orchestrator-capacity

Documents historical loop capacity request semantics for the CCB orchestrator rolepack.

3.5k|342|Updated Oct 25, 2025
One-click install
npx skills add https://github.com/bfly123/claude_code_bridge --skill orchestrator-capacity
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: orchestrator-capacity
Source: https://github.com/bfly123/claude_code_bridge/tree/main/docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.ccb_orchestrator/adapters/ccb/skills/orchestrator-capacity
Command: npx skills add https://github.com/bfly123/claude_code_bridge --skill orchestrator-capacity

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill preserves the historical reference for how loop capacity requests were once handled in the CCB orchestrator rolepack, clarifying that capacity management is now owned by the runner script rather than provider sessions.

Core Features & Use Cases

  • Historical Reference: Records the deprecated script-owned capacity request pattern for rolepack history.
  • Provider Boundary Definition: Explicitly forbids provider sessions from running CCB commands, inspecting runtime capacity, releasing agents, or mutating task status.
  • Reply Shape Guidance: Defines the semantic evidence format (requested profiles, task packets, blockers, release-readiness) that an orchestrator may return.
  • Use Case: When auditing or migrating an old agentroles.ccb_orchestrator rolepack, consult this reference to understand why capacity operations moved to the supervisor/runner script.

Quick Start

Ask the AI to explain the historical orchestrator capacity request pattern and the current runner-owned boundary described in this reference.

Frequently Asked Questions about orchestrator-capacity

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is the orchestrator-capacity skill in CCB?

It is a historical reference documenting the old script-owned loop capacity request pattern for the agentroles.ccb_orchestrator rolepack. It is not projected as an active provider skill and exists only for rolepack history.

Who owns loop capacity management in CCB now?

Loop capacity is runner-owned. The supervisor/runner script performs capacity ensure, status, release, routing, and cleanup, while the orchestrator may only recommend the semantic need for capacity.

Can a provider session run CCB capacity commands?

No. Provider sessions must not run CCB commands, inspect runtime capacity, release agents, mutate task status, import artifacts, or route work. They reply with semantic evidence only.

What should an orchestrator reply when capacity information is needed?

It should reply with semantic evidence only: requested profiles and counts, task packet and verification refs, blockers or missing evidence, and a release-readiness recommendation based on supplied worker and reviewer evidence.

When should this orchestrator-capacity reference be used?

Use it only when reviewing rolepack history or migrating legacy orchestrator configurations. It must not be used from active provider sessions, since the runner treats provider replies as evidence rather than commands.