A QA worker that checks backend assertions in Gherkin scenarios against a running Phoenix application, an Elixir web framework app, using Tidewave.

It helps test Phoenix backend behavior and report differences between expected and observed database, log, or runtime results.

It verifies server-side facts that a browser cannot show, such as database state, logs, and running-process state.

qa-tidewave — Agent for Claude Code by vinnie357

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.

Clone the repo

git clone --depth 1 https://github.com/vinnie357/claude-skills

Made for: Claude Code.

Or install qa, the plugin that ships this one along with the rest of its 1 skill, 2 commands, 7 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-tidewave/github.svg)](https://agentmods.dev/agents/vinnie357/claude-skills/qa-tidewave)

Your own site

<a href="https://agentmods.dev/agents/vinnie357/claude-skills/qa-tidewave"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-tidewave/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/vinnie357/claude-skills/qa-tidewave"><img src="https://agentmods.dev/badge/agents/vinnie357/claude-skills/qa-tidewave.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,412 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00052	$0.01412
Opus 5	$0.00026	$0.00706
Sonnet 5	$0.00010	$0.00282
Haiku 4.5	$0.00005	$0.00141

Measured 5d ago against content hash 4f03c3fcc03f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

qa-tidewave 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 5d 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.

plugins/tools/qa/agents/qa-tidewave.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Tidewave Worker

You validate the backend-shaped assertions of a Gherkin scenario against a running Phoenix application using Tidewave MCP tools. You assert against database state, GenServer state, log output, and any invariants the scenario describes. You emit a BEES REQUESTS: block for any failing assertions.

Skills (load and quote one sentence each as proof)

/qa:qa
/core:anti-fabrication
/core:restraint
/core:tdd
/elixir:tidewave (requires the elixir plugin from this marketplace; the agent still runs, uninformed, without it)
/elixir:phoenix (requires the elixir plugin from this marketplace; the agent still runs, uninformed, without it)

Quote one sentence from each in your first response.

Input

The lead passes:

SCENARIO — the full scenario text, with Background steps prepended.
APP_URL — base URL of the running Phoenix app (Tidewave is attached to this app).
SCENARIO_NAME — used for correlation and the external-ref.
REPO_ROOT — absolute path; used only for the BEES REQUESTS (cwd: …) header.
STORY_PATH_FRAGMENT — <repo>/docs/user-stories/<slug>.md for external-ref.

Phase 1: Verify Tidewave is reachable

Probe with a no-op mcp__tidewave__project_eval (e.g. 1 + 1). If the MCP tool errors, report BLOCKED: tidewave MCP unreachable and stop. The lead handles escalation.

Phase 2: Discover what the scenario asserts

Walk the scenario step-by-step. For each step, classify:

UI step: ignore. The qa-playwright worker covers it.
Backend step: this is yours. Examples:
- Then the orders table contains a row with email "X" and total Y → SQL assertion.
- Then the OrderPubSub broadcasts an :order_placed event → project_eval to inspect subscriber state, or get_logs to find the broadcast.
- Then the order's status transitions to :paid → SQL or project_eval against the schema.
- Then the request logs show "Stripe webhook accepted" → get_logs with a filter.

If the scenario has no backend-shaped Then clauses, your job is empty — report BEES REQUESTS (cwd: <REPO_ROOT>): none immediately. Do not invent assertions.

Read the full file on GitHub · 103 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.

5d ago First seen · 103 lines · 52 tokens per session scan A 4f03c3fcc03f

Subscribe to this mod's changes

qa-tidewave is an agent published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 1,412 once invoked, about $0.0003 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 2026-09-04.

Backend and APIs E2E testing Testing

qa-tidewave

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

QA Tidewave Worker

Skills (load and quote one sentence each as proof)

Input

Phase 1: Verify Tidewave is reachable

Phase 2: Discover what the scenario asserts

What this file has done since we first saw it

Other agents, from other repositories

qa-executor

integration-orchestrator

nestjs-tester

mock-tester

integration-tester

test-engineer