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 tavily-ai/tavily-cursor-plugin --skill tavily-crawlgit clone --depth 1 https://github.com/tavily-ai/tavily-cursor-pluginWrote 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/tavily-ai/tavily-cursor-plugin/tavily-crawl)<a href="https://agentmods.dev/skills/tavily-ai/tavily-cursor-plugin/tavily-crawl"><img src="https://agentmods.dev/badge/skills/tavily-ai/tavily-cursor-plugin/tavily-crawl/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/tavily-ai/tavily-cursor-plugin/tavily-crawl"><img src="https://agentmods.dev/badge/skills/tavily-ai/tavily-cursor-plugin/tavily-crawl.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 | $0.00055 | $0.00338 |
| Opus 5 | $0.00028 | $0.00169 |
| Sonnet 5 | $0.00011 | $0.00068 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
tavily-crawl 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 6d 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
86% identical to tavily-crawl — 108 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.
What it actually says
Tavily Crawl
Gather content from a site section, not from the open web.
When
- You need many pages under one site (docs, API reference, a path prefix)
- Step 4: search → extract → map → crawl → research
Do not use this skill for a single known URL (extract), for URL discovery only (map), or for a cited multi-source report across the web (research).
How
- Map first when the target section is unclear.
- Stay narrow: limit depth and page count; constrain to the paths you need.
- For answering a question, prefer instruction-guided, chunked crawls over dumping every page into context.
- For saving a docs tree onto disk, do that only in a terminal with a real filesystem. On a connector host, return the crawled content instead.
- Cite the pages you used. Always cap the crawl so it cannot run away.
Execute
If tavily_crawl is callable (the name may be prefixed), call it. Do not install the CLI and do not run tvly for this. In a coding-agent terminal that is already using tvly, pass --client-name "cursor plugin" and take flags from tvly crawl --help. Never ask for an API key in chat.
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.
- 6d ago Changed · -69 lines · -61 tokens per session scan C → A 4d2fd5f5d31b
- 11d ago First seen · 100 lines · 116 tokens per session scan C 312c144ffe3a
tavily-crawl is a skill published in the GitHub repository tavily-ai/tavily-cursor-plugin (2 stars, last pushed 9d ago), licensed MIT. It adds 55 tokens to every session and 338 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to tavily-crawl, differing in 108 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…