Coordinate Reasoning

Manage the internal coordination of reasoning processes using stigmergic principles — treating context as an environment where information signals have freshness, decay rates, and interaction rules that produce coherent behavior from simple local protocols.

When to Use

• During complex tasks where multiple sub-tasks must coordinate (multi-file edits, multi-step refactoring)
• When context has grown long and information freshness is uncertain
• After context compression when some information may have been lost
• When sub-task outputs need to feed into each other cleanly
• When earlier reasoning results need to be carried forward without degradation
• Complementing forage-solutions (exploration) and build-coherence (decision) with execution coordination

Inputs

• Required: Current task decomposition (what sub-tasks exist and how do they relate?)
• Optional: Known information freshness concerns (e.g., "I read that file 20 messages ago")
• Optional: Sub-task dependency map (which sub-tasks feed into which?)
• Optional: Available coordination tools (MEMORY.md, task list, inline notes)