--- name: orchestrate description: 'Coordinate authorized workers, prerequisites, isolated scopes and review capacity. Use when: dispatching, recovering or routing feedback. Not for implementation or judgment.' --- # Orchestrate Coordinate caller-authorized work through its existing tracker and runtime. Use the accepted task or conversation; a clear task needs zero mandatory skills. Selecting Orchestrate adds in-session guidance, not an AgentOps scheduler, work index, queue, ownership system, aggregate retry controller or delivery authority. The caller's tracker owns assignments and dependencies; its runtime owns running contexts, bounds and supervision; repository policy owns integration and delivery. ## Recover the actual work Read the accepted outcome, examples and scope from their current owner. Recover settled caller choices and rationale, completed history, consequential open questions and the next investigation from the existing native handoff. Do not repeat settled interviews or require the full transcript. Missing or contradictory pointers require source investigation, not a guessed decision. Before dispatch, inspect actual prerequisite content in the intended checkout, its identity and applicable evidence. A closed prerequisite whose bytes are missing, stale or unavailable is not usable readiness. Resolve that gap before dependent execution; preserve its native status and report the distinction. Inspect native assignments and runtime state together: task acceptance, observed worker/context identity, workspace and starting content, occupied write scope, pending checks and review, current candidate identity, and integration owner. Include active validators as well as writers. An empty ready list does not prove completion. A replacement coordinator reconciles these facts before resuming; it must not duplicate an assignment because its prior conversation is absent. ## Choose the next useful dispatch Concurrency follows the observed bottleneck. Inspect work waiting for checks, repair, integration or independent judgment before adding implementation. A free runtime slot alone is not a dispatch reason. Reserve capacity for integration, review and repair; reduce new starts while candidates accumulate. Record only the concrete constraint and next action in the existing native handoff, then reassess when evidence changes. Do not add a capacity ledger or queue. Use [Agent Native](../agent-native/SKILL.md) for runtime mechanics: executor selection, startup/engagement evidence, actual context identity, normalized scopes, native waits and follow-up, bounds and cleanup. Its optional adapters retain those methods; Orchestrate does not copy or replace them. Concurrent writers require disjoint write scopes and separate isolation, including generated companions and transitive effects. Serialize shared paths. A worktree separates Git edits; it does not establish restricted-source or model-egress enforcement. Dispatch a genuinely fresh implementer for one coherent accepted task, without the coordinator's accumulated transcript or unrelated research. A new goal, role label, cleared summary or resumed author context is not a fresh context. Pass the accepted examples, applicable constraints, exact starting content, usable prerequisites, authorized write/output scope, relevant source pointers, required checks, integration responsibility and real remaining bounds. Expand pointers when needed; brevity cannot omit a constraint. Record observed native identity at startup through Agent Native's existing association procedure. [Implement](../implement/SKILL.md) owns the complete change, meaningful checks and direct repair. It is optional guidance for that worker, not a compulsory stage. The handoff returns candidate identity, changed scope, check facts, discoveries and gaps. Successful prompt delivery or worker exit proves neither engagement nor acceptance. ## Integrate and obtain judgment Name the integration and final-validation responsibility before launch. Follow the consumer repository's integration policy, include all changed paths and generated companions, and run affected checks on the actual integrated subject. Acceptance of a leaf does not establish the combined release. Assign fresh author-distinct judgment of the exact candidate against unchanged acceptance through [Validate](../validate/SKILL.md), the sole skill owner of acceptance semantics. Its identity, freshness, complete checked scope and evidence requirements remain authoritative; preserve every explicitly required review leg. Advisory Review, Plan challenge and Council advice are not binding acceptance, and must be refused when offered in place of that judgment. Changed candidate bytes invalidate the old subject binding and require judgment of the new exact subject. Deterministic green or convincing author rationale cannot fill missing proof. No report format or persisted artifact is mandatory unless the caller or an existing consumer requires one. ## Reconcile feedback and resume Preserve successful and failed evidence in the existing native task or handoff. Identify affected unfinished work and update its native dependencies or handoff within authority. Stop or explicitly re-scope an affected active assignment before it continues on a disproven premise; obtain observable acknowledgment or stopped runtime state before treating the revision as effective. Unaffected work continues unchanged. Repeating reconciliation with unchanged facts creates no new artifact or dispatch. [Plan](../plan/SKILL.md) owns consequential uncertainty, optional challenge and refining the next complete slice. Reuse settled decisions and accepted examples; new evidence may change an approach within the accepted outcome. A different promised outcome or authority choice returns to the caller. Agent advice cannot supply that choice. Preserve completed history instead of reopening accepted work merely to fit a revised story. Known failures return to the responsible task for direct repair. On a genuine causal stall, the existing operating contract permits at most one authorized bounded fresh helper for that incident within remaining bounds; an unhelpful answer ends that attempt. Cancellation, refusal or exhausted bounds skip help. Replacement workers, retries, new subjects and compaction never reset those bounds. Inspect native evidence before replacing a worker; use native waits for unchanged pending state instead of repeated analysis or probes. When maintained context could change the next action, selectively use [Memory find/recall](../memory/references/recall.md). A supported correction may use its [capture](../memory/references/mine-learn.md) and [curation](../memory/references/curate.md) procedures. Memory retains admission, support/disclosure review and context ownership; no automatic lesson, private import or mandatory recall follows from coordination. No change is valid, and context capture alone proves no benefit. ## Selected external factory Keep the selected factory's coordinator in control. Hand it the caller-authorized source intent through its supported door; the coordinator creates its workflow and dispatches internal runs. For Gas City, use the Mayor through [Using GC](../using-gc/SKILL.md). Do not manufacture, scale or repair internal sessions by hand, or mirror factory work in an AgentOps tracker. Doctor and supervisor operations use the factory's supported external doors within caller authority. Read native state, recover through that coordinator and judge the returned exact content independently. Factory completion does not authorize delivery or establish acceptance.