Free, no credit card

The teamvince agent harness starter.
Plus a 60-second take from Vince.

Three things, free. Drop the harness into any new project and you have a working spec-first loop in ten minutes. Run your idea through the scope filter to know if it can ship in 14 days. And if you check the optional box, Vince records a 60-second Loom on whether your idea is ready to ship and how to scope it.

Send me the harness

What lands in your inbox: the harness in under a minute. Then, if you opted in, a 60-second Vince Loom on your idea within 24 to 48 hours. Then a short series of build notes about what's working in the cohort right now. No spam. Unsubscribe any time.

Fields marked with * are required.

Optional. Skip this and you still get the harness and scope filter.

Your first 10 minutes

What you can do in the first 10 minutes.

  1. Drop the harness into a new repo.
  2. Fill in the project placeholders.
  3. Run /scope against your idea.
  4. Copy the generated v1 brief.
  5. Use /diff-review and /verify before trusting the next code change.

You do not leave with theory. You leave with the beginning of an operating loop.

What you get, three things

The harness, the filter, the take.

Most lead magnets are a teaser. This one is the actual thing Vince uses on his own projects, plus a tool that protects you from picking the wrong project, plus a 60-second outside read.

01

The agent harness starter

A downloadable repo with AGENTS.md, AGENTS.example.md, CLAUDE.md, five slash commands I actually use (/scope, /diff-review, /verify, /ship, /share), one starter Skill setup, .env.example, .gitignore. Drop into any project. Edit the placeholders. Done.

Download · Yours forever
02

The scope filter, interactive

An interactive worksheet that runs your project idea through the seven-question filter. Picks the lane (Internal Tool, Workflow Automation, AI Work Agent, Niche Micro-SaaS), names the graceful fallback if scope blows up, generates a draft AGENTS.md ready to commit. The same tool the cohort uses on Day 1.

Live link · Use any time
03

A 60-second Vince Loom (limited)

If you check the box and submit your idea, Vince records a 60-second Loom on whether it is scoped right and what to cut. Capped at the first 25 per cohort cycle. Real human review, not a bot. The Loom queue opens each cohort cycle. If it is full, you still get the harness and scope filter immediately, plus a note when the next review window opens.

First 25 each cycle
Inside the harness

What you actually unzip.

.
├── AGENTS.md              # Portable project spec for tools that read AGENTS.md
├── AGENTS.example.md      # A filled-in example spec to copy from
├── CLAUDE.md              # Claude Code wrapper that imports @AGENTS.md + Claude-specific rules
├── LICENSE                # MIT
├── .env.example           # Template for your secrets, never commit the real .env
├── .gitignore             # Keeps .env out of git
├── .claude/
│   ├── commands/
│   │   ├── scope.md       # /scope, run an idea through the scope filter
│   │   ├── diff-review.md # /diff-review, plain-English diff explanation
│   │   ├── verify.md      # /verify, three-check verification before merge
│   │   ├── ship.md        # /ship, lint and deploy in sequence
│   │   └── share.md       # /share, share-ready copy for what you built
│   └── skills/
│       └── README.md      # Where Skills go, plus the install pattern
└── README.md              # This file

Why two spec files?

AGENTS.md is the portable agent spec. It is now stewarded by the Agentic AI Foundation under the Linux Foundation and is used across tools like Codex, Cursor, Gemini CLI, Amp, Devin, Factory, GitHub Copilot, and others.

Claude Code still reads CLAUDE.md as its native project memory file, so this starter includes a small CLAUDE.md that imports @AGENTS.md and adds Claude-specific defaults. That gives you portability without duplicating instructions.

The asset is the harness, not the model. If the best agent changes in six months, your project spec moves with you.

Who this is for

SMEs who want to ship.

PMs, operators, consultants, and indie builders who have already opened Claude Code at least once. You have the domain expertise. AI is the force-multiplier on top, not a replacement for being a worse developer.

Right fit

You have an idea you'd build if you weren't stuck in "I need a developer" mode. You're willing to own every diff. You want to leave with something real, not a toy.

Wrong fit

You want a tour of every AI tool. You want passive video. You've never opened Claude Code. Start there first, then come back. You want to vibe-code without reviewing the code.

What's next

Use the harness on something real. Want a 4-week structured push to ship one tool live with a small cohort? The May 12 founding cohort is underway at $497. The next cohort runs at $697+.

Honest answers

FAQ

What's in the harness, exactly?

A downloadable repo with two spec templates (AGENTS.md, CLAUDE.md), five slash commands as markdown files, an .env.example, a .gitignore, and a README with a 10-minute quick start. About 14 files, 19 KB unzipped. You unzip, fill in the placeholders, you have a working spec-first loop.

Do I need Claude Pro to use the harness?

To run the slash commands and use plan mode, yes. Claude Pro is $20 a month and is the minimum for serious agentic work. You can read AGENTS.md and CLAUDE.md as plain documents without Pro, but the loop only fires inside Claude Code.

What's the Vince Loom take, exactly?

If you submit a project idea and check the consent box, Vince records a 60-second Loom video addressing one specific question: is this scoped right to ship in 14 days, and if not, what to cut. Capped at the first 25 submissions per cohort cycle (monthly). Real human review. If the queue is full when you submit, you still get the harness and scope filter, plus a note when the next cycle opens.

Does this replace the course?

No. The harness is the starter scaffold. The course is the structured 4-week push to actually ship one tool live with a small cohort, async Loom mid-cohort demos, project approval, build buddies, and demo day. The harness is the lead magnet. The cohort is the product.

Why is this free?

Two reasons. One, this is the harness Vince uses on his own projects, so giving it away costs nothing extra. Two, it qualifies the lead. People who use the harness and want to push further into a structured cohort are the right buyers. People who don't get value from the harness are not the right fit.

How current does the harness stay?

The harness is versioned. When Anthropic, OpenAI, or Cursor ships something material (new model, new feature like Skills, new MCP standard), Vince updates the harness and email subscribers get the diff. Same living-syllabus mechanic the cohort uses.

What's new

Current version.

v0.3 · May 2026

  • Added AGENTS.md + CLAUDE.md import pattern
  • Added /scope, /diff-review, /verify, /ship, /share
  • Added scope-filter worksheet and starter Skill scaffold

Want updates? Harness subscribers get the diff when the agent workflow changes.

Want a structured push?

From Chatbot to Builder.

The next 4-week cohort runs Tuesdays at 6pm ET. The May 12 founding cohort is underway. One shipped tool, one workflow you trust, one next-project plan. Founding price closed; next cohort starts at $697+.

See the course