- Home
- Skills
- Productivity
- handover
handover
Write a verified, agent-facing HANDOVER.md so the next AI session can resume your in-progress work cold.
Free
Works with the AI Agents you already use
handover
Example session with this skill installed
Write a handover so I can pick this up next week.
- Read your context and instructions
- Compiled the handover
Writes src/billing/HANDOVER.md with the TL;DR state (branch, HEAD SHA, pushed or not, current step and blocker), ordered next actions with commands, agreed decisions with rationale, a code map with line refs and the branch commit log. Unchecked claims are marked UNVERIFIED. Adds a one-line pointer to the nearest README and asks before committing.
Connects securely to your tools. The creator never sees your data.
About this skill
Pause any piece of work and let a fresh AI session pick it up cold, without you re-explaining anything.
The skill writes a dense HANDOVER.md next to the work, aimed at the next agent rather than at you. When you come back, the agent reads it and summarises where things stand.
What goes in it
- TL;DR state: goal, branch, worktree, HEAD SHA, whether it's pushed, the current step and what it's blocked on.
- Next actions, in order, with exact commands.
- Agreed decisions with their rationale, so the next agent doesn't re-litigate them.
- A code map with file and line references, plus gotchas, constraints and the branch's commit log.
Why it's trustworthy
It runs git and your tests before writing, and every claim it can't check is marked UNVERIFIED: with how to check it. A wrong handover is worse than none.
How it behaves
- Updates an existing handover in place instead of piling up dated copies.
- Adds a one-line pointer to the nearest README.
- Asks before committing and never pushes.
- When you resume, it checks the doc against
git logand flags anything that has drifted.
Captures working state for one piece of work, not durable team documentation. Doesn't commit or push without asking.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account
Requires
Permissions
File Scopes
Runs git and the repo's own test/typecheck commands to verify state. Asks before any commit; never pushes.