context7-auto-research

context7-auto-research is a skill for Claude Code from BenedictKing/benedictking-skills. It costs 46 tokens per session (2,373 once invoked), scanned A, original, MIT.

A skill that fetches current documentation and code examples for named libraries, frameworks, software-development kits, and APIs from Context7.

In plain words
What is it for?
Use it when building with or configuring a named library, framework, SDK, or API and you need current installation steps, references, or examples.
Why use it?
It reduces the risk of using outdated setup instructions or API details from memory. It activates for implementation, configuration, documentation, and code-generation questions involving software libraries.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Claude Code.

Part of the benedictking-skills plugin — 6 skills shipped together

Good fit Use it when building with or configuring a named library, framework, SDK, or API and you need current installation steps, references, or examples.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/benedictking/benedictking-skills/context7-auto-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 BenedictKing/benedictking-skills --skill context7-auto-research
Clone the repo
git clone --depth 1 https://github.com/BenedictKing/benedictking-skills

Made for: Claude Code.

Or install benedictking-skills, the plugin that ships this one along with the rest of its 6 skills.

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 context7-auto-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/benedictking/benedictking-skills/context7-auto-research/github.svg)](https://agentmods.dev/skills/benedictking/benedictking-skills/context7-auto-research)
Your own site
<a href="https://agentmods.dev/skills/benedictking/benedictking-skills/context7-auto-research"><img src="https://agentmods.dev/badge/skills/benedictking/benedictking-skills/context7-auto-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 context7-auto-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/benedictking/benedictking-skills/context7-auto-research"><img src="https://agentmods.dev/badge/skills/benedictking/benedictking-skills/context7-auto-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,373 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.02373
Opus 5 $0.00023 $0.01187
Sonnet 5 $0.00009 $0.00475
Haiku 4.5 $0.00005 $0.00237

Measured 10d ago against content hash ae24c3837ad2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

context7-auto-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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/context7-api.cjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/context7-auto-research/SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context7 Auto Research Skill

This skill automatically fetches current documentation from Context7 API when detecting library/framework-related queries, ensuring responses use up-to-date information instead of potentially outdated training data.

Automatic Activation Triggers

This skill should activate proactively when the user's message contains:

Implementation Queries (实现相关)

  • "如何实现" / "怎么写" / "怎么做"
  • "How do I..." / "How to..." / "How can I..."
  • "Show me how to..." / "Write code for..."

Configuration & Setup (配置相关)

  • "配置" / "设置" / "安装"
  • "configure" / "setup" / "install"
  • "初始化" / "initialize"

Documentation Requests (文档相关)

  • "文档" / "参考" / "API"
  • "documentation" / "docs" / "reference"
  • "查看" / "look up"

Library/Framework Mentions (库/框架提及)

  • React, Vue, Angular, Svelte, Solid
  • Next.js, Nuxt, Remix, Astro
  • Express, Fastify, Koa, Hono
  • Prisma, Drizzle, TypeORM
  • Supabase, Firebase, Clerk
  • Tailwind, shadcn/ui, Radix
  • Any npm package or GitHub repository

Code Generation Requests (代码生成)

  • "生成代码" / "写一个" / "创建"
  • "generate" / "create" / "build"
  • "implement" / "add feature"

Research Process

When triggered, follow this workflow:

Step 1: Extract Library Information

Identify the library/framework from the user's query:

  • Library name (e.g., "react", "next.js", "prisma")
  • Version if specified (e.g., "React 19", "Next.js 15")
  • Specific feature/API mentioned (e.g., "useEffect", "middleware", "relations")

Step 2: Search for Library

Use Task tool to call context7-fetcher sub-skill:

Task parameters:
- subagent_type: Bash
- description: "Search Context7 for library"
- prompt: node scripts/context7-api.cjs search "<library-name>" "<user-query>"

Example:

Task: Search for Next.js
Prompt: node scripts/context7-api.cjs search "next.js" "How to configure middleware in Next.js 15"

Response format:

{
  "libraries": [
    {
      "id": "/vercel/next.js",
      "name": "Next.js",
      "description": "The React Framework",
      "trustScore": 95,
      "versions": ["v15.1.8", "v14.2.0", "v13.5.0"]
    }
  ]
}

Read the full file on GitHub · 344 lines

Files

What ships with it

3 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.

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. 10d ago First seen · 344 lines · 46 tokens per session scan A ae24c3837ad2

Subscribe to this mod's changes

context7-auto-research is a skill published in the GitHub repository BenedictKing/benedictking-skills (14 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 2,373 once invoked, about $0.0002 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.