Borrowing it
Nothing to install: this file belongs to karthikcsq/google-tools-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/karthikcsq/google-tools-mcp/main/.agents/skills/live-testing/SKILL.mdgit clone --depth 1 https://github.com/karthikcsq/google-tools-mcpWrote 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/karthikcsq/google-tools-mcp/live-testing)<a href="https://agentmods.dev/skills/karthikcsq/google-tools-mcp/live-testing"><img src="https://agentmods.dev/badge/skills/karthikcsq/google-tools-mcp/live-testing/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/skills/karthikcsq/google-tools-mcp/live-testing"><img src="https://agentmods.dev/badge/skills/karthikcsq/google-tools-mcp/live-testing.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 | $0.00050 | $0.00710 |
| Opus 5.5 | $0.00020 | $0.00284 |
| Sonnet 5.5 | $0.00010 | $0.00142 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
live-testing 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 10d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live testing
Use this skill when the question is whether a real MCP client can complete a goal, rather than whether a tool implementation passes a known assertion.
Choose the mode before you run anything:
- Regression smoke runs the existing in-process scenarios. It verifies behavior already encoded in
live/; its static coverage output is scenario presence, not measured successful API coverage. Read regression smoke. - Interactive agent test gives a source-blind tester an outcome, then drives the same MCP transport and session state that a client uses. It is the required mode for a fresh-agent usability verdict. Read interactive sessions and use the tester brief.
Interactive loop
- Start an owned session with
npm.cmd run agent-test -- start ...; retain the JSON manifest path it prints. - Search with
list --search <keywords>, thendescribethe candidates before calling them. Use fulllistonly when broad inventory is useful. Do not inspect source or give the tester implementation hints. - Record each unexpected error, retry, ambiguity, or workaround with
frictioneven if the goal is eventually reached. For an intentional negative call, add--expected-negative "reason"to thatcallcommand before it runs. - Read
statusand the generated report/artifacts directly. Exit status alone is never the verdict. - Fix the discovered product or documentation issue, run the applicable regression, then repeat with a fresh source-blind tester. Default to at most three repair iterations; report the unresolved blocker after that bound.
An interactive test passes only when the tester explicitly finishes pass, has meaningful successful calls, no unexpected failures or friction, and the report shows cleanup and session health are clean. Unsupported offline behavior is blocked, never a pass. The live backend remains deliberately bounded and cannot establish E2E behavior for every tool.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 37 lines · 50 tokens per session scan A 819efd97b210
live-testing is a skill published in the GitHub repository karthikcsq/google-tools-mcp (9 stars, last pushed 10d ago), licensed MIT. It adds 50 tokens to every session and 710 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 2026-10-20.
Other skills, from other repositories
ios-app-tester
Test iOS apps using AXe CLI for accessibility auditing, UI automation, and simulator control. Use when testing iOS Simulator apps, automating UI interactions, recording test videos, or auditing accessibility labels and VoiceOver support.
playwright-browser
Use when automating browsers, testing pages, taking screenshots, checking UI, verifying login flows, or testing responsive behavior.
verification
Full-story verification — infers what the user is building, then verifies the complete flow end-to-end: browser → API → data → response. Triggers on dev server start and 'why isn't this working' signals.
agent-browser-verify
Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass/fail before continuing.
flutter-testing-apps
Implement unit, widget, and integration tests for a Flutter app. Use for code quality and regression prevention.
benchmark-e2e
End-to-end benchmark suite for vercel-plugin. Runs realistic projects through skill injection, launches dev servers, verifies everything works, analyzes conversation logs, and produces an improvement report for overnight self-improvement loops.