planlisted

# /tml:plan — decide where to sit, and how long to train Two decisions, both the operator's: **where on the frontier** this project sits, and **how long each run gets**. This skill frames them, prices the options, and asks. It does not choose. ## First action, always ```bash ls -la ./.tml/ 2>/dev/null ``` Read `findings.md` if present. If it is absent, say so and either run `/tml:audit` first or proceed from what the operator states — but never invent findings to plan against. ## Hard rules 1. **The operating point is not the agent's to choose.** Present the options with honest upsides _and_ downsides and ask. Silence is not consent. 2. **A quality floor is mandatory before any `spending` change is ordered.** No floor, no spending. 3. **Non-negotiables are vetoes.** A hard constraint touched by an `unknown` or `spending` exposure stops that change regardless of effect size. 4. **Every ordered change carries a revert trigger** — the observation that means undo it — written before it is made, not after it fails. 5. **Writes only `./.tml/frontier.md`.** No project code. ## Procedure ### 1. Establish the regime `references/regime.md` §1 and §3: concurrent trials, local or remote execution. This is not optional and it is not inferable — a plan calling for 60-trial studies on a machine that runs two at a time is not a plan. Record what was sacrificed if the regime is low (`study-design.md` §4). ### 2. Fix the step budget `references/step-budget.md`. Determine