Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/genudo-ai/genudo_mcpnpx agentmods add skills/genudo-ai/genudo_mcp/setup-testing-engineWrote 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/genudo-ai/genudo_mcp/setup-testing-engine)<a href="https://agentmods.dev/skills/genudo-ai/genudo_mcp/setup-testing-engine"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/setup-testing-engine/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/genudo-ai/genudo_mcp/setup-testing-engine"><img src="https://agentmods.dev/badge/skills/genudo-ai/genudo_mcp/setup-testing-engine.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 | $0.00091 | $0.01086 |
| Opus 5.5 | $0.00036 | $0.00434 |
| Sonnet 5.5 | $0.00018 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00109 |
Grade B, and why
setup-testing-engine scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`sudo apt-get install -y python3 python3-venv git`; `winget install Python.Python.3.12 Git.Git`) How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up Testing Engine
Get genudo-agent-testing-engine ready to run, then prove it with a dry run. Nothing here
sends a message or creates a lead.
1. Check the machine
Run and report versions:
- Python 3.9+:
python3 --version(Windows:py -3 --version) - Git:
git --version - Judge CLI (at least one, optional):
claude --version(Claude subscription) orcodex --version(ChatGPT subscription). The judge uses the user's AI subscription, never an API key. With neither, tests still run with deterministic checks only.
Missing Python or Git → give the platform's install command (brew install python git;
sudo apt-get install -y python3 python3-venv git; winget install Python.Python.3.12 Git.Git)
and wait for the user rather than installing silently.
2. Get the engine
Clone it inside the client's folder (the folder Claude was opened in). In a client
folder that already connects Genudo with a token — a .mcp.json whose genudo server sends
Authorization: Bearer …, as loredex workspace creates — the engine reuses that token
automatically, so each client's runs use that client's account.
git clone https://github.com/genudo-ai/genudo-agent-testing-engine.git
cd genudo-agent-testing-engine
python3 setup_env.py # creates .venv, installs requirements, copies .env.example to .env
If the folder already exists, git pull instead.
3. Configure .env
GENUDO_TOKEN— skip this in a client folder whose.mcp.jsonalready carries a token; the engine prints[config] Using the GenuDo token from …/.mcp.jsonwhen it reuses it. Only if that token is rejected on a write (401/403 on the first live run), or the folder connects through browser sign-in instead, set one here: a bearer token the engine uses for both the MCP endpoint and the REST calls that create test opportunities and send test messages. The user creates it in the Genudo console: Developer → API Keys & Tokens → Create token, withmcp:useplus the opportunity, conversation, and message write scopes. It is shown once. The token goes in.envonly — never in chat, the suite, or a commit. This is separate from the plugin's browser sign-in.GENUDO_PIPELINES— channel-to-pipeline map, e.g.messenger=<id>,whatsapp=<id>. Look the IDs up withlist_pipelines. Point at a staging or duplicate pipeline first: runs create real opportunities and let the agent fire its real webhooks.GENUDO_ENV— leavedev.prodrefuses to run without--allow-prod.GENUDO_JUDGE—claude,codex, oroff; unset auto-detects.
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 · 81 lines · 91 tokens per session scan B 32680c1bd2c7
setup-testing-engine is a skill published in the GitHub repository genudo-ai/genudo_mcp (0 stars, last pushed 6d ago), licensed MIT. It adds 91 tokens to every session and 1,086 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-11.
Other skills, from other repositories
playwright-browser
Use when automating browsers, testing pages, taking screenshots, checking UI, verifying login flows, or testing responsive behavior.
local-e2e
A skill for running end-to-end tests against a local LeadAce application stack. End-to-end tests check complete user flows across the running application, rather than only testing individual pieces.
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work — render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.