Cost

Cost stance: balanced

Session effort runs medium, fan-out stays at six subagents or fewer, fast mode is off unless asked, and a task ends with /clear, not /compact. Past 160,000 tokens of context a call costs more; the feed says so. Past 400,000, about 3.3× the cost per call, the turn’s end is blocked once: write the handoff, then start a fresh session. Spend the effort dial on judgment work and keep gathering cheap. The table also prices each role and band: class, effort, soft budget. Tier comes from delegation; this one sets how much. Cache rules: cache-hygiene.md.

Cost stance: frugal

Session effort runs low unless the task is design or adversarial review. Subagents are gatherers only, fan-out no wider than three, and fast mode is never used. Agent teams are off. End a task with /clear, never /compact. Past 160,000 tokens of context the feed says a call costs more; past 200,000 the turn’s end is blocked once: write the handoff, then start a fresh session. Before a model call, try a deterministic command — the test, the linter, the exit code. The table prices each role and band: class, effort, budget. Tier comes from delegation. Cache: cache-hygiene.md.

Cost stance: max

Session effort stays at the model’s default, fan-out is as wide as the task needs, fast mode is allowed, compaction is allowed when a long task needs it, and the feed never nudges or blocks you toward a fresh session. Optimise for the answer, not the bill. The table prices each role and band: class, effort, budget. Tier comes from delegation; this one sets how much. cache-hygiene.md costs apply; you choose to pay them.

Cost stance: off

No cost posture is in force: this stance sets no session effort, fan-out width, context-size handoff or compaction habit. Spawns still resolve, on the balanced table’s classes and efforts, so a role keeps its model; the per-turn usage feed is off. Tier comes from the delegation stance.

An off variant still links a one-line file, so /context shows the stance is set and silent rather than missing.