orchestrating-worklisted

# Orchestrating Work Execution principles for multi-agent workflows: input validation, work acceptance, file organisation, and phase transitions. Workflow structure (which phases to run) lives in `designing-workflow`. ## 1. Validate Inputs Before Invocation Agents need complete context to work independently — every missing input costs a clarification round-trip. Universal requirements for ALL agents (read `agents/<agent-name>.md` for agent-specific ones): - Absolute path to `work/<task-id>/` directory - Absolute output path for the deliverable - All dynamic skills provided as file paths or inline content, never just names. Preloaded skills (listed in the agent's `skills` frontmatter) are injected automatically. - All agent-specific required inputs present - All paths absolute (no `./` or `../`) Before invoking: check universal requirements, read the agent's file for specific ones, then wait for the agent to echo its inputs. If validation fails: STOP, identify and provide the missing inputs, re-validate before re-invoking. If the agent does not echo inputs: STOP — silence indicates malformed or truncated instructions; verify and re-invoke. ## 2. Accept or Reject Work Deliberately Rejecting work during review costs one iteration cycle; accepting substandard work costs post-deployment rollback and rework. Universal criteria for all artefacts: - [ ] Output file exists at declared path; not empty or truncated - [ ] Basic structure present; assigned task addressed comple