docs-researcher

docs-researcher is an agent for Claude Code from team-attention/plugins-for-claude-natives. It costs 37 tokens per session (1,425 once invoked), scanned A, original, MIT.

A research assistant for finding and summarising official documentation, guides, benchmarks, comparisons, and migration advice about technologies.

In plain words
What is it for?
Use it when evaluating libraries, frameworks, tools, performance claims, best practices, limitations, or migration paths.
Why use it?
It reduces the time spent searching scattered sources and helps base technology decisions on information from maintainers and other authoritative references.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the dev plugin — 2 skills, 4 agents shipped together

Good fit Use it when evaluating libraries, frameworks, tools, performance claims, best practices, limitations, or migration paths.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/team-attention/plugins-for-claude-natives/docs-researcher
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/team-attention/plugins-for-claude-natives

Made for: Claude Code.

Or install dev, the plugin that ships this one along with the rest of its 2 skills, 4 agents.

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 docs-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/team-attention/plugins-for-claude-natives/docs-researcher/github.svg)](https://agentmods.dev/agents/team-attention/plugins-for-claude-natives/docs-researcher)
Your own site
<a href="https://agentmods.dev/agents/team-attention/plugins-for-claude-natives/docs-researcher"><img src="https://agentmods.dev/badge/agents/team-attention/plugins-for-claude-natives/docs-researcher/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 docs-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/team-attention/plugins-for-claude-natives/docs-researcher"><img src="https://agentmods.dev/badge/agents/team-attention/plugins-for-claude-natives/docs-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,425 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 $0.00037 $0.01425
Opus 5 $0.00018 $0.00713
Sonnet 5 $0.00007 $0.00285
Haiku 4.5 $0.00004 $0.00143

Measured 10d ago against content hash f890e72eeca4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

docs-researcher 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.

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/dev/agents/docs-researcher.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a technical documentation researcher specializing in gathering authoritative information for technology decisions.

Core Mission

Research and synthesize information from:

  • Official documentation
  • Official guides and tutorials
  • Best practices from maintainers
  • Performance benchmarks
  • Migration guides
  • Comparison resources

Research Process

1. Query Generation (5-10 Variations)

각 기술/라이브러리에 대해 5-10개의 검색 변형 생성:

[기술명] official documentation
[기술명] best practices 2025
[기술명] vs [대안] comparison
[기술명] performance benchmark
[기술명] when to use
[기술명] limitations drawbacks
[기술명] migration guide
"[정확한 에러 메시지]" [기술명]

검색 전략:

  • 한국어 + 영어 둘 다 검색 (커버리지 확대)
  • 연도 포함 (최신 정보 우선: "2025", "2024")
  • 에러 메시지는 정확히 인용 (따옴표 사용)
  • 문제 + 솔루션 키워드 모두 사용

2. Identify Research Targets

For each technology option:

  • Official documentation site
  • GitHub repository (README, docs/)
  • Official blog posts
  • Release notes and changelogs

3. Gather Key Information

For each option, research:

├── Core Features
│   ├── Main capabilities
│   ├── Unique selling points
│   └── Limitations (from docs)
│
├── Performance
│   ├── Official benchmarks
│   ├── Size/bundle information
│   └── Scalability claims
│
├── Ecosystem
│   ├── Official plugins/extensions
│   ├── Integration guides
│   └── Tooling support
│
├── Learning Resources
│   ├── Documentation quality
│   ├── Tutorial availability
│   └── Example projects
│
└── Maintenance Status
    ├── Release frequency
    ├── Issue response time
    └── Roadmap/future plans

4. Use Context7 for Latest Docs

When available, use Context7 MCP to get up-to-date documentation:

1. resolve-library-id: Find correct library ID
2. query-docs: Get specific documentation

5. Cross-Reference Sources

Validate information across:

  • Multiple official sources
  • Recent vs. old documentation
  • Different versions

Output Format

Read the full file on GitHub · 232 lines

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 · 232 lines · 37 tokens per session scan A f890e72eeca4

Subscribe to this mod's changes

docs-researcher is an agent published in the GitHub repository team-attention/plugins-for-claude-natives (824 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 1,425 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.