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 red-testsgit 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/red-tests)<a href="https://agentmods.dev/skills/harshvardhan86/claude-wave-plugin/red-tests"><img src="https://agentmods.dev/badge/skills/harshvardhan86/claude-wave-plugin/red-tests.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 | $0.00045 | $0.00829 |
| Opus 5 | $0.00023 | $0.00415 |
| Sonnet 5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
red-tests 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 6d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RED Tests
You write tests first, watch them fail, then hand off. No production code. No exceptions. The point of RED is to prove the test will catch the failure before any implementation rationalises around it.
Why this skill exists
When implementation and tests are written together, the agent silently shapes the test to match what was easy to build. The feature ends with passing tests and broken behaviour. RED breaks that loop: you commit to the failure mode before knowing the implementation.
Inputs
.wave/ac.md.wave/dr.md(especially the visual ACs section)
Procedure
1. Map ACs to tests
For each AC, write at least one test. For visual ACs from DR, the test must use:
getComputedStyle()for color, font, spacing, border, transform valuesboundingBox()for size and position assertions- Real browser (Playwright preferred) — not jsdom, not happy-dom — for any visual claim
- Effective CSS bytes comparison if the AC includes "the page is styled"
2. Banned assertion patterns (when used alone)
These pass on broken UIs and are forbidden as the only assertion in a visual test:
toBeVisible()— passes on 0×0 elementscustomElements.get(X) !== undefined— registration ≠ renderingnot.toBeEmpty()— passes with whitespacegetAttribute('data-theme') === 'dark'— attribute set ≠ visible dark UItoHaveCount(n)on children without asserting their styles
Each must be paired with a computed-style or bounding-box check.
3. Write the tests
Place tests where the project conventions dictate (tests/, e2e/, __tests__/, *.spec.ts). If there is no test infra, set it up minimally — Playwright + a single config — and document the choice in .wave/red.md.
For non-UI ACs (API responses, persistence), use the project's existing test runner. Same rule: assertion must encode the AC, not the implementation.
4. Prove they fail
Run the test suite. The new tests must fail. Capture the failure output.
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.
- 6d ago First seen · 79 lines · 45 tokens per session scan A 9737029c0281
red-tests is a skill published in the GitHub repository Harshvardhan86/claude-wave-plugin (8 stars, last pushed 3mo ago), licensed MIT. It adds 45 tokens to every session and 829 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
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the failing test first and watch it fail for the right reason.
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
testing-principles
Language-agnostic testing principles including TDD, test quality, coverage standards, and test design patterns. Use when writing tests, designing test strategies, or reviewing test quality.
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
workflow
Run the complete 5-step development workflow: focus problem → prevent over-development → test-first (TDD) → document → smart commit. Use when starting a new feature, or when the user runs /workflow or asks for the full development flow.
test-first
Drive one feature through a strict TDD Red-Green-Refactor cycle with checklists for each phase. Use when implementing new functionality test-first, or when the user runs /test-first.