Help us improve
Share bugs, ideas, or general feedback.
From hotl
Dispatches code-reviewer agent at executor review checkpoints with structured context: git range, workflow contracts, intent, verification evidence.
npx claudepluginhub yimwoo/hotl-plugin --plugin hotlHow this skill is triggered — by the user, by Claude, or both
Slash command
/hotl:requesting-code-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Executors invoke `requesting-code-review` at defined checkpoints. This skill dispatches the `code-reviewer` agent with structured context. Returned findings are handled by `receiving-code-review`.
Conducts pre-merge code reviews against HOTL workflow plans, contracts, and verification artifacts using git diffs and subagents; issues READY/NOT READY verdicts.
Request an independent code review with focused context for the reviewer. Use before merging high-risk work or after subagent-driven implementation slices.
Dispatches nbl:code-reviewer subagent for code reviews using git SHAs, task details, and diffs. Use after tasks, major features, or before merging to verify requirements.
Share bugs, ideas, or general feedback.
Executors invoke requesting-code-review at defined checkpoints. This skill dispatches the code-reviewer agent with structured context. Returned findings are handled by receiving-code-review.
Only request review when the checkpoint work is in a reviewable state and its planned verification has completed. Do not request review for code that has failing required verification unless the purpose of the review is to diagnose the failure.
The review base defines the git range for the reviewer. Executors record this before starting each reviewable batch.
git rev-parse HEAD recorded by the executor before starting the batchHEAD immediately before the fix. Re-review only the changed scope unless the fix affects shared architecture, risk level, or multiple modules.When dispatching the hotl:code-reviewer agent, provide this context:
Review the following implementation work.
**Review type:** checkpoint | final | follow-up | direct
**Workflow:** {workflow_file} (or "No workflow — reviewing against stated intent")
**Steps reviewed:** {step_range} (or "N/A")
**Git range:** {review_base}..{HEAD_SHA}
**Intent contract:**
- intent: {intent}
- constraints: {constraints}
- success_criteria: {success_criteria}
- risk_level: {risk_level}
(or "No formal contract — review against stated intent and general correctness/risk")
**Implementation summary:**
{summary}
**Changed files:**
{git_diff_stat}
**Verification evidence:**
- Commands run: {verification_commands}
- Outcomes: {pass_fail_status}
- Known gaps: {limitations}
Review against the workflow plan and HOTL contracts (if provided),
or against the stated intent and general correctness/risk.
Produce findings with file:line references.
receiving-code-reviewhotl:code-review (uses READY/NOT READY verdict). Findings are returned to the user without automatically invoking receiving-code-review.