prompt-evaluation-runn…
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Use when another local agent needs a one-shot Codex CLI answer and interactive behavior is acceptable or controlled.
$ npx -y skills add yeaight7/agent-powerups --skill relay-codex --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/relay-codexContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when another local agent needs a one-shot Codex CLI answer and interactive behavior is acceptable or controlled.
name: relay-codex description: Use when another local agent needs a one-shot Codex CLI answer and interactive behavior is acceptable or controlled.
Send a bounded prompt to the local Codex CLI through Agent Powerups relay when Codex is useful as an external reviewer or implementation advisor.
Compatible with: `claude-code`, `gemini-cli`, `generic`
Requires:
Do not use when an interactive TUI would block automation. Check local Codex behavior first.
1. Verify the CLI is available and note whether it opens an interactive UI:
codex --version
2. Start a Codex relay session:
apx relay start <name> --provider codex
3. Send one focused prompt:
apx relay ask <name> "<prompt>"
4. Read the relay artifact and verify claims locally before acting. 5. Stop the session unless it is deliberately needed:
apx relay stop <name>
Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
Repo: yeaight7/agent-powerups
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases.
Use when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or silent failures, or an…
Use when routing a prompt to a local provider CLI for a second opinion, review, or plan -- you are about to call a provider directly, need the response saved…
Use when starting work in an unfamiliar area of a codebase, spawning a subagent that needs targeted file context, a first search pass missed the relevant file,…