Skip to main content
Documentation
Docs / Products / Handoffs
Agent setup

Coordinate

Handoffs

Package the objective, repository state, decisions, evidence, and blockers so another agent can see where to continue.

Last updated August 22, 2026

Continue the work without reconstructing the conversation.

Use cases

Keep the starting point precise

Include repository state and the next bounded action.

Preserve what was learned

Carry decisions, failed approaches, and constraints into the next session.

Challenge unsupported certainty

Keep missing evidence and stale references visible in the continuation record.

How it works

  1. 1

    Capture the current state

    Supply the objective, repository reference, decisions, and evidence.

  2. 2

    Validate the handoff

    Review unsupported claims, missing information, and freshness.

  3. 3

    Give the recipient a next step

    Use the checked packet to continue within the stated constraints.

Quickstart

Open Handoffs in the console, provide the required inputs, and start an organization scoped run.

Inputs

  • repository binding
  • state claims with provenance
  • scope contract
  • open blockers
  • recipient answers

Outputs

  • continuation capsule
  • readiness gate result
  • freshness and drift report
  • bounded action packets
  • continuity score
Open Handoffs

MCP

Call Handoffs from a compatible agent with the preferred public tool name.

bashReady
symbolic.handoffs.run

The previous internal service identifier remains accepted for compatibility, but new integrations should use this product name.