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 commands/ghosteken/agent-harness/webperfgit clone --depth 1 https://github.com/Ghosteken/agent-harnessWhat 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 | $0.00013 | $0.00448 |
| Opus 5 | $0.00006 | $0.00224 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00001 | $0.00045 |
Grade A, and why
webperf 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 2d 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 webperf — 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.
What it actually says
/webperf targets web applications specifically. Do not use it for utility libraries, CLIs, or server-only code with no browser-facing output.
Determine the mode
Deep mode — activate when any of these is available:
- A Lighthouse JSON report file (e.g.
npx lighthouse <url> --output json --output-path ./report.json, ornpx -p chrome-devtools-mcp chrome-devtools lighthouse_audit --output-format=jsonfrom the Chrome DevTools MCP CLI) - A PageSpeed Insights JSON response (includes Lighthouse + CrUX)
- A CrUX API response (requires
CRUX_API_KEYorGOOGLE_API_KEY) - A DevTools performance trace
- A live URL plus the
chrome-devtoolsMCP server configured in the harness (the agent can capture metrics directly vialighthouse_auditandperformance_*tools) - The Chrome DevTools MCP CLI invoked locally (via
npx -p chrome-devtools-mcp chrome-devtools <tool>or afternpm i -g chrome-devtools-mcp) — the user runs commands likechrome-devtools lighthouse_audit --output-format=jsonand passes the JSON output to the agent
Quick mode — default when none of the above are available. The agent scans source code for structural anti-patterns and labels every finding as potential impact.
Run the audit
Spawn the web-performance-auditor subagent. Pass it explicitly:
- The files, components, or diff under review
- Any artifact paths (Lighthouse JSON, PSI JSON, CrUX response, trace) or pasted JSON content
- The target URL or page name when known
- A note on which mode you expect (Quick or Deep), so the agent surfaces missing inputs if Deep was intended
The subagent returns a scorecard (only populated with sourced values), a ranked list of findings, positive observations, and proactive recommendations.
Output
Return the full audit report to the user. No synthesis or merge step is needed — this is a single-persona command.
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.
- 2d ago First seen · 33 lines · 13 tokens per session scan A 74c0c1335f13
webperf is a command published in the GitHub repository Ghosteken/agent-harness (2 stars, last pushed 16d ago), licensed MIT. It adds 13 tokens to every session and 448 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to webperf, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
ads
Manage dev server - start, stop, logs, list (shortcut for dev-server).
snapshot
Capture screenshot + DOM tree + page state + storage in one shot.
storage
Inspect localStorage, sessionStorage, and cookies from the Tauri webview. One-shot read — no writes.
eval
Evaluate a JavaScript expression in the Tauri app's webview.
record
Use when the user wants to record a video of a browser task, create a screen recording, or produce an MP4 demo.
playwright-auth
Use when the user needs to log into a website for browser automation, save auth cookies, or sync browser profiles to cloud.