Engineering
Fresh Clone Onboarding
Prove the README works from zero, not tribal memory.
Use when
You suspect setup instructions only work for people who already know the system.
Cadence
Before onboarding
Verification
A clean machine reaches the documented ready state using only the README.
Structured loop spec
| Field | Value |
|---|---|
| Name | Fresh Clone Onboarding |
| Category | Engineering |
| Trigger | Before onboarding |
| Objective | Prove the README works from zero, not tribal memory. |
| Allowed inputs | Relevant files, source notes, logs, tests, screenshots, metrics, or task state for this loop |
| Allowed actions | Define the exact scope, source of truth, and approval boundary.; Inspect current state and rank the highest-risk gap.; Make one small, reversible improvement.; Run the stated verification and record evidence.; Stop on success, budget, no progress, or approval required. |
| Verification | A clean machine reaches the documented ready state using only the README. |
| Stop condition | Stop when the verifier passes, the budget is exhausted, no progress is made, a blocker appears, or approval is required. |
| Budget | Set a time, turn, token, retry, file, or dollar cap before running the loop. |
| Approval boundary | Human approval required before publishing, sending, deleting, spending, changing accounts, touching production, or making reputational/legal/financial commitments. |
| Safe output | Pull request, patch, report, or evidence log |
| Works with | Claude Code, OpenAI Codex, Cursor, Gemini CLI, any tool-using coding agent |
Steps
- Define the exact scope, source of truth, and approval boundary.
- Inspect current state and rank the highest-risk gap.
- Make one small, reversible improvement.
- Run the stated verification and record evidence.
- Stop on success, budget, no progress, or approval required.
Prompt
Run the Fresh Clone Onboarding loop. Use it when You suspect setup instructions only work for people who already know the system. Work in bounded iterations: inspect current state, choose the highest-risk gap, make one reversible improvement, verify it, and record evidence. Stop when A clean machine reaches the documented ready state using only the README. or when blocked, budget exhausted, or approval is required.Run in Claude Code
Paste this into Claude Code (or any tool-using agent) to run the loop bounded: one change per round, the same verification every round, durable state files, and explicit stop conditions.
Run the "Fresh Clone Onboarding" loop from AI Loop Library (https://ailooplibrary.com/loops/fresh-clone-onboarding/) as a bounded loop.
Goal: Prove the README works from zero, not tribal memory.
Rules: one change per round; run the same verification every round (A clean machine reaches the documented ready state using only the README.); append each round to docs/loops/fresh-clone-onboarding/progress.md and update docs/loops/fresh-clone-onboarding/state.json; stop on verifier pass, 8 rounds, 3 consecutive failed verifications, no progress, a blocker, or anything needing human approval (money, production, outbound, deletion). Finish with a proof report: rounds used, changes made, verification output, remaining risk, and the next human decision.