git:20261005.41e388b to git:20261006.f0a700f

---

---

Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).

Arguments: $ARGUMENTS

- No arguments: review uncommitted changes (default)

- `--base <branch>`: full branch diff against a base

- `--commits`: review only the most recent commit

- `--files "a.cs b.cs"`: explicit file list

- `--spec <path>` (repeatable): also check the changes against these specs (design doc, plan, or any doc that records the user's decisions)

## Review Scope Selection (no scope argument)

`--spec`, `--prompt`, and the other flags do not choose the scope. Unless `$ARGUMENTS` has `--base`, `--commits`, or `--files`, pick the scope below and pass it along with the other flags. `--auto` belongs to this skill; the script ignores it.

Override order:

1. **User specified a scope** (e.g. "review Phase 8") → follow user intent

2. **No uncommitted changes but branch has commits** → `git diff --name-only develop...HEAD -- '*.cs'`

3. **User says "review the whole branch"** → `--base develop`

Pass the file list to the review script as `--files`.

## Spec Check

When the changes finish a feature or a milestone, also pass its design doc and plan with `--spec` (next to the scope from above). The review then also lists what the specs ask for that the code does not do, what it does differently, and protections or restrictions nobody asked for. Skip it for small fixes. **Rounds 2+** use the same scope (recomputed the same way, plus every file this review's fixes created or changed) and the same flags, without `--spec`: the `[Spec]` items were listed and verified in round 1.

## Execution Flow

- No `[Critical]` issues in the review result, and no code was written for `[Spec]` items this round

- 5 rounds have been completed

Each round:

#### a. Send to Claude for Review

```bash

${CLAUDE_PLUGIN_ROOT}/bin/claude-review.sh $ARGUMENTS

```

**From round 2 onward:** If the previous round had findings deemed over-engineered, append `--prompt` to the round-2 arguments (see Spec Check):

```bash

${CLAUDE_PLUGIN_ROOT}/bin/claude-review.sh <round-2 arguments> --prompt "Review these code changes using the same criteria as round 1 (bugs, architecture, performance, security, style). Additional context: the following suggestions from the previous round were deemed over-engineered and replaced with simpler solutions: <list items and rationale>. Do not re-suggest more complex approaches unless the simpler version introduces a real defect. Classify by severity: [Critical] [Moderate] [Suggestion]."

```

#### b. Summarize Review Results

```bash

source "${CLAUDE_PLUGIN_ROOT}/scripts/platform/detect.sh"

if qq_session_id && [[ -f "$QQ_TEMP_DIR/review-gate-$QQ_SESSION_ID" ]]; then

IFS=: read -r ts count _ < "$QQ_TEMP_DIR/review-gate-$QQ_SESSION_ID"

echo "${ts}:${count}:N" > "$QQ_TEMP_DIR/review-gate-$QQ_SESSION_ID"

fi

```

#### d. Fix the Code

- For each **confirmed** critical issue, locate and fix the code

- For findings flagged as **Confirmed but over-engineered**, apply a simpler alternative fix

- For confirmed moderate issues, apply fixes at your discretion

- Fix a bug by correcting the logic or the numbers. Protections, added restrictions, and scope cuts are the user's call ([`shared/user-decisions.md`](../../shared/user-decisions.md)): if the only fix you see is one of them, or a confirmed Unrequested `[Spec]` item is one without the user's words, put it on the "Needs the user's decision" list and keep the normal rule in the code

- **Confirmed Missing or Wrong `[Spec]` items:** finish or fix them (not-due-yet items wait for their milestone); if one is too big for this pass, list it in the handoff, never drop it silently

- After all fixes, present a summary of changes to the user

#### e. Decide Whether to Continue

- If this round had `[Critical]` issues confirmed and fixed → automatically start the next round (back to a)

- If you wrote code for `[Spec]` items this round → run one more round (see Spec Check) so that code gets reviewed, even with no `[Critical]` issues

- Otherwise, if this round had no `[Critical]` issues → output "Review passed" and end the loop

- If 5 rounds are complete → output final status and end the loop

Print `=== Round N/5 ===` at the start of each round.

After the review loop ends (for any reason), clean up the gate marker:

```bash

source "${CLAUDE_PLUGIN_ROOT}/scripts/platform/detect.sh"

if qq_session_id; then rm -f "$QQ_TEMP_DIR/review-gate-$QQ_SESSION_ID"; fi

```

## Handoff

After the review loop ends, recommend the next step:

- **Review passed, no issues** → "Code looks good. Want to run `/qq:test` to verify?"

- **Issues were found and fixed** → "Fixed N issues. Want to run `/qq:test` to make sure nothing broke?"

- **Open `[Spec]` items or "Needs the user's decision" entries** → list each with its spec line, and whether it waits for a later milestone or for the user (also in `--auto` mode; don't wait for answers)

- **5 rounds exhausted with remaining issues** → "Some issues remain after 5 rounds. Run `/qq:test` to check impact, or continue fixing manually?"

**`--auto` mode:** run `qq-execute-checkpoint.py pipeline-advance --project . --completed-skill "/qq:claude-code-review" --next-skill "/qq:test"`, then invoke `/qq:test --auto`.

## Notes

- When fixing, only address the actual issues the review identified — do not opportunistically refactor surrounding code