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 arozumenko/sdlc-skills --skill performance-auditgit clone --depth 1 https://github.com/arozumenko/sdlc-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/skills/arozumenko/sdlc-skills/performance-audit)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/performance-audit"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/performance-audit/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/arozumenko/sdlc-skills/performance-audit"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/performance-audit.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 | $0.00040 | $0.00643 |
| Opus 5.5 | $0.00016 | $0.00257 |
| Sonnet 5.5 | $0.00008 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
performance-audit 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance, Network & Console Analysis
Three analysis passes:
- Performance 📡 — load/resource health, network issues
- Console 🖥️ — runtime errors, warnings, CSP violations
- JavaScript ⚡ — async issues, memory leaks, deprecated APIs
Data Sources
Performance uses browser_network_requests():
- Request/response status, resource types and (where reported) sizes
- 4xx/5xx requests, CORS failures, timeouts
Console uses browser_console_messages(level:"error") (also run with
level:"warning" for the Console pass).
Limitation: the factory's Playwright MCP toolset has no browser_evaluate,
so there is no reliable way to read performance.getEntriesByType or compute
full Core Web Vitals (LCP, CLS, INP, FCP, TTFB) in this environment. Do not
report specific CWV numbers or a Lighthouse-style score. Instead, approximate
load/resource health from browser_network_requests() (request count, resource
sizes where reported, error rate, obviously oversized responses) and from how
long the page visibly took to settle during Step-0 collection. Score confidence
low-to-medium (per the evidence rule in audit-methodology.md) for any
performance finding, and say explicitly that it is an approximation, not a
measured CWV metric.
Performance 📡 — Approximate Thresholds
See references/cwv-thresholds.md for the full CWV/budget reference table (use
it for resource-size and network-error priority mapping; do not cite the CWV
rows as measured values — see Limitation above).
Look for: obviously slow/oversized resources, waterfall bottlenecks visible in the network log, missing caching headers, CORS errors, render-blocking scripts, broken resource URLs.
Console 🖥️ — Focus Areas
Look for: JS errors, deprecated API warnings, CSP violations, failed resource loads, unhandled rejections, compatibility warnings.
Priority: console.error = p1, console.warn = p2, deprecated API = p3.
JavaScript ⚡ — Focus Areas
Look for: uncaught promise rejections, missing error handlers, blocking operations, memory leaks, race conditions, deprecated APIs, failed dynamic imports.
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 · 69 lines · 40 tokens per session scan A 01d7de87add6
performance-audit is a skill published in the GitHub repository arozumenko/sdlc-skills (25 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 643 once invoked, about $0.0002 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.