What is manual-test-run?

A manual quality-assurance test runner for Gherkin scenarios, which are plain-language descriptions of expected software behaviour. It runs the project's prepared cases in a Docker workspace and records the results.

Use it to execute manual test plans, check recommended cases for a code change, and produce a QA run report.

It avoids running cases from the wrong environment or inventing missing setup steps. It also keeps the verdicts and QA report together.

How ameshkov/mcp-compress-router configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to ameshkov/mcp-compress-router. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/ameshkov/mcp-compress-router/master/.agents/skills/manual-test-run/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/ameshkov/mcp-compress-router

Made for: Claude Code, Codex.

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/skills/ameshkov/mcp-compress-router/manual-test-run/github.svg)](https://agentmods.dev/skills/ameshkov/mcp-compress-router/manual-test-run)

Your own site

<a href="https://agentmods.dev/skills/ameshkov/mcp-compress-router/manual-test-run"><img src="https://agentmods.dev/badge/skills/ameshkov/mcp-compress-router/manual-test-run/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/skills/ameshkov/mcp-compress-router/manual-test-run"><img src="https://agentmods.dev/badge/skills/ameshkov/mcp-compress-router/manual-test-run.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,777 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	$0.00038	$0.01777
Opus 5.5	$0.00015	$0.00711
Sonnet 5.5	$0.00008	$0.00355
Haiku 4.5	$0.00004	$0.00178

Measured 1mo ago against content hash baf2723138b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

manual-test-run 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.

.agents/skills/manual-test-run/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running Manual QA Tests

Overview

Run the project's manual Gherkin plans (qa/features/) and record verdicts with the BDD runner (qa/scripts/bdd/). The plans execute inside the QA Docker workspace built from qa/Dockerfile, never from a host checkout. This skill covers only the BDD workflow — enumerating cases, executing them, and producing a report. Every stack detail (fixtures, preparation, and the commands that drive the system under test) lives in qa/README.md.

Prerequisites

The repository contains the manual QA stack: qa/README.md, qa/features/, and qa/scripts/bdd/.
Docker is available: the plans run in the QA workspace built from qa/Dockerfile, not in a host checkout.
Read qa/README.md before executing anything. It is the source of truth for fixtures, setup, and the exact commands and paths the scenarios name. Where this skill and the README disagree, the README wins.
If qa/README.md is missing, STOP: tell the user the manual QA stack is not present in this repository and wait. Do not improvise a setup or reconstruct commands from this skill.

Where things live

qa/features/ — the Gherkin plans, one file per area. A scenario's steps are instructions a tester carries out.
qa/scripts/bdd/ — the BDD runner (enumerate, walk, record) and the @TC-* ID check.
qa/README.md — the technical source of truth: test fixtures (configs, mock servers, router homes, host configs), preparation, and the commands the plans use.
qa/output/<run-id>/ — generated reports (report.json and report.md); gitignored.

When this applies

"Run the manual tests for this change"
"Run the recommended cases" (a list chosen by qa-test-planning)
"Execute <feature> / <case-id>"
"Produce a QA run report"

Step 0 — Prepare the stack

Read qa/README.md and carry out its preparation and preflight exactly as written: build the Compose stack, start it, and open a shell in the workspace container. This skill deliberately does not repeat those commands: when the stack changes, the README is updated with it.

Read the full file on GitHub · 164 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.

1mo ago First seen · 164 lines · 38 tokens per session scan A baf2723138b0

Subscribe to this mod's changes

manual-test-run is a skill published in the GitHub repository ameshkov/mcp-compress-router (21 stars, last pushed 20d ago), licensed MIT. It adds 38 tokens to every session and 1,777 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 2026-09-22.

E2E testing Testing ai mcp mcp-server

flutter-mcp-toolkit-control

Drive a running Flutter app — tap, scroll, type, fill forms, hot-reload, navigate. Use when you need to interact with the UI.

Arenukvern/mcp_flutter · 38 tokens

flutter-mcp-e2e-harness

Use this skill when writing or running repeatable E2E scenarios for Flutter apps as checked-in Dart with the fluttermcpharness package (packages/harness) — build/launch the app, attach to its VM service, drive widgets (snapshot/tap/enter text) and assert without MCP; also covers the repo showcase launcher (make…

Arenukvern/mcp_flutter · 117 tokens

flutter-mcp-cli-runtime-validation

Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime), including toolkit-extension gating, screenshot/layout capture, app error collection, optional reload verification, and retry handling for transient first-connect failures.

Arenukvern/mcp_flutter · 52 tokens

mcp-compress-router: Skill for Claude Code