Sato Hub
← Skills

managed-deep-agentsskills.sh · langchain-ai

7,972 installs

"INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith. Walks a user through their first agent end to end — interviewing them about what they want to build, mapping it onto what MDA can actually do, then scaffolding and deploying it. Covers the file-based project layout; define_deep_agent / defineDeepAgent; instructions, skills, memory, identity, tools, MCP server

Executes fetched or decoded codeSchedules itself to run repeatedly
Hosts contacted: mcp.notion.comwww.harborframework.com
Credentials it expects: ANTHROPIC_API_KEYOPENAI_API_KEYMDA_INGRESS_SECRETACME_API_KEYGITHUB_CLIENT_SECRETSLACK_SIGNING_SECRETSLACK_BOT_TOKENLANGSMITH_API_KEY
Evidence lines
  • executes_fetched_code — SKILL.md: `mda evals init` initializes the workspace and prints the pinned `harbor run` handoff; it does not run trials. `mda evals compile` is now an internal Harbor plu
  • executes_fetched_code — SKILL.md: | `mda evals init` | Initialize the Harbor eval workspace and print the run handoff. Alias: `eval`. |
  • schedules_persistence — SKILL.md: schedules/<name>.py # Managed cron schedules
  • schedules_persistence — SKILL.md: cron="0 8 * * 1-5",
  • schedules_persistence — SKILL.md: Define **exactly one** of `prompt` (turned into a user message) or `input` (a structured LangGraph input). `cron` must be a standard five-field expression; with
  • schedules_persistence — SKILL.md: `mda deploy` reconciles schedules after the deployment is live — it deletes MDA-owned crons and recreates them from the current files, so deleting a file and re
  • schedules_persistence — SKILL.md: schedules/** -> LangSmith cron jobs, after the deployment is live

Our disclosure is a static description of what the skill declares and does; it is not a safety verdict. Source record: www.skills.sh/langchain-ai/langchain-skills/managed-deep-agents.

Install

npx skills add langchain-ai/langchain-skills@managed-deep-agents

Copied from the registry's documented install form. Read the disclosure above first; it is the whole point of this page.

Observed record

2 weekly observations since 2026-09-28. Installs 7517 → 7972.

The skill's content changed 1 time(s): 2026-10-05. A changed SKILL.md is the security signal that matters — re-read it.

Cite this page

Sato Hub. "managed-deep-agents — skill disclosure on Sato Hub." Sato Hub, updated 2026-10-23, accessed 2026-10-23. https://satohub.ai/skills/skillssh%3Alangchain-ai%2Flangchain-skills%2Fmanaged-deep-agents

Data last refreshed 2026-10-23; this page is rebuilt daily. Citations carry the date so a reader can tell which snapshot a claim came from. Catalog data is licensed CC-BY-4.0.