A
licenseNot graded
qualityB
maintenanceEnables Codex to delegate tasks to interactive Claude Code sessions as role-controlled subagents for exploration, code review, and implementation, using the existing Claude Code installation on macOS.
MIT
codex-subagent-for-claude
by Ryen-LTC
Related Servers
Alternatives to codex-subagent-for-claude
No user-submitted related servers found.
Related Servers
- AlicenseAqualityDmaintenanceEnables Claude Code to delegate tasks to OpenAI's Codex CLI (GPT-5.4) with structured execution traces, parallel execution, session persistence, and adversarial code review.15MIT
- AlicenseNot gradedqualityDmaintenanceEnables Codex to offload expensive code reading, editing, and checking to a worker agent via Claude Code, supporting async jobs and long-running tasks.MIT
- AlicenseNot gradedqualityBmaintenanceEnables delegating bounded tasks from Codex to Claude Code, including read-only reviews, isolated branch edits, long-running background work, and approval handling.395 npm1MIT
- AlicenseNot gradedqualityAmaintenanceLets Codex delegate coding and repository work to an installed Claude Code CLI with permission-aware inspect/write access, model and effort selection, resumable and cloud-attached sessions, and durable synchronous or asynchronous jobs.MIT
- AlicenseAqualityAmaintenanceEnables Claude Code to delegate coding tasks—investigation, review, long-running background jobs, and optional file edits—to a locally installed OpenAI Codex CLI, with the model and reasoning effort chosen per task and read-only execution by default. Follow-up requests reuse Codex's existing context, and write-enabled delegations can be confined to a managed git worktree so the user's own checkout stays untouched.8204 npmMIT
TDQS
A4.3/5.0
Scored across 6 tools
Disambiguation4/5
Each tool targets a distinct lifecycle action (spawn, status, wait, steer, interrupt, review), and descriptions actively disambiguate near-neighbors by naming the alternative ('只想看一眼不想等，用 codex_status'). The main residual overlap is codex_status vs codex_wait, since both return task results, though the blocking-immediate distinction is explained.
Naming Consistency5/5
All six tools follow a uniform codex_<action> snake_case pattern (spawn, wait, status, steer, interrupt, review). Verbs are consistent and predictable throughout.
Tool Count5/5
Six tools is well-scoped for a subagent-management server, covering spawn, monitoring, control, and review. Every tool earns its place with no redundant additions.
Completeness4/5
The surface covers the full task lifecycle: dispatch (spawn), monitor (status/wait), control (steer/interrupt), and review, plus thread continuation via thread_id. Minor gap: no explicit tool to enumerate historical/prior threads beyond session-scoped status.
Maintenance
ActivityMaintained
ResponsivenessNo issues