Deep Agents is an extensible agent harness that provides an out-of-the-box agent for long, multi-step tasks, with features such as planning, sub-agents, filesystem access, context management, memory, and human approval of tool calls. It is used by developers building agents with different language models, and its catalogue entries extend the harness with reusable skills, MCP servers, and instructions.
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 agentmods add skills/langchain-ai/deepagents/web-researchnpx skills add langchain-ai/deepagents --skill web-researchgit clone --depth 1 https://github.com/langchain-ai/deepagentsWrote 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/langchain-ai/deepagents/web-research)<a href="https://agentmods.dev/skills/langchain-ai/deepagents/web-research"><img src="https://agentmods.dev/badge/skills/langchain-ai/deepagents/web-research.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00056 | $0.00764 |
| Opus 5 | $0.00028 | $0.00382 |
| Sonnet 5 | $0.00011 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
web-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 5d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research Skill
Research Process
Step 1: Create and Save Research Plan
Before delegating to subagents, you MUST:
-
Create a research folder - Organize all research files in a dedicated folder relative to the current working directory:
mkdir research_[topic_name]This keeps files organized and prevents clutter in the working directory.
-
Analyze the research question - Break it down into distinct, non-overlapping subtopics
-
Write a research plan file - Use the
write_filetool to createresearch_[topic_name]/research_plan.mdcontaining:- The main research question
- 2-5 specific subtopics to investigate
- Expected information from each subtopic
- How results will be synthesized
Planning Guidelines:
- Simple fact-finding: 1-2 subtopics
- Comparative analysis: 1 subtopic per comparison element (max 3)
- Complex investigations: 3-5 subtopics
Step 2: Delegate to Research Subagents
For each subtopic in your plan:
-
Use the
tasktool to spawn a research subagent with:- Clear, specific research question (no acronyms)
- Instructions to write findings to a file:
research_[topic_name]/findings_[subtopic].md - Budget: 3-5 web searches maximum
-
Run up to 3 subagents in parallel for efficient research
Subagent Instructions Template:
Research [SPECIFIC TOPIC]. Use the web_search tool to gather information.
After completing your research, use write_file to save your findings to research_[topic_name]/findings_[subtopic].md.
Include key facts, relevant quotes, and source URLs.
Use 3-5 web searches maximum.
Step 3: Synthesize Findings
After all subagents complete:
- Review the findings files that were saved locally:
- First run
list_files research_[topic_name]to see what files were created - Then use
read_filewith the file paths (e.g.,research_[topic_name]/findings_*.md) - Important: Use
read_filefor LOCAL files only, not URLs
- First run
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.
- 5d ago First seen · 78 lines · 56 tokens per session scan A 7c2b1f199037
web-research is a skill published in the GitHub repository langchain-ai/deepagents (28,997 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 764 once invoked, about $0.0003 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
recover-from-failure
How to recover when a tool call fails — diagnose, not blindly retry.
workspace-conventions
Reminders about how Dawn's workspace tools behave and what the path-jail allows.
dawn
Build AI agents and workflows with the Dawn framework — the TypeScript meta-framework for LangGraph. Use when creating, editing, or debugging a Dawn app (routes, tools, state, agents, workflows, testing, deployment).
cite-sources
How to attribute every factual claim to a corpus document.
synthesize-findings
How to merge researcher sub-answers into one cited report.
code-reviewer
当用户要求进行代码审查、Code Review、查找 Bug、安全风险、性能问题或代码质量问题时使用。.