Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add trtmn/agent-plugins/plugin install recipe-fetchWrote 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/trtmn/agent-plugins/recipe-fetch)<a href="https://agentmods.dev/skills/trtmn/agent-plugins/recipe-fetch"><img src="https://agentmods.dev/badge/skills/trtmn/agent-plugins/recipe-fetch/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/trtmn/agent-plugins/recipe-fetch"><img src="https://agentmods.dev/badge/skills/trtmn/agent-plugins/recipe-fetch.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 | $0.00124 | $0.01523 |
| Opus 5.5 | $0.00050 | $0.00609 |
| Sonnet 5.5 | $0.00025 | $0.00305 |
| Haiku 4.5 | $0.00012 | $0.00152 |
Grade A, and why
recipe-fetch scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Bash(curl *) How it starts
The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recipe Fetch Skill
Fetch a recipe from one or more URLs and save to the Obsidian vault as correctly formatted markdown.
Vault Paths
- Vault root:
~/Library/Mobile Documents/iCloud~md~obsidian/Documents/<VaultName> - Recipe files:
Recipes/<Recipe Title>.md - Recipe images:
Files/recipes/<kebab-case-title>.jpg - Vault-relative image ref:
Files/recipes/<kebab-case-title>.jpg
Handling Multiple URLs
When the user provides more than one URL, dispatch a separate background agent per URL in the same turn. Each agent runs this skill independently and saves its recipe. This lets all fetches happen simultaneously rather than one at a time.
Per-Recipe Workflow
1. Extract recipe data (JSON-LD first, WebFetch fallback)
Primary method — JSON-LD structured data (preferred):
Most recipe sites embed machine-readable recipe data in <script type="application/ld+json"> blocks. This is the most reliable extraction method because it returns verbatim structured data with no AI summarization risk.
python3 "${CLAUDE_PLUGIN_ROOT}/skills/recipe-fetch/scripts/extract_jsonld.py" "<URL>"
If exit code is 0, the script outputs a JSON object with name, ingredients, instructions, image, and og_image. Use these fields directly — they are verbatim from the site's own structured data.
If exit code is 1 (no JSON-LD found), fall back to the WebFetch method below.
Fallback method — WebFetch:
Only use this when JSON-LD extraction fails (exit code 1). Use WebFetch to get the full page. In a single pass, extract:
- Recipe title
- All ingredients (verbatim, every line)
- All instructions (verbatim, every step)
- The
og:imageURL (used to download the recipe photo)
If the page has multiple recipe components (e.g., cake + frosting, meatballs + sauce), fetch ALL of them. Use explicit language: "Extract ALL recipes on this page including [component A] AND [component B]."
2. Check for existing file
Before writing anything:
test -f "~/Library/Mobile Documents/iCloud~md~obsidian/Documents/<VaultName>/Recipes/<Recipe Title>.md"
If the file exists, read it and stop — report the conflict to the user and ask whether to overwrite, merge, or skip.
What ships with it
1 file 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.
- 1mo ago First seen · 145 lines · 124 tokens per session scan A 260d58acdfc8
recipe-fetch is a skill published in the GitHub repository trtmn/agent-plugins (2 stars, last pushed 11d ago), licensed Unlicense. It adds 124 tokens to every session and 1,523 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…