wake-performance-review

A performance-check workflow for Wake Commerce online stores. It examines GraphQL requests, caching, images, and Core Web Vitals—the loading and responsiveness measures used by browsers.

In plain words
What is it for?
Use it to measure a live or local page, compare results with an earlier run, and prioritize fixes for GraphQL, caching, images, and loading speed.
Why use it?
It helps find the changes making a storefront slow, such as requesting unnecessary data, missing cache entries, oversized images, or delayed page interaction.

Command

Install

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.

agentmods
npx agentmods add commands/wake-engineering/ai-plugin/wake-performance-review
Clone the repo
git clone --depth 1 https://github.com/wake-engineering/ai-plugin
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 841 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.00841
Opus 5 $0.00024 $0.00420
Sonnet 5 $0.00010 $0.00168
Haiku 4.5 $0.00005 $0.00084

Measured yesterday against content hash 3671f96a111f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wake-performance-review 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 yesterday.

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.

commands/wake-performance-review.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wake Performance Review Workflow

Forbidden: api.fbits.net (and any *.fbits.net). Canonical source: https://wakecommerce.readme.io/docs/schema (for Wake API references).

Diagnose and prioritize performance issues on a Wake Commerce storefront: GraphQL waste, cache misses, image regressions, and Core Web Vitals (LCP / INP / CLS).

Inputs

  • Target (required): URL of the deployed storefront page, or local route + dev-server port. Examples: https://shop.example.com/p/sneaker-x, http://localhost:3000/search?q=shoes.
  • Page type (optional): home, category, search, PDP, cart, checkout. Defaults inferred from the URL.
  • Device profile (optional): mobile (default) or desktop. Throttling: 4× CPU, Slow 4G for mobile.
  • Baseline (optional): a prior Lighthouse run / CrUX snapshot to diff against.

Steps

  1. Establish baselines. Capture LCP, INP, CLS, TBT, TTFB, and total bytes via the web-performance-audit skill (Chrome DevTools MCP lighthouse_audit + performance_start_trace). Record three runs and use the median.
  2. GraphQL shape audit. Open Network → GraphQL. For each operation: confirm only required fields are selected, fragments are reused (SingleProductData, checkoutFields), and there are no N+1 patterns (e.g., a product list followed by per-product detail fetches). Flag operations >150 KB response or >500 ms server time.
  3. Caching strategy. Inspect Apollo / React Query cache config: keys (productById, search), TTL per partner, and invalidation triggers on checkout state changes. Check CDN headers (cache-control, vary) on static and API routes.
  4. Images. Confirm imageUrl is requested with explicit w/h (no oversized originals), loading="lazy" is set below the fold, and modern formats (WebP/AVIF) are served via <picture> or Accept-based negotiation.
  5. Core Web Vitals deep-dive.
    • LCP: identify the LCP element; verify it is server-rendered, preloaded, and not blocked by JS hydration.
    • INP: profile interactions on the slowest button/link; flag long tasks > 50 ms during user input.
    • CLS: verify reserved space for images, ads, and async-loaded modules.
  6. JS payload. Bundle analyzer pass: flag duplicate libraries, polyfills shipped to modern browsers, and route-level chunks > 200 KB gzipped.
  7. Server / edge. TTFB > 600 ms? Check origin distance, SSR work, and uncached GraphQL fan-out.
  8. Delegate analysis. Hand the captured traces and findings to the wake-performance-engineer agent for prioritized remediation, performance budget recommendations, and an optimization roadmap.

Read the full file on GitHub · 46 lines

Changes

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.

  1. yesterday First seen · 46 lines · 49 tokens per session scan A 3671f96a111f

Subscribe to this mod's changes

wake-performance-review is a command published in the GitHub repository wake-engineering/ai-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 49 tokens to every session and 841 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 2026-08-31.

Related

Other commands, from other repositories