Scout
DocsBlogToolsContact
Scout + Claude Code● Claude Code asks an agent

Claude Code, with the restof your agents.

Ask your connected agents for work from inside Claude Code. Follow the returned reference, or opt in to session delivery.

Local developer pilot · validate your installed client

Use supported agents you have installed, authenticated and connected.

Set it upLet your agent do itClaude Code reads the setup for you
claude — ~/dev/app

✻ Welcome to Claude Code!

cwd: ~/dev/app

> /scout:ask --project /path/to/project --harness codex --notify "Review the diff. Do not edit files."

⏺ scout - ask (MCP)(to: "codex", body: "Review the uncommitted diff…")

⎿working…queued · ref 8c41

⏺ scout - invocations_wait (MCP)(ref: "8c41")

⎿working…completed · 52s

⏺ Codex replied: no findings in the uncommitted diff.

Continue on the same ref with /scout:ask --ref 8c41.

>

? for shortcuts

Claude Code calls Scout

Available

Plugin, MCP (local), CLI

Ask from Claude Code ↓

Scout runs Claude Code

Available

tmux (claude_stream_json fallback)

Replies reach your open session

Partly

Opt-in: the Scout channel delivers replies into the session

Let replies arrive in your open session ↓
01

Start here

  1. 01 · Connect

    Get one route working

    Check the prerequisites and access gates, then get one documented route working before asking for work.

    Follow the setup →
  2. 02 · Try

    Your first useful task

    From Claude Code, ask Codex for a second opinion on one small change. Request findings before any edits.

    Name the project and keep the request small. Asking for no edits describes the task; it does not restrict the agent’s permissions.

  3. 03 · Read

    Wait for the answer

    Keep the returned reference. Check the work’s status and read the completed response; a queued receipt is not the answer.

    Check what success looks like →

Before your next ask

Where will the reply appear?

Keep the returned reference and retrieve the completed response through your configured Scout interface. Automatic delivery into this open session is not established by this guide.

What if the answer hasn’t arrived?

Inspect the existing task before submitting another one. A wait timeout does not establish that work failed. If it needs access or input, resolve that condition before continuing.

How do I follow up?

Continue using the returned reference or exact session handle supported by this integration. Keep it with the findings so your next question follows the same work.

Can Scout run this integration, or only receive asks from it?

These are separate capabilities. Check the supported directions on this page. Connection alone does not establish that Scout can launch the integration or reach an existing session.

02

Set it up

Fastest

Give this to Claude Code

Connect yourself to Scout for me. Read openscout.app/claude/agents.md and follow it step by step: check the prerequisites first, ask me before any step that needs a token or other credential, and finish with its verification step. Tell me what you verified.

  1. reads agents.md
  2. checks prerequisites
  3. asks before any credential
  4. runs the verification

You need

  • OpenScout installed and a healthy local broker (scout doctor).
  • Claude Code installed and authenticated on the Scout machine.
  • At least one other agent Scout can reach: listed by scout who, or a harness available in scout runtimes --json. Its provider usage and permissions still apply.
  • To route by project, an absolute path to a repository you authorize that agent to read. The path must exist on the Scout machine.

Before any door

  1. 00

    Check the broker and your agents

    Run these commands in a terminal on the Scout machine. Doctor should report a healthy broker; who lists the agents you can ask. Resolve installation or authentication failures before requesting work. See Install Scout below if the CLI is missing.

    scout doctor
scout who
calls Scout

Ask from Claude Code

Start here
  1. 01

    Install the Scout plugin

    Run these commands inside Claude Code after Scout is healthy.

    /plugin marketplace add oscout/claude-scout
/plugin install scout@openscout
  2. 02

    Ask an agent from Claude Code

    Inside Claude Code, list your agents, then ask one by name. The receipt comes back right away; the answer follows in the same Scout conversation. To route by project instead, use --project with an absolute path, and --harness to choose the runtime. In a terminal without the plugin, scout ask takes the same arguments. Save the ref from the receipt.

    /scout:who
/scout:ask --to <agent> "Review the uncommitted diff. Report correctness issues with file and line references, or say no findings. Do not edit files or run tests."
  3. 03

    Follow the returned work

    In a terminal, replace RETURNED_REF with the exact ref from the receipt. Wait for the result before deciding what to change. Then use the same ref for a follow-up. A timeout means you should observe the existing request again; it is not a reason to dispatch another review.

    scout wait RETURNED_REF --timeout 120
scout ask --ref RETURNED_REF "Explain the highest-priority finding, or confirm there were no findings. Do not edit files or run tests."
your open session

Let replies arrive in your open session

03

Done when

  • Success means the request returned a ref, scout wait reported completed with the agent’s reply, and a follow-up used that same ref.
  • For a review, the reply should contain file/line findings or explicitly say there were none.

A queued receipt, timeout, or request for permission is not a completed review.

04

If it breaks

The receipt is queued, or the wait times out
Keep the returned ref and run scout wait on it again. Check the agent’s harness for an authentication or permission request. Report the observed state if blocked; do not create another request just to check progress.
The agent cannot see the intended changes
Confirm that the absolute project path points at the intended checkout on the Scout machine. Include the desired branch or diff scope in the prompt. A shared checkout can change while the agent reads it; keep it stable for the duration of the review.
Scout is not found or cannot connect
Check scout on PATH and run scout doctor in the same environment as the client. A desktop app may have a different PATH from your terminal.
Requested runtime is unavailable
Inspect scout runtimes --json and finish that runtime’s setup. Do not silently choose a different harness or model.
05

Where it stops

  • This is a local developer pilot. Client permissions and runtime availability still apply.
  • Installing a host package does not provision hosted access.
  • Scout stores coordination records locally. Your selected model provider and any enabled remote bridges may receive task data. Review the privacy and data-ownership documentation before choosing what to send.
  • A review is evidence for your decision, not an automatic approval or merge. OpenScout is intended for high-trust local developer pilots.
  • High-trust local developer pilots. Connection traffic may contain project paths, instructions, messages, and agent results. Data and privacy.
06

For agents

agents.mdThe setup contract your agent follows. Same content as this page.integration.jsonDirections, gates and steps as data.