Borrowing it
Nothing to install: this file belongs to j4th/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/j4th/mtg-mcp-server/main/.agents/skills/capture-fixture/SKILL.mdgit clone --depth 1 https://github.com/j4th/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/j4th/mtg-mcp-server/capture-fixture)<a href="https://agentmods.dev/skills/j4th/mtg-mcp-server/capture-fixture"><img src="https://agentmods.dev/badge/skills/j4th/mtg-mcp-server/capture-fixture/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/j4th/mtg-mcp-server/capture-fixture"><img src="https://agentmods.dev/badge/skills/j4th/mtg-mcp-server/capture-fixture.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 | $0.00020 | $0.00565 |
| Opus 5.5 | $0.00008 | $0.00226 |
| Sonnet 5.5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
capture-fixture scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Make the request** using `curl` or `python -c` with httpx. Include required headers: Copies of this mod
1 near-identical copy found in the catalogue:
- capture-fixture — 100% identical, 1 lines differ
What it actually says
Capture Fixture
Capture a real API response and save it as a JSON fixture for TDD testing.
Usage
/capture-fixture <service> <description>
Examples:
/capture-fixture scryfall card lookup for Muldrotha/capture-fixture spellbook combos for Muldrotha/capture-fixture 17lands card ratings for LRW PremierDraft/capture-fixture edhrec commander page for Muldrotha
Workflow
-
Identify the endpoint from
docs/SERVICE_CONTRACTS.mdbased on the service and description. -
Make the request using
curlorpython -cwith httpx. Include required headers:- Scryfall:
User-Agent: mtg-mcp-server/<version>andAccept: application/json - All others:
Accept: application/json
- Scryfall:
-
Save the response to
tests/fixtures/<service>/:- Use a descriptive snake_case filename (e.g.,
card_muldrotha.json,search_sultai_commander.json,card_not_found.json) - Pretty-print with
jq .orpython -m json.tool - Create the directory if it doesn't exist
- Use a descriptive snake_case filename (e.g.,
-
Capture error responses too — 404s, rate limits, etc. are valuable fixtures.
-
Show the user:
- The full URL hit
- The saved file path
- A brief summary of the response shape (top-level keys, array lengths)
Service Endpoints Quick Reference
| Service | Base URL | Key Endpoints |
|---|---|---|
| scryfall | https://api.scryfall.com |
/cards/named?exact=, /cards/search?q=, /cards/{id}/rulings |
| spellbook | https://backend.commanderspellbook.com |
/api/variants/?q=, /api/estimate-bracket/ |
| 17lands | https://www.17lands.com |
/card_ratings/data?expansion=&format= |
| edhrec | https://json.edhrec.com |
/pages/commanders/{slug}.json, /pages/cards/{slug}.json |
Rules
- Never overwrite an existing fixture without asking first
- Always pretty-print JSON
- Respect rate limits — wait between requests if capturing multiple fixtures
- EDHREC slugs: lowercase, hyphens for spaces, strip commas/apostrophes
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.
- 3d ago Changed · -1 lines 672f9f1d7ed2
- 1mo ago First seen · 56 lines · 20 tokens per session scan A d9121575c24c
capture-fixture is a skill published in the GitHub repository j4th/mtg-mcp-server (20 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 565 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tdd
Design features and reproduce bugs through test-first baby steps. Use before changing production behavior, or when reviewing whether a claimed TDD cycle has observable Red evidence. Distinguish behavior changes from behavior-preserving refactoring and documentation-only work.
typescript-craftsmanship
Professional TypeScript + React + Next.js coding standards enforcer. Use this skill whenever writing, reviewing, or refactoring TypeScript code in any project — whether it's a new feature, a bug fix, a refactoring pass, or a code review. Trigger on: any TypeScript or TSX file creation/editing, "clean up this code"…
mtg-commander-analysis
Expert Magic: The Gathering Commander (EDH) deck analysis, optimization, and building assistant. Use this skill whenever the user asks about Commander decks, EDH optimization, power level assessment, bracket placement, mana base construction, card cuts/additions, deck building, commander selection, synergy analysis…
using-mac
Use when invoking mac-device MCP tools to drive a Mac test machine (agent-fleet project) -- screenshot-and-click UI testing, long-running shell or zsh commands, file or process operations, AppleScript automation, or coordinating exclusive device use across multiple agents.
clean-architecture
Clean / Hexagonal Architecture adapted to this Next.js 15 App Router + Prisma + React 19 project. Use when designing a new feature, adding a module, debating where code should live, reviewing a PR that crosses layers, or when the domain logic starts leaking into UI / routes.
using-win
Use when invoking win-device MCP tools to drive a Windows test machine (agent-fleet project) -- screenshot-and-click UI testing, long-running shell commands, file or process operations, or coordinating exclusive device use across multiple agents.