From claude-code-harness
Runs a Cursor Composer review as an advisory second opinion, keeping the primary verdict on the host. Invoked via cursor:review for diff sanity checks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-code-harness:cursor-review [--base <ref>] [review-scope][--base <ref>] [review-scope]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Cursor Composer (`composer-2.5-fast`) を read-only second opinion として使う review skill。primary verdict は host brain (Opus / Claude role) が出す。
Cursor Composer (composer-2.5-fast) を read-only second opinion として使う review skill。primary verdict は host brain (Opus / Claude role) が出す。
cursor:review --base origin/main
cursor:review "Phase 88.5 command namespace diff"
Cursor review is advisory. The final verdict must come from the host reviewer.
Do not pass --write to cursor-companion.sh.
Use resolver/model routing, not direct env checks:
bash scripts/resolve-impl-backend.sh --backend cursor --role reviewer
bash scripts/model-routing.sh --host cursor --role worker --field model
Prefer the existing harness-review contract when a full review is requested. This command exists for users who explicitly ask for the Cursor lane.
Resolve the Harness helper root:
HARNESS_PLUGIN_ROOT="${HARNESS_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-}}"
if [ -z "$HARNESS_PLUGIN_ROOT" ] && [ -n "${CLAUDE_SKILL_DIR:-}" ]; then
probe="$(cd "${CLAUDE_SKILL_DIR}" && pwd)"
while [ "$probe" != "/" ] && [ ! -d "$probe/scripts" ]; do
probe="$(cd "$probe/.." && pwd)"
done
[ -d "$probe/scripts" ] && HARNESS_PLUGIN_ROOT="$probe"
fi
if [ -z "$HARNESS_PLUGIN_ROOT" ]; then
echo "ERROR: HARNESS_PLUGIN_ROOT is not set and could not be derived from CLAUDE_PLUGIN_ROOT or CLAUDE_SKILL_DIR" >&2
exit 2
fi
Determine review scope:
BASE_REF="${TASK_BASE_REF:-origin/main}"
REVIEW_SCOPE="${ARGUMENTS:-}"
if [ -n "${REVIEW_SCOPE}" ]; then
set -- ${REVIEW_SCOPE}
while [ "$#" -gt 0 ]; do
case "$1" in
--base)
BASE_REF="${2:?--base requires a ref}"
shift 2
;;
--base=*)
BASE_REF="${1#--base=}"
shift
;;
*)
shift
;;
esac
done
fi
DIFF_STAT="$(git diff --stat "${BASE_REF}..HEAD")"
DIFF_TEXT="$(git diff "${BASE_REF}..HEAD")"
Ask Cursor in read-only mode:
PROMPT="$(cat <<EOF
Review this diff as an advisory second opinion. Base ref: ${BASE_REF} Requested scope: ${ARGUMENTS:-full diff}
Focus on bugs, regressions, missing tests, and unsafe assumptions. Do not propose broad refactors.
Diff stat: ${DIFF_STAT}
Diff: ${DIFF_TEXT} EOF )" bash "${HARNESS_PLUGIN_ROOT}/scripts/cursor-companion.sh" task "${PROMPT}"
4. Host reads Cursor's output and performs the primary review:
- Findings first, ordered by severity.
- Mark Cursor-originated points as advisory when used.
- `APPROVE` / `REQUEST_CHANGES` must be the host decision, not a copied Cursor verdict.
## Output
Use the standard review shape:
- findings
- open questions
- validation run
- final host verdict
npx claudepluginhub chachamaru127/claude-code-harness --plugin claude-code-harnessRuns Codex code review with an independent double-check by Claude. Translates user intent into clean Codex invocation, then verifies findings without bias.
Provides an independent code review by invoking a different AI model with zero conversation context. Useful for second opinions on code, commits, plans, or files.
Read-only delegate to cursor-agent for questions, investigation, design discussion, and adversarial sanity checks. No write access.