A diagnostic tool for finding and fixing problems with an Oh My Codex installation, its settings, loaded skills, and connected services.

Use it when installation fails, skills do not load, configuration is invalid, connected servers cannot be reached, or performance degrades.

It replaces scattered troubleshooting with checks for the environment, files, configuration, dependencies, and runtime connections.

How junghwaYang/oh-my-codex configures Codex

Reuse

Borrowing it

Nothing to install: this file belongs to junghwaYang/oh-my-codex. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/junghwaYang/oh-my-codex/main/.codex/skills/doctor/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/junghwaYang/oh-my-codex

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/junghwayang/oh-my-codex/doctor/github.svg)](https://agentmods.dev/skills/junghwayang/oh-my-codex/doctor)

Your own site

<a href="https://agentmods.dev/skills/junghwayang/oh-my-codex/doctor"><img src="https://agentmods.dev/badge/skills/junghwayang/oh-my-codex/doctor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/junghwayang/oh-my-codex/doctor"><img src="https://agentmods.dev/badge/skills/junghwayang/oh-my-codex/doctor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 684 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 3 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00684
Opus 5.5	$0.00000	$0.00274
Sonnet 5.5	$0.00000	$0.00137
Haiku 4.5	$0.00000	$0.00068

Measured 2mo ago against content hash 3eeb328c29c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

doctor scanned grade D with 3 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ~/.codex/config.toml | grep mcp

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls ~/.codex/skills/

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.codex/skills

.codex/skills/doctor/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doctor Skill

Diagnose and fix Oh My Codex installation issues.

When to Use

Installation problems
Configuration errors
Skill loading failures
Performance issues
After updates

Diagnostic Checks

Environment

□ Node.js version (>= 18)
□ Python version (>= 3.10)
□ Codex CLI installed
□ PATH configured correctly
□ Required permissions

Installation

□ Skills directory exists
□ All skills have SKILL.md
□ Config file valid
□ No conflicting configs
□ Dependencies installed

Configuration

□ config.toml syntax valid
□ Model names correct
□ MCP servers configured
□ API keys present (if needed)
□ Profiles defined

Runtime

□ Can spawn agents
□ MCP servers reachable
□ Sessions directory writable
□ No zombie processes
□ Memory usage normal

Common Issues

"omc: command not found"

# Add to PATH
export PATH="$HOME/.local/bin:$PATH"

# Verify
which omc

"Skill not loading"

# Check skill exists
ls ~/.codex/skills/

# Verify SKILL.md present
cat ~/.codex/skills/autopilot/SKILL.md

"MCP connection failed"

# Test MCP server
npx -y codex mcp

# Check config
cat ~/.codex/config.toml | grep mcp

"Agent SDK not available"

# Install full package
pip install oh-my-codex[full]

# Or install SDK directly
pip install openai-agents-sdk

Repair Actions

Reset Configuration

# Backup current
cp ~/.codex/config.toml ~/.codex/config.toml.bak

# Reset to default
omx --reset-config

Reinstall Skills

# Remove and reinstall
rm -rf ~/.codex/skills
./install.sh

Clear Cache

# Clear sessions
rm -rf ~/.codex/sessions/*

# Clear errors
rm -rf ~/.codex/errors/*

Usage

doctor: check my Oh My Codex installation

doctor: why aren't skills loading

doctor: diagnose slow performance

Output Format

## Oh My Codex Health Check

### Environment
✅ Node.js: v22.12.0
✅ Python: 3.12.0
✅ Codex CLI: 1.2.3
⚠️ PATH: ~/.local/bin not in PATH

### Installation
✅ Skills directory: ~/.codex/skills
✅ Skills installed: 20
✅ Config: Valid

### Runtime
✅ Agent SDK: Available
❌ MCP GitHub: Connection failed
✅ Sessions: Writable

### Issues Found
1. **PATH Configuration**
   - ~/.local/bin not in PATH
   - Fix: Add to ~/.zshrc

2. **MCP GitHub**
   - Connection refused
   - Fix: Check GITHUB_TOKEN

### Recommended Actions
1. Run: export PATH="$HOME/.local/bin:$PATH"
2. Set GITHUB_TOKEN environment variable

Read the full file on GitHub · 159 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 159 lines · 0 tokens per session scan D 3eeb328c29c9

Subscribe to this mod's changes

doctor is a skill published in the GitHub repository junghwaYang/oh-my-codex (5 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 684 tokens. A static security scan graded it D with 3 findings (reads agent configuration directories, enumerates other installed skills, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Debugging

doctor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
doctorjunghwaYang/oh-my-codex	Skill	5	8mo ago	MIT	D	0	Codex
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	today	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	319	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	today	Apache-2.0	A	15	Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthog	Skill	41k	today	none	A	76	Claude Code, Codex
loop-engineeringhuytieu/COG-second-brain	Skill	1.3k	15d ago	MIT	A	63	Claude Code

oh-my-codex: Skill for Codex