Grok Bot Agency Pack: 5 client-ready templates
by PaperChaseWebb
Five agent desks for the work an agency repeats for every client: Client Intake, Scope and Proposal, Kickoff and Access, Weekly Client Report, and a separate Delivery Reviewer. Each comes with a persona, an authority map, a standing order or event routine, a handoff packet and five test cases. Plus the agency rules block, a client isolation rule, and two full packs: Grok Bot Templates and the Agency Open-Loop System.
- Price
- $49
- Difficulty
- Intermediate
- Setup
- 1 hr
- Format
- .md file
grok-bot-agency-pack-five-client-ready-templates.md · 92 KB · instant download after checkout · $78 if bought separately
Want this built for you instead? We can build it for you.
What you end up with
Each new client moves from inquiry to proposal to kickoff to weekly report with agents doing the drafting and checking, nothing reaching the client before a person approves it, and one client's data kept out of another's work.
What you get
- Five agency desk templates in one index file: Client Intake, Scope and Proposal, Kickoff and Access, Weekly Client Report, Delivery Reviewer
- For each desk: persona, authority map (can, ask first, never), standing order or event routine, handoff packet and five test cases with expected results
- An agency rules block to paste into every desk and an approval request format
- The client folder layout and an isolation rule enforced in three places
- An authority map for all five desks on one page
- A step-by-step install for one client and a four-week scorecard
- Harness notes for Grok Bot, Claude Code, Codex and Hermes, and a failure table
- Grok Bot Templates in full: 8 personas, standing orders, event routines and handoffs
- The Agency Open-Loop System in full: meeting notes to tasks, follow-ups you approve, weekly report
- A competitor teardown, credited sources, and when to hire the $5,000 Install sprint instead
Who it is for
Owners and operations leads at agencies of one to fifteen people who want agents doing the preparation work on client accounts without anything reaching a client unread.
Works with
Solid chips: the agent is named in this listing's own tools list. Dashed chip: Plain Markdown, so it also pastes into other agents such as Grok Bot, Hermes, OpenClaw or Muse. We list those as compatible by format only, not as tested.
What is in the bundle (2 packs)
| Pack | Format | Separate price |
|---|---|---|
| Grok Bot Templates: personas, standing orders and handoffs | Prompt pack | $39 |
| Agency Open-Loop System: meeting notes to tasks, client follow-ups and a weekly open-loop report | Prompt pack | $39 |
| Bought separately | $78 | |
| The bundle | $49 (you save $29) |
Tools needed
Cost to run: The pack is the only purchase. Uses the Grok Bot or other agent harness you already have.
Time to result: About an hour for the first desk and its test set, then one desk at a time over two weeks
How it works
Set up one client folder
Make clients/<code>/ and fill CLIENT.md and SCOPE.md by hand from a real contract.
Expected: One folder the desks can read, with voice, allowed claims and approvers written down.
Start with the Reviewer
Paste the rules block and the Delivery Reviewer persona into its own bot or session. Run its five test cases.
Expected: Five of five pass before it reviews real work.
Add the Weekly Report desk
Run it in draft mode for one report day and compare its draft with the one your account lead would write.
Expected: A sourced draft the Reviewer marks READY FOR OWNER or FIX FIRST with quoted lines.
Add Intake and Scope
Point Intake at your inquiry label or form with an event routine; give Scope the price sheet and a weekday standing order.
Expected: Briefs with fit scores and proposal drafts, nothing sent.
Add Kickoff for the next signed client
Test the isolation rule with a fake second client folder before any second client goes live.
Expected: A client folder, kickoff agenda and access checklist, with no passwords stored.
Sample prompt from the pack
You are the Delivery Reviewer. You did not write this draft and you never rewrite it. Check it against CLIENT.md, SCOPE.md and the source files. Return READY FOR OWNER, FIX FIRST or STOP, with pass or fail for voice, claims, numbers, scope, other clients and asks, quoting the exact line for every problem.
Template 5 of 5. The full persona, checks and test set are in section 9, and free as a sample.
Read the new LOG.md lines since yesterday and compare each request with SCOPE.md. Write one packet: in scope, out of scope with a change request draft, unclear. Price only from the price sheet. Do not send anything; tell me only if something is out of scope or unclear.
From template 2, run as a weekday standing order.
Free preview of the file
# Grok Bot Agency Pack: 5 client-ready templates Version 1.0, 2026-10-27. By PaperChaseWebb. Plain Markdown. Works with Grok Bot, Claude Code, Codex and Hermes. Five agent templates for the work an owner-led agency repeats for every client: taking in a new inquiry, scoping it, setting up the client's workspace, reporting each week, and checking work before a client sees it. Each template is a full desk: a persona, an authority map, a standing order or event routine, a handoff packet to the next desk, a test set with expected results, and notes for running it in each harness. This file is the bundle index and the five new templates. Two existing packs follow it in full, because the templates plug into them: - Grok Bot Templates: personas, standing orders and handoffs (the general setup for scheduled Grok Bots, memory rules and the four approval gates). - Agency Open-Loop System (meeting notes to tasks, client follow-ups you approve, and the weekly open-loop report). ## Contents 1. Who this is for and what it does not do 2. How the five desks fit together 3. The agency rules block (paste into every desk) 4. The client folder and the isolation rule 5. Template 1: Client Intake Desk 6. Template 2: Scope and Proposal Desk 7. Template 3: Kickoff and Access Desk 8. Template 4: Weekly Client Report Desk 9. Template 5: Delivery Reviewer 10. The agency authority map (all five desks on one page) 11. Installing the desks for one client, step by step 12. Running the test sets 13. Ha
Worth knowing
- Not legal advice and not a contract template. Have your scope and terms reviewed by someone qualified.
- Nothing in this pack promises hours saved, revenue or any client result. The four-week scorecard is how you find out.
- Test cases were dry-run against an invented client folder on 2026-10-27 as a design check. Run the test sets in your own harness before a client sees anything.
- The bundle contains the versions listed on this page on the day you buy. Each included pack keeps its own notes and limits.
Questions
Do I need Grok Bot?
No. The desks are written for Grok Bot routines first, and section 13 shows how to run each one in Claude Code, Codex or Hermes. The packet formats are the same in every harness.
Will a desk ever send something to a client?
No. Every desk reads, drafts, checks and files. Sending, posting, signing, spending and changing a client's accounts are approval gates with a named person, and the pack has you remove those permissions in the tool wherever it allows.
How does it keep clients apart?
One folder per client, one folder per session, and the Reviewer checks every draft for other clients' names, codes and data. A match is a STOP.
How is this different from Grok Bot Templates?
Grok Bot Templates covers general personas and how scheduled bots work. This pack adds five desks built for client work, with authority maps and test sets, and includes Grok Bot Templates and the Agency Open-Loop System in full.
What if I want it set up for me?
Book a call on the paperchasewebb.ai homepage about the $5,000 Install sprint, or start with the $39 Agency AI Ops Workbook to do the install yourself.
Details
Version 1.0 · Updated Oct 27, 2026 · Markdown version of this page
License: Personal and commercial use inside your own agency, including running the desks for your own clients. Do not resell, republish or share the files. Download terms
Related
The Delivery Reviewer desk (free sample)
From the Grok Bot Agency Pack: a reviewer desk that checks every client-facing draft for voice, claims, numbers, scope, other clients' data and asks, and returns READY FOR OWNER, FIX FIRST or STOP. Persona, six checks, review format, five test cases and harness notes.
Agency AI Ops Workbook: the Install sprint, self-serve
A two-week workbook for owner-led agencies and small businesses: install one AI agent workflow yourself with the same steps as our $5,000 Install sprint. Discovery and mapping, picking the first workflow from your Self-Check score, an agent card with an owner and a tested pause, data access and a test set, an approval gate register, handoff packets, cost limits, tool vetting, a baseline and stop rule, a dry run, a go-live checklist and a 30-day review. Ten worksheets, 13 prompts with harness notes.
Agent Readiness Self-Check: score one workflow before you hand it to an AI agent
A free self-check for agencies and small businesses. Score one workflow across eight areas (workflow mapped, data access, approval gates, owner per agent, handoffs, cost tracking, security and vetting, measurement) with an evidence rule and three gate rules, read your band and what to do next, plus an interview prompt for Grok Bot, Claude Code, Codex or Hermes, a score sheet and a worked example.
Grok Bot Templates: personas, standing orders and handoffs
A Markdown pack for setting up Grok Bots that do useful work on a schedule: 8 ready-to-paste personas, standing order cards for scheduled routines, event routine recipes, multi-bot handoffs with a decision log and four approval gates, memory rules and a test set.
Agency Open-Loop System: meeting notes to tasks, client follow-ups and a weekly open-loop report
A Markdown operating system for owner-led agencies: turn every meeting into commitments with an owner, a date and a done test, post them where your team works, draft client follow-ups you approve, and get one weekly report of what is still open.
Governed Agent Teams: subagent personas, authority maps and handoffs
A Markdown pack for running a team of coding and research agents with clear limits: 7 subagent personas for Claude Code with Codex AGENTS.md and Hermes skill versions, a Desk Authority Map, three role risk classes, a handoff packet the receiver verifies, an evidence standard, a decision ledger and a reach inventory.
Cross-Harness Relay: Grok Bot, Claude Code, Codex and Hermes on one job
A bot template and teaching guide for running more than one agent harness on the same work. Six seat cards (front desk, planner, builder, reviewer, tester, night shift), a RELAY.md seat map, a relay packet for every handoff, four loop shapes, routine-or-judgment routing with a fallback when limits run tight, a preflight check, the front desk and night shift split with a proof footer, shared memory rules, eight relay drills, a rules block and 14 prompts.