Handover
About
Shared, versioned context that humans and AI agents can review and continue.
Details
- Author
- 44-pixels
- Categories
- AI
Jump to
Setup
Install Handover in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/44-pixels/handover-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Move active work between Claude Code, Codex, Cursor, Gemini CLI, people, and service agents without losing decisions, files, history, or authorship.
- Human research index
- Agent-readable production index
- Versioned repository index
- Citation metadata
- Run and submit an independent benchmark result
- Interactive demo
- Continue the demo in your workspace
- Demo workflow and verification notes
- Agent-readable manifest
- Raw Markdown
- Raw SQL
- Evidence JSON
The receiver prompt requires the next actor to inspect the evidence, separate verified and unverified state, identify blockers, and state one bounded next action before continuing. Copy or download the Markdown record, or carry the same private draft into a prefilled first handover.
- Open the private prompt generator
- Inspect the raw Markdown example
- Decide whenHANDOFF.mdis enough
Codex's built-in import is the right first choice for a one-time move of supported Claude Code setup, projects, memories, and recent chats. Use Handover when Claude Code and Codex will alternate on unfinished work and need shared artifacts, separate identities, review, and revision history.
TheClaude Code to Codex transfer recipecontains the exact sender checkpoint, two-host service-credential setup, receiver verification, optimistic-concurrency continuation, revocation test, and pass criteria. Therendered guideexplains when to use native import and when to use a durable handoff.
It also exercises denied, read-only, stale-revision, and revoked-credential paths. Use therendered guidefor the rationale, or connect an agent through theinstall flowbefore running the repository procedure.
For a smaller local handoff, start with theMarkdown checklist. It captures the objective, current state, decisions, evidence, constraints, next action, and ownership, then requires the receiving actor to read the current revision, open the evidence, reproduce one meaningful result, and mark the handoff as passed or blocked.
Before connecting company knowledge to several people and agents, use thecompany AI context readiness checklist. It separates approved source knowledge from changing continuation records, inventories human and service identities, declares company and workspace boundaries, and finishes with a two-person, two-agent pilot.
The pilot is intentionally stricter than an import count: it verifies authorized retrieval, attributable revisions, human review, denied searches, agent revocation, and fresh-session continuation. Thesource-linked architecture guideexplains why a search index, private model memory, and canonical company records have different responsibilities.
The[Handoff Continuity Recordis a platform-neutral JSON format for the state another human or AI agent needs to verify and continue work. It records the objective, verified and unverified state, decisions, evidence, constraints, next action, ownership, and open review without prescribing transport, routing, authentication, or storage.
- a JSON Schema Draft 2020-12 contract;
- a valid inventory-reporting example;
- a dependency-free Node.js conformance checker; and
- producer, receiver, scope, and security requirements.
…
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
