菜单
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/evanfang0054/agent-harness --skill requesting-code-review命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | requesting-code-review |
| description | Use when completing tasks, implementing major features, or before merging to verify work meets requirements |
| when_to_use | [feedback] Triggered after implementation is complete to request peer review. |
Dispatch agent-harness:code-reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.
Core principle: Review early, review often.
Mandatory:
Optional but valuable:
1. Get git SHAs:
BASE_SHA=$(git rev-parse HEAD~1) # or origin/main
HEAD_SHA=$(git rev-parse HEAD)
2. Dispatch code-reviewer agent:
Invoke the code-reviewer agent (defined in agents/code-reviewer.md). Give it precisely constructed work-product context:
BASE_SHA and HEAD_SHANever pass the coordinator's full session history. Do not inline a review diff into the coordinator context: the reviewer reads the package and returns findings only.
Use this dispatch structure, omitting only unavailable optional work products:
agent-harness:code-reviewer
Requirements / DoD: ...
BASE_SHA: ...
HEAD_SHA: ...
Task brief: ...
Task report: ...
Review package: ...
Do not send: coordinator full session history or reasoning; inline diff
Reviewer: read the review package
Return: findings only, labeled Standards or Spec; severity Critical, Important, or Minor
Placeholders:
{WHAT_WAS_IMPLEMENTED} - What you just built{PLAN_OR_REQUIREMENTS} - What it should do{BASE_SHA} - Starting commit{HEAD_SHA} - Ending commit{DESCRIPTION} - Brief summaryEvery review request must ask the reviewer to check both axes:
Do not let one axis hide the other. A clean implementation that misses the spec is still a failed review. A spec-complete implementation with Critical quality or security issues is still a failed review.
3. Act on feedback:
scripts/log-phase-metric.sh --phase requesting-code-review --action gate --gate-result passed --spec-topic "$SPEC_TOPIC"
[Just completed Task 2: Add verification function]
You: Let me request code review before proceeding.
BASE_SHA=$(git log --oneline | grep "Task 1" | head -1 | awk '{print $1}')
HEAD_SHA=$(git rev-parse HEAD)
[Dispatch agent-harness:code-reviewer subagent]
WHAT_WAS_IMPLEMENTED: Verification and repair functions for conversation index
PLAN_OR_REQUIREMENTS: Task 2 from docs/agent-harness/plans/deployment-plan.md
BASE_SHA: a7981ec
HEAD_SHA: 3df7661
DESCRIPTION: Added verifyIndex() and repairIndex() with 4 issue types
[Subagent returns]:
Strengths: Clean architecture, real tests
Issues:
Important: Missing progress indicators
Minor: Magic number (100) for reporting interval
Assessment: Ready to proceed
You: [Fix progress indicators]
[Continue to Task 3]
Subagent-Driven Development:
Executing Plans:
Ad-Hoc Development:
Never:
If reviewer wrong:
See template at: requesting-code-review/code-reviewer.md
You MUST use this before any creative work — features, components, behavior changes. Explores intent, requirements, and design before implementation.
Use when implementation is done and tests pass, and the user must choose how to integrate or retain completed branch work.
Use when receiving code review feedback. Verify before implementing; technical correctness over blind agreement.