# Agency Install Kit: install one agent workflow in two weeks, with a binder a script can check

> Five paid packs and the free Readiness Self-Check, tied into one two-week install by a new Install Binder: plain files for readiness, one workflow, agent owners and tested pauses, a gate register, a reach inventory, a cost cap, a dry run with refusal cases, a scorecard with kill rules and a run sheet with an off switch. A fifteen-check script names every missing decision, and the owner's go-live yes is tied to the binder's sha256.

- URL: https://paperchasewebb.ai/bots/marketplace/items/agency-install-kit-one-workflow-in-two-weeks/
- Type: Bundle
- Category: Solo business
- By: PaperChaseWebb
- Works with: Claude Code, Codex, Grok Bot, Hermes (named in the listing); A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block; the scripts were tested on Linux with Python 3.13, the agent files were not loaded inside each harness
- Price: $99 USD
- Difficulty: Intermediate
- Setup time: 30 min
- Time to result: A checked binder for one workflow in about two weeks of part-time work
- Format: Markdown (.md) file, agency-install-kit-one-workflow-in-two-weeks.md
- Version: 1.0, updated 2026-10-28
- License: Use on your own machines and on installs you do for clients and teams. Do not resell or republish the kit itself.

## What you end up with

One agent workflow switched on with every install decision written down, checked and signed by the owner, in a folder the client keeps.

## What you get

- Six packs in full: Agency AI Ops Workbook, Governed Agent Teams, Local Services Agent Kit, Agency Open-Loop System, Outreach Without Spam and the free Agent Readiness Self-Check
- The Install Binder (only in this kit): one folder of plain files from readiness to go-live, with templates
- A sprint map: each phase, its deliverable, its binder file and the pack it comes from
- A two-week day-by-day plan where the owner reads one file every day
- binder.py: set up a binder, owner go-live approval at a terminal tied to the binder sha256, and verify
- binder_check.py: fifteen read-only checks, with a seeded test binder (15 findings, then 0)
- A skill file for Claude Code, Codex and Hermes, an AGENTS.md snippet and a Grok Bot rules block
- Ten prompts, a failure table, a worked example and notes on handing the binder to a client
- A look at seven agency starter kits and threads, with sources

## Who it is for

Agencies that want to sell and run agent installs, and small business owners who want to install one workflow themselves, with the owner's yes on every risky step.

## Tools needed

- Grok Bot, Claude Code, Codex or Hermes: the agent that helps fill the binder and runs the workflow; it reads the skill file, AGENTS.md snippet or rules block
- Python 3: runs binder.py (init, hash, owner approval, verify) and the fifteen-check checker; standard library only, no network
- The business owner: names every agent's owner, tests each pause, approves gates and gives the go-live yes at their own terminal
- You need: Any of Grok Bot, Claude Code, Codex or Hermes
- You need: Python 3.9 or newer
- You need: An owner who can spend about an hour a day on the install for two weeks

Cost to run: The kit is the only purchase. The checker and approval script use no model tokens; the workflow itself costs whatever your agent and connectors normally cost, capped in the binder.

## What is in the bundle (6 packs)

| Pack | Format | Separate price |
|---|---|---|
| [Agent Readiness Self-Check: score one workflow before you hand it to an AI agent](https://paperchasewebb.ai/bots/marketplace/items/agent-readiness-self-check-score-one-workflow-free.md) | Prompt pack | Free |
| [Agency AI Ops Workbook: the Install sprint, self-serve](https://paperchasewebb.ai/bots/marketplace/items/agency-ai-ops-workbook-install-sprint-self-serve.md) | Prompt pack | $39 |
| [Governed Agent Teams: subagent personas, authority maps and handoffs](https://paperchasewebb.ai/bots/marketplace/items/governed-agent-teams-subagent-personas-authority-maps-and-handoffs.md) | Prompt pack | $39 |
| [Local Services Agent Kit: booking, reminders, quote follow-up and review asks, with the owner's yes on every message](https://paperchasewebb.ai/bots/marketplace/items/local-services-agent-kit-booking-reminders-follow-up-review-asks.md) | Bot template | $39 |
| [Agency Open-Loop System: meeting notes to tasks, client follow-ups and a weekly open-loop report](https://paperchasewebb.ai/bots/marketplace/items/agency-open-loop-system-meeting-notes-to-weekly-report.md) | Prompt pack | $39 |
| [Outreach Without Spam: score first, research the pitch, draft in small batches, a person sends](https://paperchasewebb.ai/bots/marketplace/items/outreach-without-spam-ai-prospecting-with-a-human-send.md) | Prompt pack | $29 |
| Bought separately | | $185 |
| The bundle | | $99 |

## How it works

1. **Run the tests.** Copy the agency-install-kit folder and run sh test_all.sh. Expected: 15 findings on the seeded binder and 0 on the fixed one, 15 of 15 single faults caught alone, checker tests 22 passed, approval tests 19 passed, exit 2 on a missing folder.
2. **Score the workflow.** Take the free Agent Readiness Self-Check with prompt 1 and run binder.py init. Expected: readiness.csv with evidence, and a clear answer on whether approvals, owners and security are ready.
3. **Pick, map and gate.** Days 2 to 6: pick one workflow with the workbook, write agent cards, list every connector and write the gate register. Expected: binder.json, agents.csv, reach.csv and gates.csv, with leftover access removed.
4. **Build and dry run.** Days 7 to 9: build from the Local Services Agent Kit, the Agency Open-Loop System or your own design, in draft mode, and run ten or more cases including refusals. Expected: tests.csv all passed, and the owner has stopped each agent once.
5. **Go live on the owner's yes.** Day 10: write the scorecard and run sheet, run binder_check.py until only B15 is left, then the owner runs binder.py approve at their own terminal. Expected: binder.py verify prints approved; any later edit drops the workflow back to draft until a new yes.

## Sample prompt: Start an install (Grok Bot, Claude Code, Codex, Hermes)

```
Interview me with the Agent Readiness Self-Check for the workflow <name>. One question at a time. Propose a score from 0 to 3 for each of the eight areas with the evidence you would point to, then write readiness.csv.
Tell me which of approvals, owners and security are under 2, and what we fix first.
```

Prompt 1 of 10.

## Sample prompt: Before go-live (Grok Bot, Claude Code, Codex, Hermes)

```
Run binder_check.py on the binder and show me the output. For each finding except B15, propose the smallest fix and wait for my yes before editing.
When only B15 is left, print the binder hash, tell me in five lines what I am approving, and stop.
```

Prompt 9 of 10.

## Free preview of agency-install-kit-one-workflow-in-two-weeks.md

````markdown
# Agency Install Kit: install one agent workflow in two weeks, with a binder a script can check

Version 1.0, 2026-10-28. By PaperChaseWebb. A bundle of five paid packs and one free self-check, plus a new Install Binder that ties them into one two-week sprint. The binder comes with a setup and approval script, a read-only checker with fifteen checks, templates, a seeded test binder, ten prompts and the tests, all Python 3 standard library. Works with Claude Code, Codex and Hermes through a skill file and an AGENTS.md snippet, and with Grok Bot through a rules block. Tested as described in section 10: everything ran on Linux with Python 3.13, including owner approvals typed at a pseudo-terminal. The skill file, snippet and rules block were not loaded inside the harnesses for this release, and the kit has not been run on a real client install. Each is marked where it matters.

Most agency starter kits sell a pile of parts: workflow templates, a proposal, a pricing sheet, some cold emails. The parts are fine. What goes wrong is the install itself. Nobody wrote down who owns the agent. The pause was never tried. A send step had no approver. An old connector from last year still has write access. The test set was five happy cases. Cost was a guess. Then the agent goes live on a Friday and the first person to notice a problem is the customer.

This kit is built around that install. It gives you the method (the Agency AI Ops Workbook), the readiness score that starts it (the free Ag
````

## Worth knowing

- The checker checks that each install decision was made and written down. It cannot tell whether a pause really works or a test really passed, and it does not judge the quality of the agents' work; the dry run and scorecard do that.
- The skill file, AGENTS.md snippet and Grok Bot rules block were not loaded inside Claude Code, Codex, Hermes or Grok Bot for this release, and the kit has not been used on a real client install. The test binder is a made-up business. Linux only; Windows was not tested.
- The approval script refuses piped input and the environment variables Claude Code, Codex, Hermes and Grok Bot set. That stops an agent approving by mistake; it is not a lock against someone with the same account.
- On 2026-10-28, on Linux with Python 3.13.5: binder_check.py gave 15 findings on the seeded binder (each check once) and 0 on the fixed one, caught 15 of 15 single faults with only its own check, wrote nothing, and exited 2 on a missing folder, missing gates.csv or broken binder.json; checker tests 22 passed, 0 failed; approval tests at a pseudo-terminal 19 passed, 0 failed.
- The bundle contains the versions listed on this page on the day you buy. Each included pack keeps its own notes and limits.

## Questions

**How is this different from the Agency AI Ops Workbook?** The workbook is the method on paper. This kit includes it in full and adds the Install Binder: the same decisions as files a script checks, an owner approval tied to the binder hash, two ready first workflows, the team structure and the outreach pack for finding install clients.

**Do I need n8n, Zapier or a particular tool?** No. The binder is plain CSV, JSON and Markdown, and the workflow can run in Grok Bot, Claude Code, Codex, Hermes or anything else you name in binder.json.

**Can the agent approve go-live itself?** No. binder.py approve refuses piped input and refuses to run inside the agent harnesses it recognizes. The owner types their name and part of the hash at their own terminal.

**What happens if someone changes a gate after go-live?** The binder hash changes, binder.py verify fails and the checker flags B15. The workflow should drop back to draft mode until the owner approves the change.

**What if I want the install done with me?** Book a call on the paperchasewebb.ai homepage about the $5,000 Install sprint. We can pick up from a binder you started.

## How to buy

$99 one time at https://paperchasewebb.ai/bots/marketplace/items/agency-install-kit-one-workflow-in-two-weeks/. Stripe checkout, then an instant download page; the download link is also in your emailed receipt.

Seller: PaperChaseWebb Inc., mgmt@paperchasewebb.com