← ClaudeAtlas

agent-workflow-orchestratorlisted

Run or resume the full lifecycle from request clarification through reviewed planning, freeze, authorized execution, per-task audits, and final proof.
avksp/agent-lifecycle-kit · ★ 18 · AI & Automation · score 78
Install: claude install-skill avksp/agent-lifecycle-kit
# Agent workflow orchestrator Drive the complete lifecycle with this skill. The controller is host-neutral: skills define semantics; adapters own native questions, approvals, tools, launch, waiting, cancellation and telemetry. ## Lifecycle 1. Load existing durable state when present. Do not reconstruct authority from chat. 2. Clarify only decisions that materially change behavior, scope, safety, architecture, ownership, evidence, or external authority. 3. Route planning to `agent-first-planning`. 4. Route every candidate specification or plan to independent review through `audit-agent-plan`; refine until the freeze verdict passes or blocks. 5. Freeze only reviewed matching inputs. 6. Compile packets with `agent-plan-to-workers`. 7. Respect execution mode: plan-only, approval-required, or auto-after-freeze. 8. Launch only dependency-ready packets within frozen parallelism. 9. Run controller-owned validation before launch and after attempts when the plan requires it. 10. Audit every task attempt with `audit-plan-implementation` before acceptance. 11. Route implementation/test/evidence defects to bounded remediation. Route plan gaps, write-set gaps, architecture changes, or contract changes to reopen and refreeze. 12. After all required tasks are accepted, run final implementation audit and publish completion only from a reproducible proof. For remediation require a frozen retry budget, independent `REWORK` evidence and open finding IDs; in v4 use