Ask Claude
Purpose
Use local Claude Code CLI as an external advisor for focused questions, reviews, or design checks. The workflow is local-first and always leaves a Markdown artifact.
When to Use
- Need a Claude second opinion from Codex App or another shell-capable agent.
- Want reviewable output from
claude -psaved for later. - Do not use when Claude CLI is missing or unauthenticated.
- Do not use as an MCP fallback.
Inputs
- A specific prompt or task.
- Local
claudecommand available in PATH. - Optional artifact directory.
Workflow
Run through APX:
apx ask-claude "Review this patch for correctness"
Equivalent nested APX and direct CLI calls:
apx ask claude "Review this patch for correctness"
claude -p "Review this patch for correctness"
If claude is missing, stop and ask the user to install/configure Claude Code CLI. Verify with:
claude --version
Output
APX writes:
.apx/artifacts/claude-<slug>-<timestamp>.md
Artifact sections:
- Original user task
- Final prompt sent to Claude CLI
- Claude output (raw)
- Concise summary
- Action items / next steps
Verification
apx check ask-claude
apx ask-claude "Return OK only" --json
Confirm JSON includes provider, artifactPath, promptLength, and raw output in stdout. Open the artifact before applying advice.
Failure Modes
- Missing CLI: do not use MCP; ask user to install/configure
claude. - Auth failure: keep artifact if APX created one, report CLI stderr.
- Broad prompt: narrow the question before running to avoid noisy advice.