Codex Wrapped
Codex Wrapped allows you to generate creative content like code, text, and more by leveraging OpenAI's powerful language model – useful for diverse writing tasks.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add codex-wrapped npx -- -y @trustedskills/codex-wrapped
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"codex-wrapped": {
"command": "npx",
"args": [
"-y",
"@trustedskills/codex-wrapped"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill, Codex Wrapped, allows an AI agent to generate reports providing insights into usage of OpenAI's Codex model. It computes statistics over rolling time windows (last 30 days, last 7 days, and all-time focus hours) and renders these as a text-only report. The report is designed to be year-agnostic and adapts its layout based on terminal width.
When to use it
- When the user requests a "Codex Wrapped" report.
- To understand recent trends in Codex model usage.
- For periodic monitoring of focus hours spent using Codex.
Key capabilities
- Calculates usage statistics for OpenAI's Codex model over rolling time windows (last 30 days, last 7 days, all-time).
- Generates a text-only report summarizing these statistics.
- Adapts the report layout to fit terminal width.
- Supports different layout options:
columns(default) andtable.
Example prompts
- "Can you give me a Codex Wrapped report?"
- "Show me the recent usage stats for Codex."
- "Generate a report on my Codex focus hours."
Tips & gotchas
- The skill relies on Python (
get_codex_stats.py) and shell scripts (report.sh). Ensure these are executable within the agent's environment. - The intermediate statistics file
/tmp/wrapped_stats.jsonis used; consider its sensitivity before leaving it in place. Rerun the stats if you suspect they are outdated. - To force a wider report layout, set the
WRAPPED_WIDTHenvironment variable (e.g.,WRAPPED_WIDTH=120).
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🏢 Official
Published by the company or team that built the technology.