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 JansenAnalytics/claudex --skill perf-profilergit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/jansenanalytics/claudex/perf-profiler)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/perf-profiler"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/perf-profiler.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 5.1 | $0.00040 | $0.00997 |
| Opus 5 | $0.00020 | $0.00498 |
| Sonnet 5 | $0.00008 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00100 |
Grade A, and why
perf-profiler 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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
perf-profiler — Runtime Performance Analysis
Performance profiling beyond Lighthouse: bundle analysis, memory leak detection, load testing, resource analysis, and runtime CPU profiling.
Quick Start
perf-profiler bundle ./dist # Bundle size analysis
perf-profiler resources https://example.com # Resource loading analysis
perf-profiler loadtest https://api.example.com --concurrency 20 --duration 30
perf-profiler memory https://app.example.com --iterations 10
perf-profiler runtime https://app.example.com --duration 10 --interaction scroll
perf-profiler review https://app.example.com --build-dir ./dist --full
Scripts
bundle.cjs — Bundle Size Analyzer
Analyzes JS/CSS files in build output. Reports per-file + gzipped sizes, detects heavy packages (moment→dayjs, lodash→lodash-es), parses source maps for package-level treemap.
node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/perf-profiler/scripts/bundle.cjs <build-dir> [--source-maps]
Output: bundle-analysis.json
memory.cjs — Memory Leak Detector
Uses Playwright to navigate a page repeatedly, measuring heap size after each iteration. Linear regression detects consistent growth.
node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/perf-profiler/scripts/memory.cjs <url> [--iterations 10] [--actions flow.json]
Custom actions JSON format:
[{"action":"click","selector":"button.open"},{"action":"wait","ms":500},{"action":"click","selector":"button.close"}]
loadtest.cjs — HTTP Load Tester
Zero-dependency concurrent load tester. Measures p50/p95/p99 latency, req/s, error rate.
node ${CLAUDE_SKILLS_DIR:-$HOME/.claude-agent/.claude/skills}/perf-profiler/scripts/loadtest.cjs <url> \
[--concurrency 10] [--duration 30] [--requests 1000] [--ramp] \
[--method POST] [--body '{"key":"val"}'] [--header "Content-Type: application/json"]
resources.cjs — Resource Analysis
Monitors all network requests via CDP. Finds render-blocking resources, oversized images, unused CSS, uncompressed assets, third-party audit.
What ships with it
14 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.
- INSTALL.md 806 B
- references/node-profiling.md 1.6 KB
- references/perf-anti-patterns.md 1.1 KB
- references/python-profiling.md 1.4 KB
- scripts/benchmark.sh 3.1 KB runs code
- scripts/bundle.cjs 8.1 KB runs code
- scripts/loadtest.cjs 7.6 KB runs code
- scripts/memory-tracker.py 3.3 KB runs code
- scripts/memory.cjs 6.5 KB runs code
- scripts/node-profiler.sh 2.4 KB runs code
- scripts/report.cjs 6.0 KB runs code
- scripts/resources.cjs 10 KB runs code
- scripts/review.cjs 3.0 KB runs code
- scripts/runtime.cjs 7.7 KB runs code
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.
- 4d ago First seen · 100 lines · 40 tokens per session scan A 5dc56932ab78
perf-profiler is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 40 tokens to every session and 997 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
moli-webfetch
Fetch, inspect, crawl, and capture live, JavaScript-rendered websites with Moli. Use when Codex needs current web content, web research, fact lookup, link following, a bounded crawl, client-rendered or response-gated content, network diagnostics, or a standalone HTML, Markdown, JSON, semantic-tree, viewport or…
moli-cdp-server
Start Moli's CDP server and connect Playwright, Puppeteer, or raw CDP clients. Use to run a headless-browser CDP endpoint, replace a Chromium process, attach over CDP, enable real layout and screenshot surfaces, or diagnose CDP discovery, connection, and target startup—even when Moli is not named.
Flaky Test Doctor
Diagnose flaky test failures from Playwright reports, traces, and rerun history. Classify each failure as product, test, environment, data, or unknown with cited evidence and a proposed fix. Never auto-modifies code without opt-in.
performance
Use when a page or interaction is slow for one user and the fix starts from a measurement — a failing Core Web Vital (LCP, INP, CLS), a heavy JS bundle, wasted re-renders, an over-broad client boundary: profile, attribute the cost to one phase, fix it, re-measure. NOT surviving concurrent load (that is scaling), NOT…
cypress-debugger
Use when a Cypress end-to-end test has already run and failed and the user wants the root cause and a concrete fix. Trigger on a failing Cypress spec, Timed-out-retrying command, unresolved selector, cy.intercept alias or request race, suite-breaking hook, retry-only flake, hydration or timing race, or a…
playwright-debugger
Use when a Playwright end-to-end test has already run and failed and the user wants the root cause and a concrete fix. Trigger on a failing Playwright spec, TimeoutError, broken or ambiguous selector, post-deploy suite failure, retry-only flake, hydration or timing race, or a passes-locally-but-fails-in-CI split.…