Codex Deep Reasoner — Design agent for Claude Code
CLI-backed read-only deep-reasoning worker — the codex variant of deep-reasoner.
How to install Codex Deep Reasoner
Installs to ~/.claude/agents/hmj1026-dhpk-codex-deep-reasoner.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/hmj1026/dhpk/HEAD/agents/codex-deep-reasoner.md -o ~/.claude/agents/hmj1026-dhpk-codex-deep-reasoner.md Restart Claude Code, or start a new session, for it to be picked up.
What Codex Deep Reasoner does
name: codex-deep-reasoner description: 'CLI-backed read-only deep-reasoning worker — the codex variant of `deep-reasoner`. Use for root-cause analysis, algorithm design, complex multi-file debugging, and design synthesis during the implement phase when the `--reasoner=codex` backend is selected (default `gpt-5.6-sol` @ `high`) instead of the in-process opus deep-reasoner. Availability depends on the codex executable, independently of the separate CODEX review-peer switch. Runs `codex exec` i
Alternatives in Design
- Apex Architect — Use this agent when the user needs strategic architecture analysis, design tradeoffs, or read-only debugging 523 ★
- Async Code — Use Claude Code or CodeX CLI to perform multiple tasks in parallel with a Codex-style UI, functioning as a per 513 ★
- Codex Second Opinion — Get an independent opinion from OpenAI Codex (GPT-5) on a design decision, an approach, a tradeoff, or an unfa 249 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Deep Reasoner
Read-only deep-reasoning worker. Use for root-cause analysis, algorithm design, complex multi-file debugging,
Heavy Executor
Execute DEMANDING tasks that need real reasoning or design judgment (intelligence/taste need 7-8) - real root-
Fable Architect
Plan-only Fable 5.1 pass from an Opus or Sonnet main. Use for architecture, ambiguous root cause, or a design
Develop Synthesis
Strategic synthesis engine that transforms seed-stage ideas into researched TL;DR nuggets. Channels an experie
What Breaks
Opus 5 validator that pressure-tests a handed artifact — diff, PR, document, design, claim, or question — and
Playwright
Use this agent when you need to write Playwright end-to-end tests for new or existing features in the helpdesk
Related Skills
Hatch3r Bug Plan
Diagnose a complex incident -- reproduce the symptom, rank root-cause hypotheses, design the fix path, and emi
Secondmate Reason
Ask a read-only reasoning model (via secondmate) a hard analysis question — root-cause, triage, plan review, p
Bug Race
Use when a bug has already survived at least one debugging attempt and you have 2-3 genuinely distinct root-ca