Codex Bridge (shared mechanics)

This is a reference skill. Don't trigger it on its own — the three workflow skills (codex-review-plan, review-codex-plan, plan-debate) read it so the Codex-calling mechanics live in exactly one place.

The wrapper

All Codex calls go through one saved script (never inline the codex exec invocation):

~/.claude/skills/codex-bridge/codex-exec.sh <project_dir> <out_file> [extra codex args...]

• The full prompt (instructions + the plan/text) is piped to stdin.
• The agent's final message (the review) is written to <out_file> and echoed to stdout.
• Codex runs --sandbox read-only: it reads the codebase but cannot modify anything.
• --skip-git-repo-check is on (research dirs often aren't git repos).

Standard call (from a Bash tool call)

PROMPT_FILE=/tmp/codex-prompt-$$.md      # compose instructions + <PLAN> into this
OUT=/tmp/codex-plan-review-$$.md
bash ~/.claude/skills/codex-bridge/codex-exec.sh "$PROJECT_DIR" "$OUT" < "$PROMPT_FILE"

Always set a long Bash timeout (~600000 ms). Effort defaults to the config's model_reasoning_effort (see ~/.codex/config.toml), which can take several minutes at high settings.

Model (important — ChatGPT-account auth)

The wrapper does not force a model: ~/.codex/config.toml decides. This matters if you authenticate Codex with a ChatGPT account rather than an API key, because exec rejects some models under that auth.

• Override with env CODEX_REVIEW_MODEL=<model> or by passing -m <model> to the wrapper (your -m wins).
• Available slugs are listed in ~/.codex/models_cache.json.

If you ever see "not supported when using Codex with a ChatGPT account", that model isn't allowed under this auth — pick another slug from the cache file.

Speed overrides (optional extra args)

• Faster turnaround: append -c model_reasoning_effort=high (or =low for smoke tests).
• Or pass a lighter model with -m <model>.

Binary location

Codex ships inside the ChatGPT desktop app and is usually not on PATH. The wrapper resolves it as command -v codex → fallback /Applications/ChatGPT.app/Contents/Resources/codex-cli/CodexCLI.app/Contents/MacOS/codex → fallback /Applications/Codex.app/Contents/Resources/codex (old standalone app). If it can't find any, it exits 127 with an install hint.

Reviewer prompt template

Compose this (filling <PLAN>) and pipe it to the wrapper. For review-codex-plan's "generate a plan first" path, swap in the drafting variant below.

Review template:

You are a senior engineer doing an adversarial review of another AI's implementation plan for THIS repository. Read whatever files you need to validate it against the actual code. Identify, concretely and with file:line references:

1. Incorrect assumptions about the codebase or existing APIs.
2. Missing steps, edge cases, or dependencies the plan overlooks.
3. Risky or breaking changes, and how to de-risk them.
4. Simpler / more idiomatic approaches that reuse existing code.
5. What the plan gets right (brief).

End with (a) a prioritized, actionable fix list and (b) a one-line verdict: ship / revise / rethink. Be terse and specific. Critique — do not rewrite the whole plan.

<PLAN>
...plan text here...
</PLAN>

Drafting template (for the reverse direction):

You are a senior engineer. Produce a concrete, step-by-step implementation plan for the task below, grounded in THIS repository (read files as needed). Name the specific files/functions to change, call out risks and edge cases, and prefer reusing existing code. Keep it tight and actionable.

Task: ...

Output conventions (per the user's CLAUDE.md)

• Keep the full Codex review in the temp <out_file> (e.g. /tmp/codex-plan-review-*.md). Do not paste the whole thing into chat.
• Summarize the key points in ≤10 lines in chat, then act on them.

Resolving <project_dir>

The directory whose code the plan is about — so Codex can validate against real files. Infer from the plan content (a referenced project path); otherwise use the current working directory. --skip-git-repo-check makes non-repo dirs fine.