claude-codex-bridgelisted

# Claude Codex Bridge Use this workflow for bidirectional Claude-Codex review loops. - Claude execution -> Codex audit -> Claude repair feedback. - Codex execution -> Claude audit -> Codex repair feedback. Default to automatic return after audit unless the user explicitly asks for audit-only mode. Bridge delivery defaults to `cli` mode through the helper scripts. In `cli` mode, the target CLI performs the audit and prints the result back into this same conversation; do not use desktop App automation. CLI runs are tracked under `.agent-bridge/runs/<runId>/`. Use `.agent-bridge/runs/latest.json` to inspect the latest run. A completed run has `status: success` and `cli_done.json`; a failed run has `status: error` and `bridge_error.json`. If a run still says `status: started`, it is in progress or was interrupted; do not treat that as a successful audit. CLI preconditions: Codex CLI must be runnable for Codex audits. The bridge tries `AGENT_BRIDGE_CODEX_BIN`, then `codex` from PATH, then `/Applications/Codex.app/Contents/Resources/codex`. `claude --version` plus `claude auth status` must work for Claude audits. If the Claude auth preflight fails, tell the user to run Claude Code login/status rather than treating it as an App handoff failure. If a CLI is missing or auth fails, run: ```bash node "$HOME/.agent-bridge/bridge.mjs" doctor ``` Use the doctor's suggested fix. Common fixes are: ```bash npm install -g @openai/codex npm install -g @anthropic-ai/claude-code claude