Borrowing it
Nothing to install: this file belongs to Cladios34/mtg-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/Cladios34/mtg-mcp-server/main/.claude/skills/smoke-test/SKILL.mdgit clone --depth 1 https://github.com/Cladios34/mtg-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/cladios34/mtg-mcp-server/smoke-test)<a href="https://agentmods.dev/skills/cladios34/mtg-mcp-server/smoke-test"><img src="https://agentmods.dev/badge/skills/cladios34/mtg-mcp-server/smoke-test/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/cladios34/mtg-mcp-server/smoke-test"><img src="https://agentmods.dev/badge/skills/cladios34/mtg-mcp-server/smoke-test.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 | $0.00026 | $0.02975 |
| Opus 5.5 | $0.00010 | $0.01190 |
| Sonnet 5.5 | $0.00005 | $0.00595 |
| Haiku 4.5 | $0.00003 | $0.00298 |
Grade A, and why
smoke-test 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.
This is a copy
94% identical to smoke-test — 24 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive MCP Server Smoke Test
Exercise every tool category on the MTG MCP server via real MCP tool calls and validate results.
Target Server
- Default: local server — tools prefixed
mcp__mtg__ /smoke-test horizon: production Horizon server — tools prefixedmcp__claude_ai_mtg-mcp-server-horizon__
Use $ARGUMENTS to select. If empty or not "horizon", use local.
Execution
Parallelize aggressively. Batch independent tool calls in the same message. Only serialize when a later call depends on an earlier result (e.g., combo detail needs an ID from combo search).
For each call: note PASS / FAIL (with detail) / SKIP (tool unavailable or feature-flagged).
Test Sequence
1. Health + Scryfall API (parallel batch)
| Call | Validate |
|---|---|
ping() |
Returns "pong" |
scryfall_card_details(name="Sol Ring") |
Artifact, mana cost {1}, commander legal |
scryfall_search_cards(query="t:creature id:sultai cmc<=3") |
Multiple creature results |
scryfall_card_rulings(name="Muldrotha, the Gravetide") |
At least one ruling (Sol Ring has 0 rulings; Muldrotha reliably has 8+) |
2. Bulk Data (parallel batch)
| Call | Validate |
|---|---|
bulk_card_lookup(name="Sol Ring") |
Regression check: type_line = "Artifact" (NOT "Card // Card"), set NOT "acmm", commander "legal" (NOT "not_legal"), EDHREC rank present. Note: Oracle Cards printing (SOC) may lack USD prices — this is expected, not a failure |
bulk_card_lookup(name="Delver of Secrets") |
DFC lookup works, oracle text present |
bulk_card_search(query="Lightning", search_field="name") |
Lightning Bolt in results |
bulk_card_search(query="Creature", search_field="type", limit=3) |
Creature type lines |
If bulk tools unavailable (older server), try bulk_card_lookup / bulk_card_search and SKIP the regression check.
3. Bulk Format Staples — Ranking Modes (parallel batch)
| Call | Validate |
|---|---|
bulk_format_staples(format="commander", limit=5) |
EDHREC mode: header contains "Rank", Sol Ring likely in top 5 |
bulk_format_staples(format="modern", limit=5) |
Tournament or competitive mode: header contains "% Decks" or "Score" (NOT "Rank #") |
bulk_format_staples(format="pauper", limit=5) |
Tournament or competitive mode: header contains "% Decks" or "Score", results should be commons (Lightning Bolt, Counterspell typical) |
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 · 205 lines · 26 tokens per session scan A aabb0815ef54
smoke-test is a skill published in the GitHub repository Cladios34/mtg-mcp-server (0 stars, last pushed 9d ago), licensed MIT. It adds 26 tokens to every session and 2,975 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 94% identical to smoke-test, differing in 24 lines, and is treated as a copy.
Other skills, from other repositories
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.
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…
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.