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 agentmods add skills/initializ/forge/tavily-researchnpx skills add initializ/forge --skill tavily-researchgit clone --depth 1 https://github.com/initializ/forgeWrote 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/initializ/forge/tavily-research)<a href="https://agentmods.dev/skills/initializ/forge/tavily-research"><img src="https://agentmods.dev/badge/skills/initializ/forge/tavily-research.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.01047 |
| Opus 5 | $0.00008 | $0.00524 |
| Sonnet 5 | $0.00003 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
tavily-research scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tavily Research Skill
Perform deep, multi-source research using the Tavily Research API. Unlike basic search, research produces comprehensive reports (1000-3000 words) synthesizing information from multiple sources. Research tasks typically take 30-300 seconds depending on complexity and model.
Authentication
Set the TAVILY_API_KEY environment variable with your Tavily API key.
Get your key at https://tavily.com
No OAuth or MCP configuration required.
Quick Start
# Submit research request
./scripts/tavily-research.sh '{"input": "impact of quantum computing on cryptography"}'
# Returns: {"status": "pending", "request_id": "..."}
# Poll for results
./scripts/tavily-research-poll.sh '{"request_id": "72d4a81c-..."}'
# Returns: {"status": "completed", "summary": "...", "report": "...", ...}
Workflow
The research API is asynchronous. Use the two tools in sequence:
- Call
tavily_researchwith your query — returns immediately with arequest_id - Inform the user that research is in progress and may take 30-300 seconds
- Call
tavily_research_pollwith therequest_id— this tool waits internally until the research completes (up to ~5 minutes), so you only need to call it once - When the poll returns, include the full
reporttext in your response — do not summarize or truncate it. Responses over 8000 characters are automatically delivered as a downloadable document by channel adapters (Telegram, Slack), giving the user the complete report as a file
Tool: tavily_research
Submit a deep research request to Tavily AI. Returns immediately with a request_id for polling.
Input:
| Parameter | Type | Required | Description |
|---|---|---|---|
| input | string | yes | The research query or topic |
| model | string | no | Research model: mini (faster, ~30s), pro (thorough, ~300s), or auto (default). Default: auto |
Output: JSON object with status ("pending"), request_id, input, model, and created_at.
What ships with it
2 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.
- 4d ago First seen · 119 lines · 15 tokens per session scan A 857ec831ea92
tavily-research is a skill published in the GitHub repository initializ/forge (156 stars, last pushed 6d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,047 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
quality-loop
Use this workflow recipe when a draft, plan, proposal, or other deliverable should be independently reviewed and revised until it satisfies explicit quality criteria.
mcporter
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, CLI/type generation, and MCP-backed skills that need a durable command path.
mistake-reflection
Use when you discover you made a mistake — caught by the user, by a tool result, by your own re-reading, or by a failed check. Appends a structured entry to docs/ai/ailearnings.md and re-reads recent entries to avoid repeats.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
plan_route
Plan a route and return distance + ETA (schema + deterministic result).
recommend_poi
Recommend a POI in a city (schema + deterministic result).