CLAUDE.md@claude git:20260820.8752119A

Immutable. This exact content is served forever at /api/v1/blob/b88cf0f8418ae3b0.

# Claude Edition

This directory is the Claude Code edition of Turbo. The root [`CLAUDE.md`](../CLAUDE.md) covers project-wide context; this file adds edition-specific rules.

- Keep Claude Code tool vocabulary here: `TaskCreate`, `TaskList`, `AskUserQuestion`, the Skill tool, and Claude Agent tool phrasing are expected in this edition.
- Install/update paths point at `claude/skills/` and `~/.claude/skills/`.
- Claude peer review delegates to Codex. `/peer-review` is the stable abstraction (uses `/codex-exec` with a Turbo-controlled prompt). `/codex-exec` is the raw one-shot helper. `/consult-codex` is the consultation helper. `/codex-review` wraps Codex's built-in `codex review` CLI subcommand and has no Claude analog (Codex CLI exposes a review subcommand; Claude Code does not), so the Codex edition correctly has no `$claude-review` mirror.
- Codex-specific changes belong under [`../codex/`](../codex/), not here.
- When changing a skill, convention, addition, or setup/update/migration file here, mirror the change to the parallel file in [`../codex/`](../codex/). Translate vocabulary via [`../codex/docs/harness-vocabulary.md`](../codex/docs/harness-vocabulary.md). The two editions track each other behaviorally; vocabulary differs but principles stay aligned. Drift between editions is the most common failure mode.
- After mirroring, run [`/codex-exec`](skills/codex-exec/SKILL.md) to have Codex review the Codex sibling against `../codex/SKILL-CONVENTIONS.md` and `../codex/AGENTS.md`. Instruct it to read those conventions and the changed files and report findings directly, the way `/create-skill` reviews a skill, without invoking `$review-code` or any other skill. Review skills carry user-input gates that `codex exec` drops, stalling the run. Independent cross-edition eyes catch vocabulary leaks and behavioral drift the same-edition reviewer cannot see. Treat findings the same as a same-edition review (evaluate, apply).
- **Intentional divergence — crash retry:** `/codex-exec`'s retry-once-on-a-run-that-died-producing-nothing rule stays in this edition. Leave `$claude-print` without it: the evidence is codex-process-specific, and `$claude-print` Step 3 polls a shell session rather than observing a process, so a retry trigger there would license the premature give-up that Step 3 exists to prevent.
- **Intentional divergence — consultation option budget:** `AskUserQuestion` allows 4 options per question while Codex's `request_user_input` allows 3. Where a gate's concrete choices already fill the smaller budget, this edition adds the consultation option and the Codex edition displaces the option that fits least, routing the displaced one through "Other" with explicit freeform handling in the consuming step. `/apply-findings`, `/resolve-pr-comments`, `/create-project-skills`, and `/simplify-code` differ from their Codex siblings for this reason; keep the asymmetry when resyncing. Both editions displace at `/update-dependencies`, whose strategies already fill either budget.
- **Intentional divergence — loop autonomy:** the Codex edition deliberately runs `$polish-code`/`$refine-plan` without this edition's iteration hard cap and skip/continue `AskUserQuestion` gates, because Codex's `request_user_input` is unreliable in non-interactive modes. Keep the Claude gates as-is; do not strip them to match Codex when mirroring, and do not port Codex's autonomy here.