tavily-hikari-research

tavily-hikari-research is a skill for Claude Code, Codex from IvanLi-CN/tavily-hikari. It costs 25 tokens per session (280 once invoked), scanned A, original, MIT.

A command-line workflow for conducting multi-step web research through Tavily Hikari, a research service for finding and combining online information.

In plain words
What is it for?
Use it to run scoped research questions, save results as JSON, and check the status of research requests that are still running.
Why use it?
It gives research tasks a defined question and lets you save or check results when the service responds asynchronously.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to run scoped research questions, save results as JSON, and check the status of research requests that are still running.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ivanli-cn/tavily-hikari/tavily-hikari-research
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.

Any agent
npx skills add IvanLi-CN/tavily-hikari --skill tavily-hikari-research
Clone the repo
git clone --depth 1 https://github.com/IvanLi-CN/tavily-hikari

Made for: Claude Code, Codex.

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.

agentmods badge for tavily-hikari-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/ivanli-cn/tavily-hikari/tavily-hikari-research/github.svg)](https://agentmods.dev/skills/ivanli-cn/tavily-hikari/tavily-hikari-research)
Your own site
<a href="https://agentmods.dev/skills/ivanli-cn/tavily-hikari/tavily-hikari-research"><img src="https://agentmods.dev/badge/skills/ivanli-cn/tavily-hikari/tavily-hikari-research/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.

agentmods 80×15 button for tavily-hikari-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/ivanli-cn/tavily-hikari/tavily-hikari-research"><img src="https://agentmods.dev/badge/skills/ivanli-cn/tavily-hikari/tavily-hikari-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 280 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.00280
Opus 5 $0.00013 $0.00140
Sonnet 5 $0.00005 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured 12d ago against content hash f3eceb044df3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tavily-hikari-research 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 12d 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.

skills/tavily-hikari-research/SKILL.md · 38 lines

What it actually says

Tavily Hikari Research

Use this skill when the task needs multi-step Tavily research through Tavily Hikari.

Workflow

  1. Write a concise research question with scope, date, geography, and source constraints.

  2. Run:

    tvly-hikari research "Compare Tavily CLI, Agent Skills, and MCP for AI agents" --json
    
  3. Save the response for longer investigations:

    tvly-hikari research "Compare Tavily CLI, Agent Skills, and MCP for AI agents" --json -o tavily-research.json
    
  4. If the official CLI returns an async request id, inspect or wait for the result through the official follow-up commands exposed by the wrapper:

    tvly-hikari research status <request-id> --json
    tvly-hikari research poll <request-id> --json -o tavily-research.json
    

Hikari Notes

  • Requests go to the configured Hikari /api/tavily/research facade.
  • Hikari token quota applies to research calls.
  • Hikari audit logs retain the downstream token context while upstream keys remain private.
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.

  1. 12d ago First seen · 38 lines · 25 tokens per session scan A f3eceb044df3

Subscribe to this mod's changes

tavily-hikari-research is a skill published in the GitHub repository IvanLi-CN/tavily-hikari (348 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 280 once invoked, about $0.0001 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

status-card-query

Create and maintain agent-authored Paperclip status cards, or compile a prose interest prompt into bounded CompanySearchQuery objects and write the first summary from the assigned Summarizer run.

paperclipai/paperclip · 40 tokens

gpt-researcher

Autonomous deep research from Codex via MCP.

assafelovic/gpt-researcher · 15 tokens

bilibili_search

Search for videos on Bilibili using keyword queries generated from user interests.

whiteguo233/OpenBiliClaw · 20 tokens

vs-search-tuning-specify-policy-direction

Viking Search tuning for specified policy directions. Use this when the user provides specific queries, a type of query, or a business policy direction, and asks to boost, suppress, or fix a class of search results through request-parameter passthrough. You must only perform read-only baseline evaluation and…

volcengine/SearchCLI · 93 tokens

vs-search-tuning-partial-case

Use when the user provides 1-50 concrete bad-case search queries for one Viking Search app and wants local deterministic fixes. This skill only verifies request-level fine-operation interventions against a read-only baseline scene and delivers a console-ready configuration sheet, validated payloads, and a replay…

volcengine/SearchCLI · 85 tokens

site-config-creation

Create or update the [site] section of stencila.toml for published Stencila sites. Use when asked to configure site domain, title, author, logo, icons, labels, descriptions, socials, featured content, navigation, routes, access, layout presets and regions, glide, search, formats, reviews, uploads, remotes, actions…

stencila/stencila · 106 tokens