# reasoning-optimized

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.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 850 repo stars
- Author: ruvnet
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/reasoning/reasoning-optimized.md
- Updated: 2026-10-26
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/reasoning-optimized

## What it 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.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/reasoning-optimized.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/reasoning-optimized.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/reasoning-optimized.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/ruvnet/agentic-flow/tree/HEAD/.claude/agents/reasoning/reasoning-optimized.md

## When to use it
- 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
- 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.

## Similar
- [recall-reasoning](https://affpapa.org/en/nevibecode/skills/recall-reasoning.md) — skill · 605 installs
- [critical-thinking-logical-reasoning](https://affpapa.org/en/nevibecode/skills/critical-thinking-logical-reasoning.md) — skill · 2500 installs
- [thought-based-reasoning](https://affpapa.org/en/nevibecode/skills/thought-based-reasoning.md) — skill · 1500 installs
- [clinical-diagnostic-reasoning](https://affpapa.org/en/nevibecode/skills/clinical-diagnostic-reasoning.md) — skill · 178 installs
- [critical-reasoning](https://affpapa.org/en/nevibecode/skills/critical-reasoning.md) — skill · 170 installs
- [complex-reasoning](https://affpapa.org/en/nevibecode/skills/complex-reasoning.md) — skill · 167 installs

From the same set: [ruvnet/agentic-flow](https://affpapa.org/en/nevibecode/by/ruvnet/agentic-flow.md) — 76 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
