By jamesprial
Deep research agent: parallel web research with source archival and cited reports
A Claude Code plugin that emulates Claude.ai's Deep Research feature. Conducts parallel multi-agent web research, writes a structured cited report, and archives all sources locally.
Add to your Claude Code plugins:
claude plugins add /path/to/deep-research
Or symlink into ~/.claude/plugins/.
Ask Claude a research question with the plugin active. The deep-researching skill triggers automatically and runs a 6-phase pipeline:
research-worker agents in parallel, each investigating a sub-topic via web searchEach research run creates a timestamped directory:
./research-{topic}-{YYYYMMDD-HHMMSS}/
├── report.md # Final report with inline citations [1][2]...
└── sources/
├── index.md # Source index table
├── 001-example-com.md
├── 001-example-com.html
├── 002-arxiv-org.md
├── 002-arxiv-org.html
└── ...
| Agent | Model | Role |
|---|---|---|
research-worker | sonnet | Searches the web, reads sources, extracts structured findings with citations |
source-archiver | haiku | Archives URLs as markdown (WebFetch) and raw HTML (curl) |
MIT
Uses power tools
Uses Bash, Write, or Edit tools
Runs pre-commands
Contains inline bash commands via ! syntax
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub jamesprial/prial-plugins --plugin deep-researchGit operations and GitHub CLI agents for version control workflows
Go development workflow with TDD-first parallel agents, failure triage, and automated code quality hooks
Security hooks to detect and block potential secrets in git commits
Captures TodoWrite tool usage and saves to timestamped history file with configurable log location (default: .claude/todos.json)
Create custom slash commands for Claude Code with syntax, patterns, and helper scripts
AI-powered deep research with multi-agent source verification and structured outputs
Multi-agent deep research plugin with parallel web searches and synthesis
深度研究 — 13 agent 协作:研究问题定义、系统性检索、偏差评估、综合分析、引用编译
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.