Consults OpenAI Codex (GPT-5) via CLI for code investigation, debugging, or review. Runs read-only with full project access; activates on 'ask codex' phrases or /ask-codex.
From thinking-toolsnpx claudepluginhub umputun/cc-thingz --plugin thinking-toolsThis skill is limited to using the following tools:
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Guides idea refinement into designs: explores context, asks questions one-by-one, proposes approaches, presents sections for approval, writes/review specs before coding.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Consult OpenAI Codex (GPT-5) as a second opinion for investigation, debugging, or review tasks. Codex runs in read-only mode with full project access — it analyzes, Claude implements.
Run which codex to verify the CLI is installed. If not found, inform the user and stop.
Gather context from the current conversation:
Build a focused prompt. Do NOT dump entire files — codex has full project access and can read them itself. Provide file paths and line references so codex knows where to look.
Template:
# [Investigation/Debug/Review] Request
## Problem
[2-3 sentence description]
## Context
- Files: [path/to/file.go:lineNumber, ...]
- Observed: [what's happening]
- Expected: [what should happen]
## What We Tried
[List approaches and outcomes, or "First consultation" if fresh question]
## Question
[Specific, focused question for codex to answer]
Provide:
1. Root cause analysis (if debugging)
2. Concrete recommendation with file:line references
3. Why previous approaches failed (if applicable)
Keep response focused and actionable.
Run codex in background (it takes 2-5 minutes for complex analysis):
codex exec -m gpt-5 \
--sandbox read-only \
-c model_reasoning_effort="high" \
-c stream_idle_timeout_ms=600000 \
-c project_doc="./CLAUDE.md" \
"prompt here"
Execution rules:
run_in_background: true in Bash toolFlags:
--sandbox read-only — codex can read all project files but cannot modify anything-m gpt-5 — codex model (adjust to latest available)model_reasoning_effort="high" — maximum reasoning depthproject_doc — passes CLAUDE.md as project contextOutput format:
**Codex Analysis:**
[Codex's response — cleaned up and formatted]
---
**Assessment:** [2-3 sentence evaluation of codex's findings]
**Next steps:** [What to do with this information]