Codex.Default — AI skill for Claude Code
You are Astra, the Codex participant in this live call.
How to install Codex.Default
Installs to ~/.claude/skills/petergpt-claude-interview-codex.default/SKILL.md
mkdir -p ~/.claude/skills/petergpt-claude-interview-codex.default && curl -fsSL https://raw.githubusercontent.com/petergpt/claude-interview/HEAD/prompts/codex.default.md -o ~/.claude/skills/petergpt-claude-interview-codex.default/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Codex.Default does
You are Astra, the Codex participant in this live call. Astra is your name here; the call context gives your selected model.
Your output is sent to a speech engine. Use plain spoken text, without Markdown or speaker labels. Optional square-bracket delivery cues are supported.
Speech arrives as transcribed text and vision as supplied still images, not continuous audio or video. You have no tools for taking external actions in this call.
Alternatives in AI
- Open Multi Agent — TypeScript multi-agent orchestration engine — one runTeam() call from goal to result 5.8k ★
- User Research Skill — Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, syn 1.5k ★
- Memmy Agent — 🍙 A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memor 1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Seedeep
What Claude Code is doing between your prompt and its answer, drawn live from the logs it already writes: ever
Goal Agent
Dispatch ONE of the DTD-declared agents on a task — agent name validated against the trust contract, model and
Landscape Scan
Topic-parameterised external-intelligence scan + digest. Default topic is the AI/Claude Code/PKM landscape; pa
Mimir Config
Show active Mimir configuration (context window, thresholds, default model)
Token Save MCP
Stop your coding agent burning context on file reads. Delegates big reads to a cheap worker model and returns
Ccdeck
A live canvas for your AI agents — watch Claude Code and OpenAI Codex call tools, fork subagents and finish, i
Related Agents
GPT 5.6 Sol
General-purpose agent that runs on GPT-5.6-Sol (routed through the shunt gateway to the ChatGPT/Codex subscrip
Codex CLI Research Agent
Senior OpenAI researcher specializing in Codex CLI - researches latest context window and model availability
LLM Sec Review
LLM/agent security review specialist — prompt injection, the Agents Rule of Two, tool-call authorization, mode