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 templatesgit 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/templates)<a href="https://agentmods.dev/skills/unblockingapi/mcp/templates"><img src="https://agentmods.dev/badge/skills/unblockingapi/mcp/templates/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/templates"><img src="https://agentmods.dev/badge/skills/unblockingapi/mcp/templates.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 | $0.00080 | $0.00538 |
| Opus 5.5 | $0.00032 | $0.00215 |
| Sonnet 5.5 | $0.00016 | $0.00108 |
| Haiku 4.5 | $0.00008 | $0.00054 |
Grade A, and why
templates 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
UnblockingAPI templates in an app
A template parses one kind of page into named fields. Passing its reference as
template makes /unblock return response_format: "json" with response as
an object, so the app stores fields instead of parsing HTML.
Read references/templates.md for the endpoints, an output example and the
calling code.
Workflow
- Find one for the exact URL the app will fetch. In this conversation call
find_templateswith that URL; it searches every published template and returns the fields each produces. Without the tool, readGET https://api.unblockingapi.com/templates.json?url=<url>(no key). - Get the real output shape before writing types or a schema:
GET https://app.unblockingapi.com/public/v1/templates/<handle>/<name>returnsresponse_skeletonandfield_tree. Write the app's types from that, not from a guess. - Call it with a pinned version in production:
template: "handle/name@3".template_versionin the response says which version answered. A template forces its own render and wait settings, so do not add wait options to it. - Handle
parse_error: true. When the site changed and the template's parser failed, the response is HTML instead of JSON. Log it, keep the last good data, and do not write the HTML into JSON columns. - No template for the site? Either parse the HTML in code (cheerio or linkedom in JavaScript, BeautifulSoup or selectolax in Python, selecting the repeated item element), or suggest the user builds one without code at https://editor.unblockingapi.com: load the page, click the fields, publish. A template can be repaired in the editor when the site changes, without redeploying the app, which is usually the better choice for a site the app depends on.
Templates are listed in the template library at https://unblockingapi.com/templates.
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.
- 2d ago First seen · 40 lines · 80 tokens per session scan A 3ce8cdb6dc88
templates is a skill published in the GitHub repository unblockingapi/mcp (2 stars, last pushed yesterday), licensed MIT. It adds 80 tokens to every session and 538 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
har-derived-api-client
Record a site's XHR into a HAR, derive an HTTP client.
design-patterns
Agents should invoke this skill when choosing patterns, designing traits/interfaces/components, deciding abstraction boundaries, evaluating dependency injection/callbacks, or comparing implementation approaches in Rust, TypeScript/React, or Django/Python.
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.
mcp-builder
Guide the creation of high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when the user wants to build an MCP server to integrate an external API or service, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
huggingface-community-evals
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .evalresults publication, or community-evals automation.
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…