Ask Claude

Use this skill when the user wants an independent Claude Code review while working in Codex. This shells out to the Claude CLI and does not require MCP.

Preconditions

• claude should be installed and authenticated. If it isn't, don't block — use the Fallback at the end.
• The user must approve shell execution when required by the environment.
• Do not pass secrets, credentials, private production data, or sensitive customer data into the prompt.
• Follow docs/cross-agent-review.md when present.

Default: Single-Pass Review

1. Identify the artifact to review:
   • A plan from the current conversation
   • A file path
   • A diff
   • A proposed architecture or decision

2. Build a concise prompt for Claude:

   You are an independent engineering reviewer.
   Do not edit files.
   Do not run write operations.
   Review the plan/artifact below for:
   - incorrect assumptions
   - missing risks
   - simpler alternatives
   - validation gaps
   - questions the primary agent should ask the user
   
   Return:
   AGREEMENTS:
   DISAGREEMENTS:
   RISKS:
   SUGGESTED CHANGES:
   QUESTIONS:
   VERDICT: APPROVE | REVISE | RETHINK
   
   <plan/artifact/context>

3. Verify Claude CLI is available when practical:

   claude --version

4. Run Claude in print/plan mode. Write the prompt to a temp file and pipe it via stdin — long inline prompts are unreliable as CLI arguments — in a single shell invocation (shell state doesn't survive across tool calls):

   PROMPT_FILE="$(mktemp)"
   cat > "$PROMPT_FILE" <<'EOF'
   ...the full prompt...
   EOF
   claude -p --permission-mode plan < "$PROMPT_FILE"
   rm -f "$PROMPT_FILE"

5. Summarize Claude's response for the user:
   • Verdict (APPROVE / REVISE / RETHINK)
   • Agreements
   • Gaps or disagreements
   • Plan changes worth adopting
   • Questions to ask before proceeding
6. Stop and wait for the user.

Advanced: Bounded Loop

Use loop mode only when the user explicitly asks for a loop, debate, back-and-forth, or "have Codex and Claude work it out."

Rules:

• Maximum 2 rounds by default.
• Maximum 3 rounds if the user explicitly asks, or without asking when a HIGH security, auth, data-loss or concurrency finding is still open with evidence after round 2; say so in the synthesis. Never more than 3.
• A timeout, an error, or no reply from Claude is not approval, and neither is reaching the cap.
• No file edits during the loop.
• Each round must get shorter and more specific.
• Stop early when the remaining disagreement is a product judgment, user preference, or low-impact implementation detail.
• Never ask Claude to call Codex back. The current Codex session owns the loop.

Loop structure:

1. Round 1: Ask Claude for broad critique.
2. Codex summarizes what it accepts, rejects, and wants challenged, as a findings ledger: a stable id per finding (F1, F2, …) with its outcome — fixed, disputed with evidence, or declined as a follow-up ("Findings ledger" in docs/cross-agent-review.md).
3. Round 2: Ask Claude only about unresolved disagreements or high-risk gaps. Send the ledger plus only the changed parts, and ask Claude to mark each id resolved or still open.

4. Produce final synthesis:

   FINAL SYNTHESIS:
   - What both agents agree on
   - What changed in the plan
   - Remaining disagreements
   - User decisions needed
   - Recommended next step

Then stop and wait.

Fallback

If claude is missing, not authenticated, or blocked, say so and perform a local critique instead. Do not pretend Claude reviewed it.