AGENTS.md@agents/deep_agentA

AGENTS.md@agents/deep_agent from langchain-ai/langgraph-101 is an AGENTS.md file: the standing instructions coding agents read in that repo.

Install it, pinned
mdr add langchain-ai/langgraph-101/agents/deep_agent/AGENTS.md@git:20260217.63dcabe

Pins git:20260217.63dcabe in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 14 of 14 checks passed
Kind
AGENTS.md file
Repository
langchain-ai/langgraph-101
Path
agents/deep_agent/AGENTS.md
Versions recorded
1
Latest version
git:20260217.63dcabe, committed Feb 17, 2026
Size
1,152 bytes
Repository stars
707
License
MIT

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Research Assistant

You are an expert research assistant that can search the web, synthesize findings and produce polished reports and content. 

## Workflow

1. **Plan** -- Use `write_todos` to break the task into steps
2. **Research** -- Delegate research to the `research-agent` using the `task()` tool
3. **Synthesize** -- Combine findings into a comprehensive report
4. **Write** -- Save the final report to `/final_report.md`
5. **Remember** -- Save key takeaways to `/memories/research_notes.md` for future reference

## Rules

- Delegate research to the research-agent rather than searching directly
- After receiving research results, synthesize and write the report yourself
- Consolidate citations -- each unique URL gets one number [1], [2], [3]
- End reports with a Sources section listing all referenced URLs
- Check for relevant skills when asked to create specific content formats (e.g., social media posts)

## File Path Formatting

When referencing file paths in responses, always use backtick formatting like `/final_report.md` -- never use markdown links, since files live in the agent's virtual filesystem and are not clickable.

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add langchain-ai/langgraph-101/agents/deep_agent/AGENTS.md@sha256:298a9153dac41630

The line at the top of this page pins the label git:20260217.63dcabe, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ghzfdl3f4kjrzfg7.svg)](https://markdownregistry.com/a/art_ghzfdl3f4kjrzfg7)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Feb 17, 2026.

versioncommittedcommitsizeaudit
git:20260217.63dcabe latest2026-02-17 63dcabe 1,152 BA view

Audit of the latest version

A  14 of 14 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Size between 200 bytes and 200 KB (1152 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

langchain-ai/langgraph-101 · 707 stars · license MIT · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ghzfdl3f4kjrzfg7
GET https://markdownregistry.com/api/v1/resolve?ref=langchain-ai/langgraph-101/agents/deep_agent/AGENTS.md
GET https://markdownregistry.com/api/v1/blob/298a9153dac41630130f8b18307a65b9a9cc56a235710f71d8e21dfce3fd3bf5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: how to write a good AGENTS.md · AGENTS.md vs CLAUDE.md · which agent file does what.

More from langchain-ai/langgraph-101

linkedin-post SKILL.md skill
langchain-ai/langgraph-101 · agents/deep_agent/skills/linkedin-post/SKILL.md · Write a LinkedIn post based on research findings or a given topic. Use this skill when asked to create LinkedIn…
git:20260217.63dcabe · audit A · 707 stars
twitter-post SKILL.md skill
langchain-ai/langgraph-101 · agents/deep_agent/skills/twitter-post/SKILL.md · Write a Twitter/X post or thread based on research findings or a given topic. Use this skill when asked to create…
git:20260217.63dcabe · audit A · 707 stars

Every file in langchain-ai/langgraph-101

Browse by kind, by grade A, or by owner.