cr-code-gate
【Code Review 子 Agent · 门控二】对 git diff 逐项执行代码质量门控检查（运行时异常、性能瓶颈、安全漏洞、权限缺失、破坏性变更等 10 项），按 LOGAF h/m/l 分级输出，h 级清零后方可进入门控三。由 spec-driven-dev 的 code_review 阶段自动调用。
Best for CI/CD pipelinesWorks with GitHubLow risk
⌘source
- author
@LeoYeAI- language
- Python
★2kstars
306forks
May 6, 2026
✦overview.md
Key Features
- ·Scans git diff for 10 quality gate checks
- ·Classifies findings by LOGAF severity (h/m/l)
- ·Blocks progression if high-severity issues found
- ·Automatically invoked by spec-driven-dev pipeline
Use Cases
- →Run as second gate in a multi-stage code review pipeline
- →Automatically block PRs with runtime or security issues
- →Enforce coding standards without manual review
Best for
- ✓CI/CD pipelines
- ✓multi-stage review workflows
Not ideal for
- !one-off code reviews
- !non-diff-based analysis
FAQs
name
cr-code-gate
description
【Code Review 子 Agent · 门控二】对 git diff 逐项执行代码质量门控检查（运行时异常、性能瓶颈、安全漏洞、权限缺失、破坏性变更等 10 项），按 LOGAF h/m/l 分级输出，h 级清零后方可进入门控三。由 spec-driven-dev 的 code_review 阶段自动调用。
user-invocable:false
metadata:{"openclaw":{"emoji":"🔬","requires":{"bins":["git"]},"calledBy":["spec-driven-dev"]}}
cr-code-gate
Code Review 流水线的第二道门控：代码质量静态门控子 Agent。
由 spec-driven-dev 的 code_review 阶段在 cr-commit-check 通过后调用，
对 diff 进行结构性问题扫描，参照 Sentry 工程实践的必检项分类。
调用契约
输入（由 Orchestrator 注入上下文）
| 字段 | 类型 | 说明 |
|---|---|---|
us_id | string | 用户故事 ID |
iter_id | string | 当前迭代 ID |
git_diff | string | git diff main...HEAD 的完整输出 |
iter_summary_path | string | requirements/{us_id}/docs/iteration_summary/current_iter.md 路径，用于核查架构变更审批记录 |
coding_standards_path | string | auxiliary/coding_standards.md 路径 |
Orchestrator 调用示例（OpenCode Sub-Agent 格式）：
invoke_skill: cr-code-gate
with:
us_id: "US042"
iter_id: "iter_003"
git_diff: "<diff output>"
iter_summary_path: "requirements/US042/docs/iteration_summary/current_iter.md"
coding_standards_path: "auxiliary/coding_standards.md"
输出（写回 Orchestrator）
{
"agent": "cr-code-gate",
"verdict": "PASS | WARN | FAIL",
"h_count": 0,
"m_count": 0,
"l_count": 0,
"findings": [
{
"id": "GK-01",
"logaf": "h",
"result": "PASS | FAIL | WARN",
"file": "src/foo.py:42",
"description": "…",
"suggestion": "…"
}
]
}
$install
1-click copynpx skills add LeoYeAI/openclaw-master-skills --skill cr-code-gateSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
5/ 5
excellentVery clear and well structured, with almost no room for misunderstanding.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
5/ 5
very highHighly actionable with clear, concrete steps that an agent can follow directly.