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.
git clone --depth 1 https://github.com/wake-engineering/ai-pluginWrote 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/commands/wake-engineering/ai-plugin/wake-test-plan)<a href="https://agentmods.dev/commands/wake-engineering/ai-plugin/wake-test-plan"><img src="https://agentmods.dev/badge/commands/wake-engineering/ai-plugin/wake-test-plan/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/commands/wake-engineering/ai-plugin/wake-test-plan"><img src="https://agentmods.dev/badge/commands/wake-engineering/ai-plugin/wake-test-plan.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 | $0.00042 | $0.00714 |
| Opus 5.5 | $0.00017 | $0.00286 |
| Sonnet 5.5 | $0.00008 | $0.00143 |
| Haiku 4.5 | $0.00004 | $0.00071 |
Grade A, and why
wake-test-plan 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wake Test Plan Workflow
Forbidden: api.fbits.net (and any *.fbits.net). Canonical source: https://wakecommerce.readme.io/docs/schema (for Wake API references).
Produce a structured test plan for a Wake Commerce storefront feature: critical-path E2E flows, contract tests against the Storefront API, and Given/When/Then acceptance criteria.
Inputs
- Feature (required): name and short description. Examples: "PDP add-to-cart with variant matrix", "Guest checkout with multiple shipping quotes", "Customer login + order history".
- User roles (optional): guest, logged-in customer, B2B partner. Defaults to guest + logged-in customer.
- Channels (optional): web, mobile web, native. Defaults to web.
- Existing test framework (optional): Playwright, Cypress, Vitest, etc. Defaults to Playwright + Vitest.
Steps
- Scope the feature. Restate it in one sentence and list the user-visible outcomes (what the user can see/do after success).
- Map the user journey. Sketch the happy path as a sequence of screens/actions and the GraphQL operations triggered at each step (
createCheckout,checkoutCustomerAssociate,shippingQuotes, etc.). - Critical-path E2E scenarios. One scenario per role × channel combination. Each scenario lists preconditions, steps, and the assertion that proves success.
- Contract tests. For every Storefront API operation in the journey, lock the query/mutation shape and a representative response fixture. Include negative fixtures (auth error, validation error, server error).
- Edge cases. Empty cart, invalid coupon, out-of-stock variant, expired session, network timeout, partial inventory, region/currency mismatches, concurrent checkout.
- Acceptance criteria. Given/When/Then per scenario. Each criterion must be independently verifiable in CI.
- Test pyramid placement. Tag each item: unit (pure logic, schemas), integration (API client + cache), E2E (browser-level critical paths). Aim for many unit, some integration, few E2E.
- Non-functional checks. Accessibility (WCAG 2.2 AA on the new screens), performance budget (LCP/INP/CLS), and i18n if the feature touches text.
- Delegate detailed design. Hand the outline to the wake-qa-expert agent for full Given/When/Then expansion and fixture authoring.
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 · 47 lines · 42 tokens per session scan A b8c6c36876e4
wake-test-plan is a command published in the GitHub repository wake-engineering/ai-plugin (4 stars, last pushed 13d ago), licensed MIT. It adds 42 tokens to every session and 714 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 2026-08-31.
Other commands, from other repositories
playwright-test-heal
Run all my tests and fix the failing ones.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
verify-pr
Verify a PR's frontend changes through browser automation.
test-run
Run E2E tests with qa-use CLI.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.