Dos

Refresh a plan portfolio from evidence: close shipped queue items, update cooldown state, and surface the few decisions an operator must make. Use after dispatch bursts, drained backlogs, or recurring findings.

Snapshot the repo's phased-plan portfolio into a dispatch packet: audit candidates with `dos verify`, render who-does-what, and emit a `dos gate` verdict. Use when you need the current next-work view before dispatching agents.

Surface units held out of the pickable set with their typed HoldReason and derived unblock action, auto-applying only safe reclassifies. Use when work is stuck unpickable and a human needs the exact unblock move.

Analyze BLOCKED/DRAIN run history, cluster recurring causes, and propose one structural fix per wedge via `dos decisions`. Use when a fleet keeps stalling and you want a systemic unblock rather than another manual nudge.

Plan and ship the next batch on one lane: run `dos-next-up`, acquire a lease with `dos arbitrate`, gate empty work, dispatch the packet, and archive the run. Use when a single lane should move end to end with collision safety.

Convert an agent skill into a DOS-grounded variant by replacing self-certified claims with `dos` witness checks and emitting an additive copy plus report. Use when asked to make a skill DOS-aware or audit its self-checks.

Ground a keep-working goal in evidence the worker did not author by wiring `dos hook stop` to refuse false done claims. Use for one self-stopping agent or loop worker; use `dos-witness-claim` for fold barriers.

Launch multiple goal-scoped workers in waves, each with a witness-gated stop condition and `dos arbitrate` file-tree safety. Use when an operator asks to run several independent goals in parallel and fold only verified ships.

Price a proposed multi-agent fan-out before launch by computing tree collisions, safe concurrency, and a cheaper disjoint partition. Use before `dos-goal-fleet`, a `dos-next-up` dispatch packet, or any N-agent tree split.

Run one DOS plan-class lifecycle tick from the workspace `[lifecycle]` table: evaluate declared transitions, have a judge approve/defer them, write gated plan-meta edits, and log the cycle. Use when gardening plan lifecycle classes automatically.

Run bounded, recurring `dos-replan` sweeps, optionally guarded by the workspace's release policy. Use when the planning queue needs unattended refresh for a fixed cadence rather than one manual sweep.

Tune DOS enforcement policy knobs (`[intervention_policy]`, `[intervention]`, `[improve]`) from false-deny versus held-catch evidence. Use when running `dos enforce-tune` to keep only measured net_task_delta gains and escalate repeated non-keeps.

Run the DOS self-improvement loop: propose a candidate, verify it in an isolated worktree, measure suite/truth/metric gates, and keep only confirmed gains. Use for recursive improvement; use `dos-enforce-tune` for policy knobs.

Run recurring `dos-dispatch` cycles, switching to `dos-replan` when the backlog drains and stopping on the kernel's loop verdict. Use for unattended dispatch->replan->dispatch work across disjoint lanes.

Route subagent claims through independent read-back before another agent relies on them. Use at parallel, pipeline, or synthesis barriers where shipped phases, files, rows, messages, or other effects must be witnessed.

Keep a target count of dispatch loops alive across the workspace lane roster: spawn missing loops, scavenge stalled leases, and surface spinning workers. Use when supervising a DOS dispatch-loop fleet.