Kill criteria, written so they fire.

Every pattern here is one project type, one table of Gates, and one paste-ready block you can put straight into your own plan.

A commitment becomes real when a missed deadline produces an outcome instead of nothing. That is the only idea these pages contain, applied one project type at a time.

sec 01the library

nopatternproject type

01Kill criteria that actually fireA kill criterion is not a feeling. It is a number, a date, and what happens when nobody shows up.any project 02How to kill a side projectKilling it is a 20 minute procedure with a written record. Abandoning it is a slow tax you keep paying.side project 03A decision log that does not decayMost decision logs die in three weeks. They die because writing in them is optional and nothing reads them back.the record itself 04A WIP limit for a solo founderYou are the only approver. A work in progress limit for one person is arithmetic, and the arithmetic is tighter than any team wants it.solo company 05When agents produce more than you can approveYour agents removed the build constraint. They did not add an approver. The queue forms at you.agent-built repos 06Pivot or persevere, decided on a dateThe decision is not hard because the evidence is unclear. It is hard because nothing forces it, so it stays open.a project with some signal 07Sunk cost is a timing problem, not a willpower problemYou cannot reason your way out of sunk cost at the moment it matters. You can only have written the exit terms before you were in it.a project you cannot put down 08How long to give a side project before quittingAny limit works if it is written down. No limit works if it is a feeling about how long feels fair.a project just started 09Too many projects, nothing finishedThe problem is not focus. It is that eleven projects are all technically still alive, because none of them was ever formally allowed to die.a whole portfolio 10Which old repo is worth finishingA folder of abandoned repositories is not a backlog. It is a set of decisions you have already made and never written down.abandoned repositories 11Finish this, or start the new thingThe new idea always looks better, because it is the only one you have not yet found the boring part of.the next decision 12Accountability when you are the only approverEvery accountability tool you have ever used had a witness. A cofounder, a manager, a stake on the line. A solo builder has none, and the witness can be built.the only approver 13Shiny object syndrome is a slot problemNew ideas do not steal your time. They steal a slot somebody else was holding, and the trade is never written down.serial starters 14Polishing forever: why you never launchThe last ten percent is not work. It is a hiding place, and it has no deadline of its own.perpetual polishers

Table 1 · every pattern, free, no account

sec 02the next step

Or start from the plan you already wrote.

Paste a plan, a CLAUDE.md or a launch checklist. Every line carrying a promise and a date comes back as a Gate, quoted in your own words, with the deadline and the Default filled in.

free · no account, no email, no card