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 commands/wake-engineering/ai-plugin/wake-performance-reviewgit clone --depth 1 https://github.com/wake-engineering/ai-pluginWhat 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 | $0.00049 | $0.00841 |
| Opus 5 | $0.00024 | $0.00420 |
| Sonnet 5 | $0.00010 | $0.00168 |
| Haiku 4.5 | $0.00005 | $0.00084 |
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.
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
- 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. - 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. - 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. - Images. Confirm
imageUrlis requested with explicitw/h(no oversized originals),loading="lazy"is set below the fold, and modern formats (WebP/AVIF) are served via<picture>orAccept-based negotiation. - 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.
- JS payload. Bundle analyzer pass: flag duplicate libraries, polyfills shipped to modern browsers, and route-level chunks > 200 KB gzipped.
- Server / edge. TTFB > 600 ms? Check origin distance, SSR work, and uncached GraphQL fan-out.
- Delegate analysis. Hand the captured traces and findings to the wake-performance-engineer agent for prioritized remediation, performance budget recommendations, and an optimization roadmap.
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.
- yesterday First seen · 46 lines · 49 tokens per session scan A 3671f96a111f
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.
Other commands, from other repositories
merge
Finalize work on a branch: verify docs + tree are clean, merge to main, clean up. Supports both standard git checkout -b branches and git worktree flows — auto-detected at pre-flight.
expect
Diff-aware AI browser testing — reads the git diff, maps changes to affected pages via the route map, generates a targeted test plan, and executes it via agent-browser (Rust daemon + CDP, ARIA-tree-first) with pass/fail reporting. Use when testing UI changes, verifying PRs before merge, or running regression checks on…
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
dev
Runs Vendure in development mode. By default it starts three processes: the GraphQL server (ts-node ./src/index.ts), the worker (ts-node ./src/index-worker.ts), and the dashboard (a Vite dev server).
start
Runs a project that has already been compiled with vendure build.
pipeline-undo
Undo a pipeline run's result. With worktree isolation (the current engine), this is clean and low-risk: a run never touches your checkout — its result lives only on a pipeline/ branch (and, for a --push run, on the remote). "Undo" therefore means deleting that branch and its worktree, not reverting your working tree.