codexlisted

# Codex Bridge Invoke the OpenAI Codex CLI for a second opinion from a non-Claude model. The `scripts/codex` wrapper is a thin pass-through that auto-installs the CLI via npx on first use (requires `node`/`npx` on PATH, or `mise`). Pass codex's own flags directly; the wrapper forwards everything. The wrapper pins the CLI version (24 h TTL, falls back to the last working install if npm breaks). `AGENTS_BRIDGE_CODEX_VERSION=<x.y.z>` freezes it explicitly — the only env var the wrapper reads; everything codex-native goes through codex's own flags. ## Models Configured default (`~/.codex/config.toml`): !`grep -E '^(model|model_reasoning_effort)' ~/.codex/config.toml 2>/dev/null || echo "(no ~/.codex/config.toml — codex uses its built-in default; the active model is printed in every 'exec' run header)"` Models the installed CLI accepts right now: <codex_available_models> ```! # Live model list, injected once at skill load (~0.1 s). # visibility != "list" hides codex-internal models (auto-review, reserve). # Two constraints from the injected-command permission check: # - No brace near a quote anywhere in this block, comments included: that # is "expansion obfuscation", and allowed-tools cannot override it. Hence # + concatenation in jq. CLAUDE_PLUGIN_ROOT is substituted before the check. # - The allowed-tools Bash rule must match the codex call: Bash(*) does, # Bash(*:*) does not (it reads as a literal-star prefix). # Never exit non-zero: a failed injected command abor