External Reviewer — Development agent for Claude Code
Gets an independent second opinion on a finished resume or application from a different model (OpenAI Codex CLI or ChatGPT), then fact-checks what comes back.
How to install External Reviewer
Installs to ~/.claude/agents/manishvermadagar-job-search-os-external-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Manishvermadagar/job-search-os/HEAD/.claude/agents/external-reviewer.md -o ~/.claude/agents/manishvermadagar-job-search-os-external-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What External Reviewer does
name: external-reviewer description: Gets an independent second opinion on a finished resume or application from a different model (OpenAI Codex CLI or ChatGPT), then fact-checks what comes back. Use after resume-reviewer or application-verifier passes, when an outside review is wanted. tools: Read, Write, Bash
You are the external reviewer. Follow `.claude/skills/ai-cross-reviewer/SKILL.md`.
If the `codex` CLI is installed and signed in (`codex login status`), run the review non-inter
Alternatives in Development
- Startup Metrics Framework — Comprehensive guide to tracking, calculating, and optimizing key performance metrics for different s... - wsho 31.9k ★
- Codex Orchestrator — CLI tool for delegating tasks to GPT Codex agents via tmux sessions 263 ★
- Flask Route Builder — Use this agent to add, modify, or debug Flask routes in app.py 204 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Second Opinion
Gets an independent review from a NON-Claude model (via a local CLI such as kimi, or a local Ollama model) and
Fresh Eyes
Fresh-context second opinion on finished written work — a plan, a doc set, any scope. Flags wrong solution, un
Codex Consultant
An independent code review and debugging subagent that uses Codex MCP as its sole execution engine, acting as
OpenAI Assistants
Setup: OpenAI Assistants API / ChatGPT Custom GPT
Opencode
Coding subagent that runs inside opencode, on any provider and model opencode supports (OpenAI, Google, Moonsh
Ff Reviewer
Flapforge adversarial reviewer: audits a finished change for correctness, regression, purity and determinism v
Related Skills
Second O Pi Nion
A pi-coding-agent extension that lets the LLM ask a different LLM for a second opinion when it gets stuck.
Consilium
A cross-agent consultation bus: a CLI coding agent asks a different-provider agent for a second opinion — one
Ask Kilo
Get an advisory second opinion from an external non-Claude model via the kilo CLI. Prompt-only — kilo never se