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 Harshvardhan86/claude-wave-plugin --skill teet-verifygit clone --depth 1 https://github.com/Harshvardhan86/claude-wave-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/skills/harshvardhan86/claude-wave-plugin/teet-verify)<a href="https://agentmods.dev/skills/harshvardhan86/claude-wave-plugin/teet-verify"><img src="https://agentmods.dev/badge/skills/harshvardhan86/claude-wave-plugin/teet-verify.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 | $0.00047 | $0.01085 |
| Opus 5 | $0.00023 | $0.00543 |
| Sonnet 5 | $0.00009 | $0.00217 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
teet-verify 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 8d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TEET — True End-to-End Testing
TEET is the final phase. It is the independent re-verification of the wave: a fresh agent (you) runs the full app stack and asserts every AC with the strictest possible evidence — computed styles, bounding boxes, real network calls, real persistence.
Why this is its own phase
GREEN's job is to make tests pass. TEET's job is to distrust GREEN and re-verify against the original AC. The same agent that wrote the implementation cannot reliably grade it. Lean, dedicated context per phase is the rule.
Pre-condition
The orchestrator only invokes you after the user typed approval of the GREEN screenshot. If you're invoked without that, refuse and tell the orchestrator to gate.
Inputs
.wave/ac.md.wave/dr.md.wave/green.md.wave/screenshots/green-*.png
Procedure
1. Bring up the entire stack
- Frontend, backend, DB, queues, external service emulators if used
- Use the project's documented startup procedure (do not invent one)
- Wait until every service reports healthy
2. Walk every route, click every interactive element
For multi-step flows (wizards, onboarding, dashboards):
- Click through the entire flow end-to-end with Playwright
- Take a screenshot at every step, save to
.wave/screenshots/teet-step-N-<route>.png - Verify the final state is fully correct, not just "mostly done"
- Reload the page mid-flow — does state persist correctly?
- Click every button, link, toggle and verify its observable effect
3. Computed-style and boundingBox assertions
For every visual AC from DR:
- Assert with
getComputedStyle()nottoBeVisible() - Assert with
boundingBox()for sizes and positions - Compute total effective CSS bytes for the route — if below a project-set threshold, flag (the page is unstyled)
- Compare each route screenshot against a known-good reference if one exists (e.g., the previous successful wave's screenshot)
4. Cross-system assertions
For ACs that span systems (e.g., "toggle dark mode → persisted in DB → visible after fresh login"):
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.
- 8d ago First seen · 114 lines · 47 tokens per session scan A 253a21bae62f
teet-verify is a skill published in the GitHub repository Harshvardhan86/claude-wave-plugin (8 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 1,085 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 skills, from other repositories
fec-tdd-workflow
A frontend test-driven development workflow, or TDD, describes the expected behavior with a failing test, implements the smallest change to pass it, and then refactors. It covers UI components, hooks, API clients, route guards, and user workflows.
e2e-generate
Create or update end-to-end tests for a user-facing flow that changed, using whatever e2e framework the repo already uses. Use after implementing a user story that alters UI behavior, routing, forms, or API-driven views.
Component Test Scaffold (Next.js)
Generate React/Next.js component test skeletons (RTL) from specifications.
Component Test Scaffold (Vue.js)
Generate Vue.js component test skeletons (Vue Test Utils) from specifications.
Component Test Scaffold (React)
Generate generic React component test skeletons (RTL) from specifications.
Route/Function Test Scaffold (Remix)
Generate Remix loader/action and route component test skeletons.