For George's Claude, and for George
One framework your agent follows to set up everything, then keep it running.
Memory that doesn't reset, skills ready to use, a dashboard your team can open, and jobs that run on their own while you approve what matters. Your agent works through it module by module and fills in what only it knows about you, like G's Plan and TOI.
38modules
30ready skills
12templates
1dashboard starter
Start here
Open the Claude desktop app on your laptop, go to the Code tab, start a local session, and paste this:
Read https://andersoncollab.github.io/george-kit/HANDOFF.md and follow it. Work part by part, check each step, batch your questions for me, and stop only for the steps marked GEORGE.
- Your agent reads module 00 and lays out the order.
- It fills the blanks from what it already knows about you and asks you once, in a batch.
- You do only the GEORGE steps: sign-ups, approvals, choosing people.
- You and Trevor iterate. New versions land as proposals your agent shows you. Nothing you changed gets overwritten.
The modules
Click a module to read it. Agents fetch the .md link.
Start and foundation
- 00Start HereOne page that tells you, George's Claude, what this framework is, the order to run it in, and the first thing to do..md
- 01How This Framework WorksGeorge learns one way to drive his agent through any module, and the agent learns one way to run them..md
- 02Ground RulesThe rules every agent, skill and automation follows, written into the brain repo so no agent ever has to guess..md
- 03System MapOne picture of George's whole system, so every agent knows where things live and which way work flows..md
- 04Inventory and InterviewGather everything Claude already knows about George in one place, ask him the rest once, and never ask again..md
- 05ProfileWho George is, written once so every agent starts out knowing him..md
- 06Brain RepoOne private GitHub repo becomes George's single source of truth, which every agent reads first and writes last..md
- 07Memory RitualEvery session starts and ends the same way, so no agent forgets what another did and long jobs never lose their place..md
- 08Claude App SetupGeorge's Claude Pro account is set up so Projects, memory, connectors and Claude Code all point at the same brain..md
- 09Passwords and SecretsGeorge's logins live in 1Password, his team shares only what they need, and agents use keys without ever seeing or printing them..md
- 10Skills AdoptionThe george-* skills get installed everywhere George works, become his to change, and never overwrite his edits or anyone else's skills..md
- 11Skills CatalogEvery george-* skill on one page: what it does, the sentence that runs it, and the module it belongs to..md
Quality: voice, anti-slop, design
- 12Voice GuideA written guide to how George actually sounds, built only from his own writing, so every draft starts in his voice instead of a machine's..md
- 13Anti-Slop StandardA hard gate that catches machine-sounding writing before anything reaches George's approval queue, plus the procedure to fix it in his voice..md
- 14Design StandardA short design brief and a separate review pass so George's pages, graphics and dashboard look designed, not generated..md
Dashboard and team
- 15Dashboard: What and WhyOne private web address where George and his helpers see everything in flight, approve work, and track his numbers, so nothing depends on George remembering it..md
- 16Dashboard BuildTurn the blank dashboard shell into George's live, private dashboard: sign-in for his team, an approval queue his agents fill, and a log of everything that shipped..md
- 17Dashboard Data SourcesPull George's real numbers into the dashboard every day, so he and his team see how things are going without logging into seven sites..md
- 18Team AccessGive each of George's helpers exactly the access they need: one private link, their own Google sign-in, and viewer, reviewer or approver rights per area of his work..md
Automation and autonomy
- 19Automation ChooserDecide, job by job, whether it runs by hand, as a scheduled task on George's Pro plan, or as a Managed Agent on the Claude API..md
- 20Scheduled Tasks (on George's Pro plan)Set up the lean weekly jobs that run in the cloud on George's Pro plan, read the brain first, and land drafts in his dashboard..md
- 21Managed Agents SetupGive George his own always-on agents on the Claude API, with a hard budget, his brain repo mounted, and keys he never has to type into a chat..md
- 22Managed Agent RecipesReady-made agent briefs for George's recurring jobs. Fill the slots, create the agent with module 21, start at level 2..md
- 23Autonomy LadderA clear rule for which jobs run on their own and which wait for George, and how a job earns more freedom (or loses it) based on its record..md
- 24Weekly RhythmGeorge's week on one page: what runs when, what lands on the dashboard, and the few things only he does..md
Your work: G's Plan, TOI, boundaries, channels
- 25G's Plan PlaybookA written playbook for G's Plan, one of George's two main things, so no agent ever has to relearn it..md
- 26The Overseas Initiative PlaybookA written playbook for The Overseas Initiative, so updates, donor care and trips run on rails in English and Spanish..md
- 27Other Work BoundariesClear lines between George's personal and ministry system and his other jobs, so nothing leaks, crosses or gets sent from the wrong place..md
- 28Publishing ChannelsOne page that says, for every place George publishes, what goes out automatically, what's handed to him ready to paste, and how to move a channel up later..md
Running it: scoreboard, fixes, iteration, prompts
- 29Control and ScoreboardA short set of rules that keep the system honest, and one weekly scoreboard that shows George whether it's working..md
- 30TroubleshootingWhat to do when something in the system goes wrong, written so the agent can fix most of it without George..md
- 31Iteration LoopHow George and Trevor improve this framework together, round after round, without anyone's changes getting overwritten..md
- 32Prompt LibraryEvery prompt George needs, ready to copy, so he never has to work out how to ask..md
Marketing command center: social, ads, email, search
- 33Command CenterGeorge runs the whole operation from Claude Code with a few short commands, while his reviewer checks everything before it goes out..md
- 34Meta Social (Facebook and Instagram)George's Facebook Page and Instagram account sit in his own Meta business portfolio, posts go out on a steady plan, and his reviewer checks them first..md
- 35Meta AdsGeorge's Meta ads run from his own ad account with a hard spending limit, his agent prepares every campaign, and a person launches it only after George approves the spend..md
- 36Email MarketingGeorge's email list grows from his site and Substack, every campaign is drafted in his voice, tested on two people, and sent only after approval..md
- 37GEO and SEO StrategyGet George named and cited when people ask ChatGPT, Google, Claude, Perplexity and the rest a Bible question, not only when they already know his name..md
Ready skills
Your copies to rename, rewrite or delete. Install them with the skills README.
- george-ai-visibility
- george-approval-queue
- george-book-promo
- george-brain
- george-coach
- george-command
- george-dashboard-data
- george-design-check
- george-donor-thanks
- george-email
- george-email-campaign
- george-gsplan
- george-handoff
- george-interview-pitch
- george-managed-agent-brief
- george-meta-ads
- george-meta-post
- george-missions-update
- george-premium-page
- george-repurpose
- george-secrets
- george-sermon-to-article
- george-session-start
- george-site-update
- george-slop-check
- george-trip-planner
- george-video-package
- george-voice
- george-weekly-article
- george-weekly-brief
Templates for your brain repo
Starter files your agent copies into george-os.
The dashboard starter
A clean, blank dashboard your agent customizes into yours: approvals, your weekly rhythm, G's Plan and TOI pages, memory, automations, data and team. It runs with sample data until module 16 connects it.
Open it