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 expandingideas-ai/mcp-wet --skill research-topicgit clone --depth 1 https://github.com/expandingideas-ai/mcp-wetWrote 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/expandingideas-ai/mcp-wet/research-topic)<a href="https://agentmods.dev/skills/expandingideas-ai/mcp-wet/research-topic"><img src="https://agentmods.dev/badge/skills/expandingideas-ai/mcp-wet/research-topic/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/expandingideas-ai/mcp-wet/research-topic"><img src="https://agentmods.dev/badge/skills/expandingideas-ai/mcp-wet/research-topic.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 | $0.00808 |
| Opus 5 | $0.00034 | $0.00404 |
| Sonnet 5 | $0.00014 | $0.00162 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
research-topic 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 9d 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
100% identical to research-topic — 0 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
research-topic
Drive wet-mcp's extract(action="agent") to answer a research question
end to end: one search round + concurrent extracts of the top hits + a
single LLM synthesis pass that preserves numbered [N] citations
matching the returned sources.
Use this skill when:
- The user asks an open-ended question that needs multiple sources.
- "Summarise the current state of X."
- "What's the latest on Y?"
- "Compare approaches to Z."
- The user needs a quoted, cited answer (the citations are first-class output, not an afterthought).
Do NOT use this skill when:
- The user already gave you a specific URL -- call
extract(action="extract"). - The user wants a single search result list -- call
search(action="web"). - The question is about library API documentation -- call
search(action="docs_query")against a Tier 1 / locked stack.
Steps
-
Restate the question to the user in 1-2 sentences (calibration: confirm scope before spending tokens).
-
Pick
max_urlsbased on breadth:- 3-5 for a tight question (single technology, single timeframe).
- 6-10 for a broad survey (multiple competitors, multi-year window).
- Hard ceiling is 20 (cost guard).
-
Pick
synthesis_modelonly if the user asked for a specific model. Otherwise omit and let wet auto-detect fromLLM_MODELS/GEMINI_API_KEY/OPENAI_API_KEY/XAI_API_KEY. -
Call
extract(action="agent", query="<question>", max_urls=<N>)Optional knobs:
synthesis_model="...",token_budget=<int>(default 10000; raise for long-form questions, lower for tight cost control). -
Quote the synthesised Markdown verbatim to the user, then list the sources from the
sourcesarray as clickable URLs. Ifper_url_metadatashows anyerror, mention which URL failed and that the synthesis used the remaining N-K sources. -
If wet returns
Error: no LLM provider detected, surface the exact error to the user (do not silently retry againstsearch(action="research")); they need to set one of the supported API keys before agent works.
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.
- 9d ago First seen · 83 lines · 68 tokens per session scan A 253c4689d3bd
research-topic is a skill published in the GitHub repository expandingideas-ai/mcp-wet (0 stars, last pushed 2mo ago), licensed MIT. It adds 68 tokens to every session and 808 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to research-topic, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…