Borrowing it
Nothing to install: this file belongs to garoon/garoon-mcp-server. 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/garoon/garoon-mcp-server/main/.claude/skills/smoke-test-mcp-tools/SKILL.mdgit clone --depth 1 https://github.com/garoon/garoon-mcp-serverWrote 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/garoon/garoon-mcp-server/smoke-test-mcp-tools)<a href="https://agentmods.dev/skills/garoon/garoon-mcp-server/smoke-test-mcp-tools"><img src="https://agentmods.dev/badge/skills/garoon/garoon-mcp-server/smoke-test-mcp-tools/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/garoon/garoon-mcp-server/smoke-test-mcp-tools"><img src="https://agentmods.dev/badge/skills/garoon/garoon-mcp-server/smoke-test-mcp-tools.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 | $0.00096 | $0.01581 |
| Opus 5.5 | $0.00038 | $0.00632 |
| Sonnet 5.5 | $0.00019 | $0.00316 |
| Haiku 4.5 | $0.00010 | $0.00158 |
Grade A, and why
smoke-test-mcp-tools 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 21d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Garoon MCP tool smoke test
Purpose
Verify that every tool of the Garoon MCP server under development executes without
error against a live Garoon environment. For each tool, the agent derives a
sample-prompt-equivalent input, actually invokes the corresponding mcp__garoon__*
tool, and judges the result. This is a live smoke test (real API calls), not a
static argument-validation check.
Prerequisites
.envrc(gitignored) exportsGAROON_BASE_URL,GAROON_USERNAME,GAROON_PASSWORD, and any optional variables (proxy, PFX, basic auth,GAROON_PUBLIC_ONLY). See CONTRIBUTING.md for the setup.- direnv has loaded those variables into the
claudeprocess environment (direnv allowwas run andclaudewas started from the repository root). dist/is up to date (pnpm run build).- The
garoonserver from.mcp.jsonis connected in Claude Code (claude mcp listshowsgaroonas✔ Connected). - The current user has an event in the search range with at least one comment, preferably including a mention. Garoon provides no REST API for posting comments, so write them manually in the Garoon UI beforehand.
Changing .mcp.json, env vars, or the build usually requires reconnecting
(restarting the Claude Code session). If no mcp__garoon__* tools are visible,
satisfy the prerequisites above and reconnect before retrying.
Procedure
Step 0: Readiness check
- Confirm
dist/is current; runpnpm run buildif unsure. - Enumerate the available
mcp__garoon__*tools. If none exist, return to the prerequisites. - Do not hardcode the tool list. Target whatever
mcp__garoon__*tools are enumerable at runtime, so newly added tools are covered without editing this skill.
Sample-prompt generation
For each tool, derive one natural sample prompt from its title / description /
inputSchema, record it in the report, and call the tool with arguments that
satisfy that intent (e.g. garoon-get-current-time → "What is the current time in
Garoon?").
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.
- 21d ago Changed · +8 lines 8b6ce89cdb95
- 1mo ago First seen · 127 lines · 96 tokens per session scan A dd897b6fcf82
smoke-test-mcp-tools is a skill published in the GitHub repository garoon/garoon-mcp-server (10 stars, last pushed today), licensed Apache-2.0. It adds 96 tokens to every session and 1,581 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
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…
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
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.