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.
npx skills add LazyAGI/LazyMind --skill deep-researchgit clone --depth 1 https://github.com/LazyAGI/LazyMindWrote 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/skills/lazyagi/lazymind/deep-research)<a href="https://agentmods.dev/skills/lazyagi/lazymind/deep-research"><img src="https://agentmods.dev/badge/skills/lazyagi/lazymind/deep-research.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00125 | $0.02166 |
| Opus 5 | $0.00063 | $0.01083 |
| Sonnet 5 | $0.00025 | $0.00433 |
| Haiku 4.5 | $0.00013 | $0.00217 |
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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Research Skill
Overview
This skill provides a systematic methodology for genuinely comprehensive research. Load it only when the user explicitly asks for deep, systematic, multi-source investigation or when the requested deliverable inherently requires such research. Do not load it for a normal answer, introductory explanation, how-to question, or ordinary content-generation request.
When to Use This Skill
Always load this skill when:
Research Questions
- User asks for comprehensive analysis: "research X", "deep dive into X", "detailed comparison of X and Y", "investigate the landscape of X", "thorough analysis of X"
- User uses Chinese research triggers: "调研一下X", "深入分析X", "全面调查X", "X与Y的深度对比", "详细梳理X的发展历程", "X的现状与未来趋势"
- User explicitly wants to understand a complex concept, technology, or topic in depth, rather than seeking normal guidance.
- The question requires synthesizing current, comprehensive information from multiple distinct sources.
- A single web search or factual retrieval would be explicitly insufficient to answer properly.
Do not infer deep-research intent merely because the topic is broad or because the user wants to create a presentation, article, report, video, or other content.
Core Principle
Never generate content based solely on general knowledge. The quality of your output directly depends on the quality and quantity of research conducted beforehand. A single search query is NEVER enough.
Research Methodology
Phase 1: Material Retrieval and Source Planning
Identify the evidence needed, then retrieve material from the sources prioritized or permitted by the system instructions and the user's request. Sources may include internal documents, public web pages, academic collections, user-provided files, or specific URLs. Do not assume a source priority, probe for sources that were not offered, or override the host system's routing rules.
- Define Evidence Needs: Break the question into facts, examples, viewpoints, and time-sensitive claims that require support.
- Choose Appropriate Sources: Match each evidence need to the source types and retrieval capabilities made available for this task.
- Retrieve Initial Material: Use precise semantic, keyword, or document-scoped queries as appropriate.
- Assess Coverage: Record which dimensions are supported and which still contain gaps or conflicting evidence.
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.
- 8d ago First seen · 211 lines · 125 tokens per session scan A f8ea28131414
deep-research is a skill published in the GitHub repository LazyAGI/LazyMind (77 stars, last pushed yesterday), licensed Apache-2.0. It adds 125 tokens to every session and 2,166 once invoked, about $0.0006 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.
Other skills, from other repositories
remote-compute-modal
Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.
customize
Create, configure, and maintain custom agent profiles and author new skills via the repl tool. Use when the user wants to create an agent profile, build a custom agent, modify agent capabilities, attach or detach skills/connectors on a profile, author a skill, or inspect which connectors and tools are available. Also…
smart-data-analysis
A central workflow for handling data questions and data assets across tables, views, metrics, SQL, charts, and Business Knowledge Networks.
claude-api
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports anthropic/@anthropic-ai/sdk/claudeagentsdk, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports openai/other AI SDK, general programming, or ML/data-science tasks.
compute-env-setup
Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…
ima-skill
A unified IMA skill for managing personal notes and knowledge bases through the platform's APIs.