Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add unblockingapi/mcp --skill app-recipesgit clone --depth 1 https://github.com/unblockingapi/mcpWrote 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/unblockingapi/mcp/app-recipes)<a href="https://agentmods.dev/skills/unblockingapi/mcp/app-recipes"><img src="https://agentmods.dev/badge/skills/unblockingapi/mcp/app-recipes/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/unblockingapi/mcp/app-recipes"><img src="https://agentmods.dev/badge/skills/unblockingapi/mcp/app-recipes.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 | $0.00068 | $0.00465 |
| Opus 5.5 | $0.00027 | $0.00186 |
| Sonnet 5.5 | $0.00014 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
app-recipes 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 2d 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.
What it actually says
App recipes on UnblockingAPI
Complete designs for the apps people most often build on UnblockingAPI: data model, fetching code, scheduling, cost and UI. Read the one that fits before planning, and adapt it to the user's stack:
| The user wants | Read |
|---|---|
| Google positions for keywords and domains over time | references/rank-tracker.md |
| Product prices watched, with alerts on changes or a target price | references/price-monitor.md |
| Listings from several sites, normalised into one searchable page | references/listings-aggregator.md |
For something close but different (a news monitor, a job board, a stock checker), take the nearest recipe: they share the same shape.
The shape every recipe shares
- Sources first. For each site, look for a template (
find_templateswith a real URL from that site, or thetemplatesskill); fall back to parsing HTML only when none fits. - Store every check. One table for what is watched, one for each check with a timestamp, so the app can show history and change.
- Fetch on a schedule, in the background. A scheduled job with a worker
pool of 3-5, a 180 s timeout and backoff on 429/503/504, never inside a web
request. The
build-appskill has the rules. - Tell the user the cost. 1 credit per successful fetch: items x checks per day x 30 per month. Suggest the slowest schedule that still serves them.
Start with a working fetch of one real URL from each source before building
the rest. In this conversation, unblock_fetch with template set shows the
exact JSON the app will receive.
What ships with it
3 files 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.
- 2d ago First seen · 37 lines · 68 tokens per session scan A b378b0cfccc6
app-recipes is a skill published in the GitHub repository unblockingapi/mcp (2 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 465 once invoked, about $0.0003 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 2026-10-21.
Other skills, from other repositories
transformers-js
Run Hugging Face models in JavaScript or TypeScript with Transformers.js, WebGPU, or WASM across browser, Node.js, Bun, and Deno. Use for client-side or JS-runtime inference, not Python training.
octen-web-search
Use when anything needs live information from the web — looking something up, checking current or recent information, finding sources, comparing products / vendors / pricing, researching a topic, or reading a specific web page — even if the user never mentions Octen or the word "search". Also use before falling back…
agent-browser-verify
Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass/fail before continuing.
vercel-sandbox
Vercel Sandbox guidance — ephemeral Firecracker microVMs for running untrusted code safely. Supports AI agents, code generation, and experimentation. Use when executing user-generated or AI-generated code in isolation.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
get-domain-cookies
Use when the user asks for Chrome cookies for a domain (especially amctheatres.com Queue-it sessions).