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 skills/aemsites/author-kit/performance-reviewnpx skills add aemsites/author-kit --skill performance-reviewgit clone --depth 1 https://github.com/aemsites/author-kitWhat 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 | $0.00066 | $0.02331 |
| Opus 5 | $0.00033 | $0.01166 |
| Sonnet 5 | $0.00013 | $0.00466 |
| Haiku 4.5 | $0.00007 | $0.00233 |
Grade A, and why
performance-review scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
const data = fetch(url).then((r) => r.json()); // started, not awaited How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance review
This project is buildless and every line ships. Regressions here are not slow functions — they are bytes and requests added before first paint, and work hoisted ahead of the lifecycle stage that should own it.
This skill analyses; it does not measure. Lighthouse against a proxied dev server produces numbers that are not the published numbers, and every check below is decidable from source.
Report findings. Do not fix them unless asked.
The lifecycle — what already happens, in order
| # | Where | What runs | Network |
|---|---|---|---|
| 1 | scripts.js top level |
setConfig, then top-level await loadPage() |
no |
| 2 | loadArea → decorateSession / decorateDoc (document only) |
header mode, template metadata, stored colour scheme, hash → localStorage |
no |
| 3 | decoratePictures |
adds the 3000px source to picture:has([loading]) |
no |
| 4 | config.decorateArea hook |
project-specific; today eager-loads the first image | no |
| 5 | decorateSections |
.section wrapping, child regrouping, decorateLinks |
no |
| 6 | section loop, per section | loadIcons, then link blocks, then div blocks, then section-metadata |
yes — dynamic import per block, parallel within a phase, sections awaited in order |
| 7 | after section 0 | postlcp.js (loads the header block), deps/rum.js |
deferred |
| 8 | after all sections | lazy.js → lazyhash, favicon, footer, author tools in non-prod |
deferred, post-paint |
Steps 1–5 are synchronous and block the first section. Anything added there delays every paint on every page.
Parallelise with purpose
Awaited and unawaited async are both deliberate here. The pattern is consistent once you see it:
- The LCP image and the first section's blocks race — same paint, so concurrency costs nothing and finishing sooner helps.
- Blocks within a section run concurrently — all of them are needed for that section to render.
- Sections are awaited one at a time — section 3's blocks racing section 0's would saturate bandwidth and delay LCP for content nobody can see yet.
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 · 188 lines · 66 tokens per session scan A 54b2110c0273
performance-review is a skill published in the GitHub repository aemsites/author-kit (12 stars, last pushed 20d ago), licensed Apache-2.0. It adds 66 tokens to every session and 2,331 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…