df-dispatch-subagentslisted

# Dark Factory — Dispatching Sub-Agents (Promise Theory) ## Overview A sub-agent is an **autonomous promiser**: it cannot be coerced, it lives in its own private context, and it makes **best-effort** promises, not guarantees. You don't command it — you specify a promise and **assess the evidence** it returns. Apply this **every time** you dispatch one. ## When to delegate — an obligation, not an option **If it CAN be delegated under Promise Theory, it MUST be.** Promise Theory is self-limiting, so this is a rule with its own brake built in: a task is delegable **iff** (a) the promise is crisply statable AND (b) it returns unforgeable evidence you can verify **without redoing the work**. If you cannot name both, it is not delegable — do it inline. Optimize for **quality, not token budget**: parallel fan-out costs more, and that is accepted. **Evidence is RAW, never prose.** A sub-agent returns `file:line`, diffs, exit codes, verbatim command or query output — never "looks fine". Prose is forgeable: a confident summary is indistinguishable from a correct one, so a prose return means the promise was never verifiable and the task was not actually delegable. Raw evidence has a second purpose beyond forgeability — it preserves **your own** situational model. **Delegate the fetching, keep the seeing**; the map you build while reading real evidence is the byproduct that makes the *next* decision good. ## Which tier — sort by judgment, never by the verb **Default HIGH; downgrade