo-technical. Use this when performance itself is the goal.
When to use
- Fixing Core Web Vitals (LCP, INP, CLS)
- Diagnosing slow page loads
- Reducing JavaScript bundle size
- Optimizing images, fonts, and other assets
- Fixing layout shift, render-blocking resources, jank
- Pre-launch performance verification
- Annual performance health check
When NOT to use
- General QA after deploys (use
qa-testing) - Technical SEO including indexing and crawling (use
seo-technical) - Code review for general bugs (use
code-review-web)
Required inputs
- The site or page under audit
- Specific performance complaints if any
- Target metrics (Core Web Vitals thresholds, Lighthouse score, custom)
- Browser dev tools access
- Performance monitoring data if available (Real User Monitoring, lab data)
The framework: Core Web Vitals
Three metrics carry most of the weight for both user experience and SEO:
LCP (Largest Contentful Paint)
What it measures: Time until the largest visible content element finishes rendering.
Targets:
- Good: under 2.5 seconds
- Needs improvement: 2.5 to 4.0 seconds
- Poor: over 4.0 seconds
Common causes of poor LCP:
- Slow server response time (TTFB over 800ms)
- Render-blocking JavaScript or CSS
- Large unoptimized images for the LCP element
- Late-loading fonts that delay text render
- Client-side rendering of the LCP element
Common fixes:
- Server-render the LCP element (no client-side render)
- Optimize the LCP image (right format, right size, preloaded)
- Reduce render-blocking resources (defer non-critical CSS and JS)
- Use modern image formats (WebP, AVIF)
- Specify image dimensions to skip layout pass
INP (Interaction to Next Paint)
What ships with it
3 files 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.
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.
- 3d ago First seen · 275 lines · 141 tokens per session scan A 197dff3e07f0
performance-optimization is a skill published in the GitHub repository rampstackco/claude-skills-starter (2 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 2,345 once invoked, about $0.0007 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 skills, from other repositories
add-community-extension
Add a community extension to the Spec Kit catalog from a GitHub issue submission. USE FOR: processing extension submission issues, validating catalog entries, updating catalog.community.json and docs/community/extensions.md, creating PRs. DO NOT USE FOR: creating new extensions from scratch, or first-party extension…
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
Developmental Gene Panel Design Workflow
Panel design for DEVELOPING / dynamic systems (embryonic organs, differentiation, regeneration). The target experiment is usually a LATE / terminal stage, but the biology is a trajectory: terminal cell types are end-products of earlier lineage programs. A panel built from the target stage alone resolves terminal…
code-review-web
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug…
development-workflow
Detailed development workflow with modular patterns for git, review, testing, and deployment.
to-issues
Decompose a PRD and/or SPEC into implementable, vertically-sliced Issues with real blocking edges, then create them in your chosen platform (GitHub or Local). Use after /prd (and optionally /prd-to-spec) to turn requirements into agent-ready tickets. Triggers on: create issues, to-issues, 创建issue, 拆解issue, 生成卡片, 创建卡片…