/flow-next-spec-completion-review

name: flow-next-spec-completion-review
description: Spec completion review - verifies all spec tasks implement the spec requirements. Triggers on /flow-next:spec-completion-review.
user-invocable: false

Spec Completion Review Mode

**Workflow is backend-split. Read [workflow-common.md](workflow-common.md) for Phase 0 (backend detection + philosophy), then read ONLY the file matching your active backend:**

• `BACKEND=codex` → [workflow-codex.md](workflow-codex.md)
• `BACKEND=copilot` → [workflow-copilot.md](workflow-copilot.md)
• `BACKEND=cursor` → [workflow-cursor.md](workflow-cursor.md)
• `BACKEND=host` → [workflow-host.md](workflow-host.md)
• `BACKEND=rp` → [workflow-rp.md](workflow-rp.md)

Do not load the others — only the active backend's file is needed.

Verify that the combined implementation of all tasks in a spec satisfies the spec requirements. This is NOT a code quality review (that's impl-review's job) — this confirms spec compliance only.

**Role**: Spec Completion Review Coordinator (NOT the reviewer) **Backends** (branch on the Phase 0 `RP_ELIGIBLE` probe):

• When `RP_ELIGIBLE=1`: RepoPrompt (rp), Codex CLI (codex), GitHub Copilot CLI (copilot), Cursor CLI (cursor), or host-native (`host`)
• When `RP_ELIGIBLE=0`: Codex CLI (codex), GitHub Copilot CLI (copilot), Cursor CLI (cursor), or host-native (`host`) — rp is macOS-only; never list it in guidance you surface (`--review=rp` stays accepted)

Preamble — execute Phase 0 exactly once

**The executable Phase 0 lives in [workflow-common.md](workflow-common.md) §"Phase 0: Backend Detection" — Read it and execute it ONCE, before any other bash in this skill.** It defines `$FLOWCTL` (bundled — NOT installed globally; `which flowctl` fails, expected), probes `RP_ELIGIBLE`, resolves `$BACKEND` via the single `flowctl review-backend` call, and handles the ASK / `none` cases. Never invoke `flowctl review-backend` a second time in the same run.

Exception: a `--review=<backend>` argument (see Backend Selection below) wins — when present, set `BACKEND` from the flag and skip Phase 0's `review-backend` call + ASK handling (still run its `$FLOWCTL` / `RP_ELIGIBLE` setup lines).

When `RP_ELIGIBLE=0` (not macOS, no supported RepoPrompt CLI), never *steer* the user toward rp: every backend summary, recommendation, or override hint you surface presents only the runnable configured backends `codex`, `copilot`, `cursor`, `host` (plus `none`). Suppression is not a ban: an explicit `--review=rp`, `FLOW_REVIEW_BACKEND=rp`, or `review.backend=rp` still resolves to rp and errors at runtime via `require_rp_cli()`.

Backend Selection

**Priority** (first match wins): 1. `--review=rp|codex|copilot|cursor|host|none` argument 2. `FLOW_REVIEW_BACKEND` env var — bare backend (`rp`, `codex`, `copilot`, `cursor`, `host`, `none`) OR spec form (`codex:gpt-5.4:xhigh`, `copilot:claude-opus-4.5`, `cursor:gpt-5.5-high`); `host` is bare-only (`host:<model>` is rejected) 3. `.flow/config.json` → `review.backend` (same bare / spec forms) 4. **Error** - no auto-detection

Parse from arguments first

Check $ARGUMENTS for:

• `--review=rp` or `--review rp` → use rp
• `--review=codex` or `--review codex` → use codex
• `--review=copilot` or `--review copilot` → use copilot
• `--review=cursor` or `--review cursor` → use cursor
• `--review=host` or `--review host` → use host
• `--review=none` or `--review none` → skip review

If found, use that backend and skip all other detection.

Otherwise: Phase 0 resolves it

No `--review` flag → `$BACKEND` comes from [workflow-common.md](workflow-common.md) Phase 0 (executed once per the Preamble): the single `flowctl review-backend "$SPEC_ID"` call with ASK handling included. Do not re-resolve here.

Backend at a glance

When `RP_ELIGIBLE=0`, omit the **rp** line below from any guidance you surface (explicit `--review=rp` still honored):

• **rp** — RepoPrompt (macOS GUI); builder auto-selects context. Primary backend.
• **codex** — Codex CLI (cross-platform); uses OpenAI models (default `gpt-5.5`). `FLOW_CODEX_MODEL` / `FLOW_CODEX_EFFORT` env vars, or `--spec codex:gpt-5.4:xhigh`.
• **copilot** — GitHub Copilot CLI (cross-platform); supports Claude Opus/Sonnet/Haiku 4.5 and GPT-5.2 families via a Copilot subscription. `FLOW_COPILOT_MODEL` / `FLOW_COPILOT_EFFORT` env vars, or `--spec copilot:claude-opus-4.5:xhigh`.
• **cursor** — Cursor CLI (`cursor-agent`, cross-platform); reaches `gpt-5.5-high` (1M-ctx default), the `gpt-5.3-codex` family, `composer-2.5`, and `claude-opus-4-8-thinking-high` via a Cursor subscription. `FLOW_CURSOR_MODEL` env var, or `--spec cursor:gpt-5.5-high`. Cursor folds reasoning effort into the model name — **no effort field**.
• **host** — Bare-only non-executable selection sentinel; selected mechanics

live in [workflow-host.md](workflow-host.md).

**Spec grammar:** `backend[:model[:effort]]` — `FLOW_REVIEW_BACKEND` and `.flow/config.json review.backend` both accept this. Examples: `codex`, `codex:gpt-5.2`, `copilot:claude-opus-4.5:xhigh`, `cursor:gpt-5.5-high` (cursor takes model only — no `:effort`), `host` (bare only). Per-spec `default_review` (set via `flowctl spec set-backend`) overrides env.

Critical Rules

**For rp backend:** 1. **DO NOT REVIEW CODE YOURSELF** - you coordinate, RepoPrompt reviews 2. **MUST WAIT for actual RP response** - never simulate/skip the review 3. **MUST use `setup-review`** - handles window selection + builder atomically 4. **DO NOT add --json flag to chat-send** - it suppresses the review response 5. **Re-reviews MUST stay in SAME chat** - omit `--new-chat` after first review

**For codex backend:** 1. Use `$FLOWCTL codex completion-review` exclusively 2. Pass `--receipt` for session continuity on re-reviews 3. Parse verdict from command output

**For copilot backend:** 1. Use `$FLOWCTL copilot completion-review` exclusively 2. Pass `--receipt` for session continuity on re-reviews (session only resumes when prior receipt has `mode == "copi