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 skills add tahirraufkeeyu/software-development-agent-stack--sdas --skill performance-testgit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/performance-test)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/performance-test"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/performance-test/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/skills/tahirraufkeeyu/software-development-agent-stack--sdas/performance-test"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/performance-test.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 | $0.00071 | $0.02029 |
| Opus 5.5 | $0.00028 | $0.00812 |
| Sonnet 5.5 | $0.00014 | $0.00406 |
| Haiku 4.5 | $0.00007 | $0.00203 |
Grade A, and why
performance-test 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.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Invoke this skill when:
- A release candidate URL needs to be gated on Core Web Vitals thresholds.
- A reported regression ("home page feels slow") needs quantified data.
- A new feature ships a heavyweight component and you need to check its cost.
- You need a mobile vs. desktop comparison on an identical route.
Do NOT use when: the target needs auth you cannot provide to Chrome DevTools; you need multi-hour RUM-style measurement (this skill is lab-based, not field-based); you need a load test against the origin (outside scope).
Inputs
url(required): Fully qualified URL including path.form_factor(optional):mobileordesktop. Defaultmobile(matches CrUX reporting).throttling(optional):simulated-3g,applied-4g,none. Defaultsimulated-3gfor mobile,nonefor desktop.runs(optional): Number of Lighthouse runs; report median. Default3.budget(optional): JSON of metric thresholds; defaults to CWV "good" perreferences/web-vitals-thresholds.md.auth_cookie(optional): Session cookie set before audit for gated routes.
Outputs
- A Markdown audit report including:
- Metric table (LCP / INP / CLS / TTFB / FCP) with value, threshold, verdict.
- Top 5 opportunities from Lighthouse with estimated savings.
- Long-task list (name, duration, source) from the trace.
- Render-blocking resources with suggested remediation.
- A prioritized fix list (P0/P1/P2) keyed to the worst-offender metric.
- A raw trace file path (saved via DevTools MCP) for engineers to open in Chrome.
Tool dependencies
mcp__chrome-devtools__new_page,mcp__chrome-devtools__navigate_page,mcp__chrome-devtools__emulate(for form factor).mcp__chrome-devtools__lighthouse_audit(core Lighthouse run).mcp__chrome-devtools__performance_start_trace,mcp__chrome-devtools__performance_stop_trace,mcp__chrome-devtools__performance_analyze_insight.mcp__chrome-devtools__list_network_requestsfor render-blocking analysis.Writefor the report.references/web-vitals-thresholds.mdfor thresholds and fix playbook.
What ships with it
1 file 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.
- 1mo ago First seen · 140 lines · 71 tokens per session scan A bb40d1b5b6c0
performance-test is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (19 stars, last pushed 5mo ago), licensed MIT. It adds 71 tokens to every session and 2,029 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
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.
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".
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.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.