blitzdotdev/blitzos/run-codex

Claude Code and agent skill by blitzdotdev/blitzos

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Run real Codex with a prompt to test and verify code during development. Use when debugging event handling, understanding Codex responses, or validating implementation changes against real behavior.

Install

npx vskill@latest install blitzdotdev/blitzos/run-codex

SKILL.md

Run Real Codex Test

This skill runs real Codex with a prompt and captures all events for analysis during development.

When to Use

  • Testing new event handlers
  • Debugging event processing issues
  • Understanding Codex response format and event order
  • Validating implementation changes against real Codex behavior
  • Seeing actual token usage, rate limits, and other metadata

How to Run

Execute the test script using npm:

bash
npm run codex-test -- -p "Your prompt here"
Options
OptionShortDescriptionDefault
--prompt-pPrompt to send to Codex (required)-
--cwd-cWorking directory for the sessionCurrent dir
--output-oOutput format: all, codex, acp, summaryall
--json-Output events as JSONfalse
--help-hShow help message-
Examples
bash
# See all events for a simple prompt
npm run codex-test -- -p "What files are in this directory?"
# Test with specific working directory
npm run codex-test -- -p "Read the README" -c /path/to/project
# See only Codex events (raw server notifications)
npm run codex-test -- -p "Hello" -o codex
# See only summary (token usage, timing, event counts)
npm run codex-test -- -p "Hello" -o summary
# Get JSON output for analysis with jq
npm run codex-test -- -p "Hello" --json | jq '.method'

Output

The script outputs events in real-time as they arrive:

  1. Codex Events ([CODEX]): Raw events from Codex app server
  • thread/started, turn/started, turn/completed
  • item/started, item/completed, item/agentMessage/delta
  • thread/tokenUsage/updated, account/rateLimits/updated
  1. ACP Events ([ACP]): Events sent to ACP connection
  • sessionUpdate with various update types
  1. Summary: Aggregated statistics
  • Stop reason, duration, event counts
  • Token usage breakdown (input, cached, output, reasoning, total)
  • Event type frequency
  1. PromptResponse: Full response object including _meta.quota.token_count

Security

  • Security scanPassed, 91 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
181
Repository forks
21
7-day trend score
26

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/blitzdotdev/blitzos/run-codex/badge)](https://verified-skill.com/skills/blitzdotdev/blitzos/run-codex)

Something wrong with this skill or its page? Tell us.