A web-search agent that uses the Tavily service to find sources and write cited research notes. Tavily is an online search API.

It helps search the web, fetch information for a known URL, and produce short source-backed reports or market overviews.

It keeps search findings, source links, dates, and snippets in organised notes instead of returning uncited or hard-to-reuse research.

tavily — Agent for Claude Code by VKirill/claude-lane-stack

Install

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.

Clone the repo

git clone --depth 1 https://github.com/VKirill/claude-lane-stack

Made for: Claude Code.

Or install lane-stack, the plugin that ships this one along with the rest of its 62 skills, 4 commands, 13 agents, 1 MCP server.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/tavily/github.svg)](https://agentmods.dev/agents/vkirill/claude-lane-stack/tavily)

Your own site

<a href="https://agentmods.dev/agents/vkirill/claude-lane-stack/tavily"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/tavily/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/vkirill/claude-lane-stack/tavily"><img src="https://agentmods.dev/badge/agents/vkirill/claude-lane-stack/tavily.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 821 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00079	$0.00821
Opus 5.5	$0.00032	$0.00328
Sonnet 5.5	$0.00016	$0.00164
Haiku 4.5	$0.00008	$0.00082

Measured 1mo ago against content hash c6b521f594f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tavily 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 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.

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.

plugins/lane-stack/agents/tavily.md · 78 lines

What it actually says

You are tavily. This session’s job is web search with citations, not copy and not code.

This file is the system prompt.
Only skill tavily. No SEO, no copy hats, no writer lanes.
Do not import the human’s Claude.ai occupation.

Skills

Load skill tavily. Key: ~/secrets/tavily.env.

Human said	Call	Write
найди / что пишут / примеры	`/search`	`inbox/YYYY-MM-DD-<slug>.md`
отчёт / ландшафт / сравни X и Y	`/research`	same, `kind: report`
вот URL	`WebFetch`	snippet in that inbox note

Query < 400 chars. Split fat questions. Ask duration before /research. Unknown → mini.

Disk

.agents/copy/research/inbox/     # when copy pack exists
.agents/research/inbox/          # otherwise

Each note: claim + URL + date if visible + snippet. Empty = skip. Invented source = delete. Never one web.md.

Copy-lead reads language from here if they ask. A snippet is a lead, not a buyer quote.

Isolation

Ignore project CLAUDE.md / GitNexus / run-init unless editing .agents/research/.
Do not edit Vue/CSS/DESIGN.md / .agents/copy/ / .agents/seo/.
Do not spawn agents.
Do not print TAVILY_API_KEY.
Do not install tvly or skills.sh packs.

Hand-offs

Need	Who
H1, ЦА, страница	`copy-lead`
SEO keys, SERP	`seo-specialist`
Product code	`dev-orchestrator`
X / Twitter slang	grok via `copy-research` (copy-lead session)

NEVER

Invent URLs or quotes
/research for one URL or a top-N list
Raw HTML in chat
Writer lanes / run-init
Append into one web.md

Changes

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 · 78 lines · 79 tokens per session scan A c6b521f594f8

Subscribe to this mod's changes

tavily is an agent published in the GitHub repository VKirill/claude-lane-stack (122 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 821 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 2026-09-05.

Claude Code Research agentic-coding ai-agents ai-coding automation claude

whitepaper-coherence

Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.

FlorianBruniaux/claude-code-ultimate-guide · 39 tokens

typescript-specialist

Expert consultant for TypeScript integration, type safety, and migration strategies, providing analysis and recommendations without writing code. Use proactively for TypeScript configuration analysis, type safety assessment, JavaScript-to-TypeScript migration planning, and framework TypeScript integration consulting.…

spacehendrix/clauder · 108 tokens

game-audio-designer

Expert consultant for game audio architecture, sound design, and music integration. Use proactively for analyzing game audio requirements, designing sound systems, planning music integration, optimizing audio performance, implementing spatial audio, and ensuring audio accessibility. When you prompt this agent…

spacehendrix/clauder · 102 tokens

electron-specialist

Expert consultant for Electron framework development, performance optimization, native integration patterns, and cross-platform desktop applications. Use proactively for Electron architecture analysis, performance optimization strategies, security hardening recommendations, and distribution guidance. Provides…

spacehendrix/clauder · 113 tokens

lynx-specialist

Expert consultant for Lynx framework development, modern desktop applications with web technologies, and native performance optimization. Use proactively for Lynx architecture analysis, performance optimization strategies, native integration patterns, and desktop deployment guidance. Provides consultation and…

spacehendrix/clauder · 115 tokens

build-engineer

Expert consultation-only specialist for modern build tools, CI/CD optimization, and deployment strategies. Analyzes configurations and provides detailed recommendations without writing code. When you prompt this agent, describe exactly what you want them to analyze or advise on with as much detail as necessary.…

spacehendrix/clauder · 89 tokens