Start with the read-only boundary audit. Use the other prompts when context, design, continuity, reasoning, or automation becomes the bottleneck.
TL;DR
Every prompt declares its input, expected result, and success check.
Copying is preparation; attempting and verifying are separate progress stages.
Your agent can install the complete audit from agent.md.
Paste this into your agent:
Fetch https://proud-anchor-53zn.here.now/agent.md and follow it to install the factory-loop audit in my current project. Run the success check and show me the result.
Quick start
Orient yourself in the current repository before choosing a prompt.
Repository-capable coding agentProject rootOne recurring task and the current repositoryA seven-part boundary map with one human gate
Success: All claims are Observed, Inferred, or Proposed; the tree is unchanged.
You are auditing one recurring software task as a bounded factory loop. Work read-only until I explicitly approve a change.
First inspect the current repository and ask me to name the recurring task if it is not already clear. Then return these seven sections:
1. Task contract — input, desired outcome, and what is outside scope.
2. Required context — the minimum current evidence needed before acting.
3. Boundary map — repository rule, launch rule, command rule, human gate, and automated check.
4. Risk gate — the first expensive, destructive, public, or hard-to-reverse action that must stop for approval.
5. Success evidence — one exact command or observable signal that can prove the task worked.
6. Receipt — what the next session needs to reproduce the result and understand the decision.
7. Smallest reversible delta — the first experiment that tests this loop without production mutation.
Label every statement Observed, Inferred, or Proposed. Do not install tools, use credentials, mutate data, publish, or edit files. If evidence is missing, stop and name the missing evidence instead of guessing.
Compose the smallest useful evidence packet
Coding agentProject rootTask, relevant files, fresh command output, optional annotated imageA source list, omissions, and one verification plan
Success: Every included source changes the decision, action, or verification.
Prepare the smallest evidence packet for this task before proposing a solution. Separate: task, constraints, current implementation, fresh runtime evidence, visual evidence, and success check. For each source, say which decision it can change. Identify stale, duplicated, contradictory, or irrelevant material and exclude it. End with the exact evidence still missing. Do not implement yet.
Generate structural variations
Design-capable coding agentProject root; write only to a scratch route or directoryStable content, product goal, design constraintsFour meaningfully different mockups and a comparison index
Success: Options differ in structure, not only color or type.
Create four dependency-free design variations without editing production files. Hold the content and product goal constant. Vary information architecture, hierarchy, density, navigation, and interaction emphasis. Give every option a distinct design thesis. Build a comparison index that explains what each option optimizes, what it sacrifices, and which user behavior it makes easiest. Stop before choosing a winner. Label this a Companion-authored exercise.
Recover a trustworthy handoff
Coding agent with repository and history accessProject rootWorking tree, recent commits, notes, artifacts, available session historyA compact recovery memo and one next check
Success: The memo distinguishes verified state from remembered or inferred state.
Recover this task from durable evidence. Report: current objective, current repository state, last verified result, decisions already settled, open risks, failed attempts worth preserving, next bounded action, and the exact command or observation that will prove it. Use history only to locate evidence; verify important claims against the current tree or artifacts. Do not continue implementation until the recovery memo is internally consistent.
Prepare a maximum-intelligence consult
Strong independent reasoning modelProject root or supplied evidence bundleOne hard decision and filtered supporting evidenceAlternatives, hidden assumptions, experiment, reversal plan
Success: The recommendation is falsifiable and does not depend on missing context.
Review this decision independently. State the decision in one sentence. Identify hidden assumptions and the most costly way the current framing could be wrong. Propose at least three materially different options, including the simplest viable option. For each, give evidence, tradeoffs, reversibility, and failure modes. Recommend the smallest discriminating experiment and define the result that would change your recommendation. Finish with a reversal plan.
Earn the right to automate
Coding agent and human ownerProject rootVISION.md or product evidence plus one recurring reviewManual → script → agent → CI → blocking-gate promotion plan
Success: Every promotion has an owner, evidence threshold, cost boundary, and recovery path.
Map this recurring review onto an automation ladder: manual run, deterministic script, bounded agent, non-blocking CI report, blocking gate, schedule, or human approval. Keep it at the lowest stage that is currently justified. For each possible promotion, specify the evidence threshold, false-positive tolerance, latency and cost budget, owner, stop condition, and recovery path. Run nothing and schedule nothing. End with the next five manual receipts we should collect.
# Factory Loop Boundary Audit
Use this prompt before automating or expanding a recurring software task.
## Instructions
You are auditing one recurring software task as a bounded factory loop. Work read-only until I explicitly approve a change.
First inspect the current repository and ask me to name the recurring task if it is not already clear. Then return these seven sections:
1. Task contract — input, desired outcome, and what is outside scope.
2. Required context — the minimum current evidence needed before acting.
3. Boundary map — repository rule, launch rule, command rule, human gate, and automated check.
4. Risk gate — the first expensive, destructive, public, or hard-to-reverse action that must stop for approval.
5. Success evidence — one exact command or observable signal that can prove the task worked.
6. Receipt — what the next session needs to reproduce the result and understand the decision.
7. Smallest reversible delta — the first experiment that tests this loop without production mutation.
Label every statement Observed, Inferred, or Proposed. Do not install tools, use credentials, mutate data, publish, or edit files. If evidence is missing, stop and name the missing evidence instead of guessing.
## Success contract
- The output contains all seven named sections.
- Every statement is labeled Observed, Inferred, or Proposed.
- One explicit human gate and one exact verification signal are named.
- The audit makes no repository changes.
Success check: the installed audit returns seven labeled sections, one human gate, one exact verification signal, and changes no pre-existing file.
factory loop prompt installed
Use the smallest prompt that can change the result
Before: name the boundary. Prompt: include only decisive evidence. Success evidence: run one exact check. Reflect: record what changed your decision. Continue: return to the related lesson.
The prompts are companion-authored exercises grounded in the recorded operating patterns. They are not presented as verbatim workshop quotations.
Appendix
Limits and caveats
The prompts cannot supply missing repository evidence, current tool pricing, account permissions, or a human approval decision. Keep destructive and public actions behind explicit gates.
Provenance
Derived from the workshop recording, prepared modules, exact chat resources, and the validated follow-up analysis. Evidence coverage: 79/79.