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.
/plugin marketplace add Hayes-Zhang/deep-researchnpx agentmods add plugins/hayes-zhang/deep-research/deep-researchgit clone --depth 1 https://github.com/Hayes-Zhang/deep-researchWrote 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/plugins/hayes-zhang/deep-research/deep-research)<a href="https://agentmods.dev/plugins/hayes-zhang/deep-research/deep-research"><img src="https://agentmods.dev/badge/plugins/hayes-zhang/deep-research/deep-research.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
deep-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 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.
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.
What it actually says
{
"name": "deep-research",
"version": "1.3.0",
"description": "A 7-perspective Agent Team + adversarial critic for Claude Code: 7 researchers (Product, UX, Tech, Practice, Academic, History, Social) run in parallel; the critic traces primary sources and tags per-finding confidence; the team lead synthesizes one HTML + Markdown + Notion report.",
"author": {
"name": "Hayes Zhang",
"url": "https://github.com/Hayes-Zhang"
},
"homepage": "https://github.com/Hayes-Zhang/deep-research",
"repository": "https://github.com/Hayes-Zhang/deep-research",
"license": "MIT",
"keywords": [
"agent-team",
"multi-agent",
"deep-research",
"claude-code",
"product-strategy",
"research-automation"
]
}
What it installs
The manifest is a name and a version. 1 command, 8 agents travel with it, and installing the plugin installs all of them — 290 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command deep A 27 tokens
- Agent critic-reviewer A 36 tokens
- Agent researcher-academic A 34 tokens
- Agent researcher-history A 27 tokens
- Agent researcher-practice A 37 tokens
- Agent researcher-product A 30 tokens
- Agent researcher-social A 34 tokens
- Agent researcher-tech A 32 tokens
- Agent researcher-ux A 33 tokens
What ships with it
1 file beside plugin.json 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 · 21 lines scan A fe630d163fa2
deep-research is a plugin published in the GitHub repository Hayes-Zhang/deep-research (4 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.
Other plugins, from other repositories
autosearch
Self-evolving deep research. Gets smarter every time you use it. Searches across channels, synthesizes cited reports, and learns which queries and platforms work best.
antigravity
Antigravity plugin for Claude Code with TRAID Design System: 5 canonical HTML templates (traid-dark, traid-light, stripe-press, notion-docs, magazine) for branded report generation from markdown. Plus audio & video transcription (/agy:transcribe, /agy:media), a local NotebookLM (/agy:notebook — sweep a folder of…
policy-research-kit
정책연구보고서를 끝까지 쓰는 에이전트 팀. 연구설계 → 설계검토 게이트(GO/NO-GO) → 목차 사용자 승인 → 근거조사(출처 병기) → 집필 → 초안검수(참고문헌·출처 실재 검증 포함 5축) → 한글 .hwpx 변환까지 한 파이프라인. 표준 보고서(50p+)와 단형 정책브리프(48p) 2모드. A five-agent team that produces Korean policy research reports end-to-end, with two-stage verification gates and native HWPX output.
oh-my-harness
The team-architecture factory for Claude Code — a meta-skill that turns a domain description into an agent team and the skills they use. Three native execution modes (Workflow orchestration, persistent named-agent collaboration, sub-agent delegation), six team-architecture patterns, and workflow-native quality…
socsci-paper-kit
사회과학 학술논문을 쓰는 에이전트 팀. 연구설계(RQ·가설·변수·조작적 정의·이론틀) → 설계검토 게이트 → 근거조사∥데이터분석(조건부) → 학술 문체 집필(APA7) → 5축 검수(유령인용·환각출처 적발) → Word .docx + Markdown 산출. 계량서지·정량 논문용 심화 검수(scientometric review) 포함. A six-agent social-science paper team with hypothesis design, five-axis review, and DOCX output.
harness-zh
Agent Team & Skill Architect (Simplified Chinese). Meta-skill for Claude Code that designs domain-specific agent teams, defines specialized agents, and generates the skills they use. 面向 Claude Code 的简体中文元技能：为任意领域自动设计多智能体团队、定义专家智能体，并生成团队协作所需的技能。.