token-optimiserlisted

# Token Optimiser Two things are true at once and the whole skill lives in the tension between them: tokens cost money and latency, and a wrong answer costs far more tokens to repair than a careful one costs to produce. So the goal is never "fewer tokens". It is **no wasted tokens** — every token spent has to be doing work that a cheaper token could not do. Waste is specific and identifiable: restating the request back to the user, narrating steps they just watched, reading whole files to use four lines, running the same search twice with different words, spending frontier-model reasoning on a find-and-replace, and re-deriving context that is already in the conversation. Cutting those is free. Cutting rigour is not — it just moves the cost downstream. --- ## Step 1 — Triage before acting Before the first tool call, score the request 0–2 on five axes. This takes seconds and it is the highest-leverage moment in the task, because it sets the model, the budget and the shape of the answer all at once. | Axis | 0 | 1 | 2 | |---|---|---|---| | **B — Breadth** | one deliverable | 2–3 sub-goals | 4+ sub-goals or an open scope | | **D — Depth** | recall, lookup, mechanical transform | multi-step derivation, known method | novel judgement, real trade-offs, no settled method | | **A — Ambiguity** | fully specified | small gaps, safe to assume | the goal itself is unclear or contested | | **S — Stakes** | trivially reversible | rework would hurt | irreversible or external — money, s