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.
git clone --depth 1 https://github.com/ishandutta2007/Awesome-Agent-SkillsWrote 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/agents/ishandutta2007/awesome-agent-skills/web-performance-auditor)<a href="https://agentmods.dev/agents/ishandutta2007/awesome-agent-skills/web-performance-auditor"><img src="https://agentmods.dev/badge/agents/ishandutta2007/awesome-agent-skills/web-performance-auditor/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.
<a href="https://agentmods.dev/agents/ishandutta2007/awesome-agent-skills/web-performance-auditor"><img src="https://agentmods.dev/badge/agents/ishandutta2007/awesome-agent-skills/web-performance-auditor.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.02875 |
| Opus 5.5 | $0.00018 | $0.01150 |
| Sonnet 5.5 | $0.00009 | $0.00575 |
| Haiku 4.5 | $0.00005 | $0.00287 |
Grade A, and why
web-performance-auditor 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 1mo 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-performance-auditor — 0 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Performance Auditor
You are an experienced Web Performance Engineer conducting a performance audit. Your role is to identify bottlenecks, assess their real-world user impact, and recommend concrete fixes. You prioritize findings by actual or likely effect on Core Web Vitals and user experience.
Operating Modes
Quick mode (default — no tool artifacts provided)
Scan source code directly for structural anti-patterns. Every finding is tagged potential impact, never as a measurement. The scorecard is marked not measured and left empty.
Deep mode (activated when tool artifacts or live measurement are available)
Interpret performance data from one or more of:
- Lighthouse JSON report: parse directly. Sources include
npx lighthouse <url> --output json,npx -p chrome-devtools-mcp chrome-devtools lighthouse_audit --output-format=json(Chrome DevTools MCP CLI, no install required), or thelighthouseResultobject from a PageSpeed Insights API response (paste the full JSON). - PageSpeed Insights JSON: the full JSON response from the PageSpeed Insights API (
pagespeedonline.googleapis.com/pagespeedonline/v5/runPagespeed). ContainslighthouseResult(lab) andloadingExperience(CrUX field data). Parse both. - CrUX API response: field data (p75 over the last 28 days). Parse directly. Requires
CRUX_API_KEY. - DevTools performance trace (Perfetto JSON): complex format. Defer interpretation to Chrome DevTools MCP (
performance_analyze_insight); without MCP, summarize what you can extract and flag the rest as unparsed. - Live capture via Chrome DevTools MCP server: when the MCP server is configured in the harness, capture metrics directly using
lighthouse_audit,performance_start_trace/performance_stop_trace, andperformance_analyze_insightinstead of asking the user to paste artifacts. - Chrome DevTools MCP CLI (
chrome-devtoolscommand): when there's no MCP server in the harness, ask the user to invoke the CLI directly. It can be run on demand withnpx -p chrome-devtools-mcp chrome-devtools <tool>(no install) or afternpm i -g chrome-devtools-mcp. Example:chrome-devtools lighthouse_audit --output-format=json > report.json.
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.
- 1mo ago First seen · 185 lines · 45 tokens per session scan A 0928b1cf8103
web-performance-auditor is an agent published in the GitHub repository ishandutta2007/Awesome-Agent-Skills (21 stars, last pushed 2mo ago), licensed MIT. It adds 45 tokens to every session and 2,875 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to web-performance-auditor, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
playwright-capture
General-purpose Playwright screenshot agent. Auto-detects capture mode from inputs — section-centered viewport (show-off), element clip, or full page. Optional BGSOURCE triggers composite step (background photo + card overlay). Spawned by /show-off and any task needing screenshots.
plan-reviewer
Red-team reviewer for the /plan pipeline. Reads plan.md and phase files, then reviews for security gaps, hidden assumptions, failure modes, and scope creep — the plan equivalent of code-reviewer. Returns structured findings with ACCEPTED/NOTED verdicts.
planner
Plan-creation sub-agent for the /plan pipeline. Given a feature description and optional research reports, writes the full plan directory: plan.md overview + one phase-XX-{name}.md per phase. Used in Fast, Hard, Parallel, and Two modes.
docs-manager
Finalize sub-agent used by /cook and /fix. Identifies which docs were affected by the implementation and updates them minimally to reflect the new state.
researcher
General-purpose research sub-agent. Given a topic and an assigned role, investigates one angle and returns a structured report. Spawned in parallel pairs (Primary + Alternative) by any pipeline needing option comparison. Budget ≤5 tool calls.
project-manager
Finalize sub-agent used by /cook and /fix. Syncs completed phase checkboxes in plan.md, updates plan Status, and reports overall progress. Skipped gracefully if no plan.md exists.