# Clean Handover: keep running if your agent provider stops tomorrow

> A free kit for anyone who pays for agent or automation work, and for the providers who do it. List every account, data store, automation, schedule and bill the work touches in one register. A checker finds each place the client would be stranded: an account in the provider's name, no client admin, an export never tested, a job with no runbook or off switch, a bill the provider pays. Then it turns every gap into one decision sheet the client owner answers in a single reply.

- URL: https://paperchasewebb.ai/bots/marketplace/items/clean-handover-keep-running-if-your-provider-stops/
- Type: Prompt pack
- Category: Solo business
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Grok Bot, Hermes (named in the listing); One Python script, a register template, a fictional bakery example with a runbook, and agent rules for each harness. Tested on Linux
- Price: Free USD
- Difficulty: Beginner
- Setup time: 15 min
- Time to result: First scan in about 20 minutes
- Format: Markdown (.md) file, clean-handover-keep-running-if-your-provider-stops.md
- Version: 1.0, updated 2026-11-03
- License: Personal and commercial use.

## What you end up with

A client who could keep running tomorrow, and a dated plan of only the handover steps they approved.

## What you get

- The method: one register, one test (could the client keep running tomorrow?), one reply, one plan with done tests
- handover.py: 4 register checks, 6 gap checks and 4 reply checks across accounts, data, automations, schedules and bills
- A one-reply decision sheet with options for every gap, including an honest accept that is dated and signed in the plan
- Owner decisions refused inside an agent session, from anyone but the client owner, or after the register or a runbook changes
- AGENTS.md, CLAUDE.md, a Grok Bot standing order and a Hermes skill, a fictional example, and 28 tests

## Who it is for

Owners who want proof they are not locked in, and providers who want to hand every client a clean exit.

## Tools needed

- Python 3.8 or newer: handover.py: register check, gap scan, decision sheet, owner reply and handover plan; standard library only
- Grok Bot, Claude Code, Codex or Hermes (optional): drafts the register and runbooks, runs the scan and sends the sheet under AGENTS.md; never records decisions, signs in or moves an account
- You need: Python 3.8 or newer
- You need: A list of the accounts, automations and bills the work touches

Cost to run: Free. Python is free.

## How it works

1. **Run the example.** Unpack the file and run python3 handover.py scan example/handover.json --today 2026-11-03. Expected: 9 gaps across 6 systems; the order inbox agent is clean.
2. **List your systems.** Fill in templates/handover.json with every account, data store, automation, schedule and bill, and write a runbook for each job. Expected: handover.py check shows 0 errors.
3. **Scan and send.** Run scan, then sheet, and send decisions.md to the client owner. Expected: decisions.md with one numbered item per gap.
4. **Reply once, then plan.** The client owner answers in one line at their own terminal, then run plan and work each step with the client watching. Expected: handover-plan.md with only the approved steps, each with a done test.

## Sample prompt: Quarterly handover check (Grok Bot, Claude Code, Codex, Hermes)

```
Follow AGENTS.md. Ask what changed, draft updates to handover.json and runbooks/ for review, run handover.py scan, and if there are gaps, run sheet and send the client owner decisions.md with the reply line. Do not sign in anywhere, move an account or write a secret into the folder.
```

One prompt.

## Free preview of clean-handover-keep-running-if-your-provider-stops.md

````markdown
# Clean Handover

**If your provider stopped tomorrow, could you keep running? One register of every account, export, automation and bill the work touches, a checker that finds each place the answer is no, and one reply to close the gaps.**

Version 1.0, 2026-11-03. By PaperChaseWebb Inc. Free. Works with Grok Bot, Claude Code, Codex and Hermes, or by hand. Python 3.8 or newer, no installs.

## The problem

Agent and automation work piles up quietly. A host signed up on the provider's card. A customer list the client cannot export. A weekly job nobody on the client side knows how to pause. None of it matters until the contract ends, the provider is unreachable, or something breaks at 6 AM. Then it is the only thing that matters.

A good provider wants this list as much as the client does. It is the clearest proof that the client stays because the work is good, not because leaving is hard.

## What you get out of it

- One register of every system the work touches, with who owns it, who can administer it, how to export it, how to switch it off and who answers for it.
- A scan that names every gap by system, in plain words.
- One decision sheet with a numbered item per gap and a reply line like `1: test 2: transfer 3: accept`. Answer in one message.
- A handover plan of only the steps the client approved, each with a done test the client checks themselves.

## Who it is for

Owners who pay for agent or automation work and want to know they are not locked in. Providers and small
````

## Test record

- Date: Nov 3, 2026
- What was run: tests/test_handover.py (28 tests) unpacked from the pack file and run fresh on Linux, Python 3.8, 3.9, 3.11, 3.12 and 3.13; scan, sheet, reply and plan on the fictional example.
- Result: 28 passed, 0 failed on all five versions; the example gives 9 gaps across 6 systems with the order inbox agent clean; decisions refused in agent sessions, without a terminal, for the wrong name and after a register or runbook edit; the register is never modified.
- Not run: macOS or Windows. Real client systems. A live Grok Bot, Claude Code, Codex or Hermes session.

Copied from this item's dated test notes. What was not run stays in.

## Worth knowing

- It knows only what the register lists. Walk it with both sides before you trust the scan.
- It checks that a runbook file exists, not that it is good, and it never signs in, so people confirm each done test.
- On 2026-11-03: 28 tests passed on Python 3.8, 3.9, 3.11, 3.12 and 3.13 on Linux, run from the files unpacked out of the pack. Agent rules guide; they were not loaded inside each harness for this release.
- Not legal advice, and not a substitute for the exit terms in a contract.

## Questions

**Is this for the client or the provider?** Both. The client owner decides every item. A provider can run it at onboarding to show the client they can leave cleanly at any time.

**Does it store passwords?** No. The register says where access lives and who holds it. AGENTS.md forbids writing a secret into the folder.

**Can my agent do the transfers?** No. It drafts the register, runbooks and plan. Recording decisions is refused inside an agent session, and the tool never signs in or changes an account.

**What should I pair it with?** Reach Inventory ($19) lists every connector your agents hold, which feeds the register, and Retainer Scope Sheet ($29) itemizes what the monthly covers.

## How to get it

Free sample. Download it directly at https://paperchasewebb.ai/bots/marketplace/items/clean-handover-keep-running-if-your-provider-stops/, no signup.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com