Skip to main content
subagent CX Codex

reasoning-optimized — Claude Code subagent: what it does

The reasoning-optimized subagent selects a reasoning strategy based on the task and coordinates five specialist agents. Use it when a task calls for context synthesis, pattern reuse, or curation of results.

no license ★ 850 updated 2026-10-26

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/reasoning-optimized.md
Open on GitHub

What reasoning-optimized does

reasoning-optimized assesses task complexity, familiarity, context needs, and quality concerns before choosing agents. adaptive-learner draws on prior experience, pattern-matcher looks for related solutions, context-synthesizer combines relevant context, experience-curator reviews learnings, and memory-optimizer maintains memory. It coordinates this group rather than acting as a single-purpose task worker.

The agents can follow a sequence from context gathering through pattern matching and execution to reviewing outcomes. For independent work, the described flow runs agents in parallel and then combines their findings. Hooks check ReasoningBank status before a task and run automatic consolidation afterward; both use npx agentic-flow@latest. Agent selection changes with the task characteristics, so the same setup can route different requests to different specialists.

What it helps with

  • choose agents based on a task’s complexity and context needs
  • reuse solutions from similar past problems
  • combine context across domains before execution
  • curate useful learnings after a task
  • run background memory maintenance

Example prompts for the agent

  • Use reasoning-optimized to assess this task and choose a reasoning strategy.
  • Have reasoning-optimized find relevant patterns and coordinate the agents for this problem.
  • After the task, ask reasoning-optimized to curate the learnings and consolidate memory.

How to install reasoning-optimized

Manually: put the files in place

.claude/agents/reasoning-optimized.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about reasoning-optimized

How do I install reasoning-optimized in Claude Code?

Add the subagent file at .claude/agents/reasoning-optimized.md.

What does reasoning-optimized do?

It chooses a reasoning approach based on task characteristics, then coordinates specialist agents for context, pattern matching, learning, memory, and curation.

Which agents does reasoning-optimized coordinate?

It works with adaptive-learner, pattern-matcher, memory-optimizer, context-synthesizer, and experience-curator. The described workflows use either a sequential pipeline or parallel processing followed by synthesis.

Similar subagents

All subagents for Agent setup: memory, context, orchestration →

From the same set76

The whole set →
pattern-matcher The pattern-matcher subagent breaks down tasks, finds related solutions in ReasoningBank, and adapts them to a new context. CX Codex ★ 850repo stars Verification & Quality Assurance Verification & Quality Assurance is a Claude Code skill that checks code and agent outputs with reliability scores (0–1.0), reverting failed changes. CX Codex +1 ★ 850repo stars memory-optimizer memory-optimizer is a Claude Code, Codex, and Cursor subagent that merges similar ReasoningBank memories and removes stale or conflicting patterns. It also checks memory quality. CX Codex ★ 850repo stars sync-coordinator sync-coordinator coordinates version alignment, cross-package dependencies, and documentation updates across multiple repositories using an agent swarm. CX Codex ★ 850repo stars experience-curator experience-curator — a Claude subagent that screens finished task runs and keeps only verified lessons in ReasoningBank memory. CX Codex ★ 850repo stars issue-tracker issue-tracker coordinates GitHub issues and task progress using ReasoningBank pattern storage. Fits projects needing structured triage. CX Codex ★ 850repo stars parallel-execution-guide The parallel-execution-guide prompt guides Claude Code through splitting work into independent tasks, spawning CLI subagents, and combining their results. Use it for parallel research or code review. GP ChatGPT ★ 850repo stars architecture A subagent for the Architecture stage of SPARC. It turns pseudocode into a component design, pulls similar patterns from claude-flow memory, and stores what worked. CX Codex ★ 850repo stars

Project sponsors

Companies that keep this analytics open