Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Kokxi/qa-test-skills --skill qa-release-risk-governancegit clone --depth 1 https://github.com/Kokxi/qa-test-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kokxi/qa-test-skills/qa-release-risk-governance)<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-release-risk-governance"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-release-risk-governance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kokxi/qa-test-skills/qa-release-risk-governance"><img src="https://agentmods.dev/badge/skills/kokxi/qa-test-skills/qa-release-risk-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00121 | $0.02843 |
| Opus 5 | $0.00060 | $0.01422 |
| Sonnet 5 | $0.00024 | $0.00569 |
| Haiku 4.5 | $0.00012 | $0.00284 |
Grade A, and why
qa-release-risk-governance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ 安全警告:本技能的示例可能涉及发布决策、灰度方案和回滚操作。 实际使用时请勿直接执行发布或回滚,先确认审批权限、灰度比例和回滚预案。 本技能仅在 workspace/ 输出评估文件,不持久化、不外传、不跨会话复用。
发布风险管理
核心原则
发布决策不仅仅是"Bug都修完了没",而是综合判断变更影响面、灰度策略、回滚能力。
发布风险评估矩阵
维度1:变更特征分析
变更范围:
├─ 代码变更量:新增/修改/删除行数
├─ 文件影响面:涉及多少文件
├─ 模块影响面:涉及多少模块
├─ 接口影响面:涉及多少接口
└─ 数据影响面:涉及多少数据表
风险等级:
- 大变更:>1000行/>20文件/>5模块
- 中变更:500-1000行/10-20文件/3-5模块
- 小变更:<500行/<10文件/<3模块
维度2:变更类型风险
高风险变更:
├─ 数据库变更:表结构/索引/数据迁移
├─ 核心逻辑变更:支付/认证/权限
├─ 配置变更:生产环境配置
├─ 依赖变更:第三方库/服务升级
└─ 架构变更:服务拆分/合并
中风险变更:
├─ 业务规则变更:计算逻辑/流程
├─ 接口变更:入参/出参/协议
├─ UI变更:页面/交互/样式
└─ 性能优化:缓存/异步/并发
低风险变更:
├─ Bug修复:不影响主流程
├─ 文案修改:提示信息/文档
├─ 日志调整:日志级别/格式
└─ 测试相关:测试代码/配置
维度3:业务影响评估
影响范围:
├─ 用户影响:影响多少用户
├─ 功能影响:影响哪些功能
├─ 收入影响:是否影响交易
├─ 声誉影响:是否影响品牌形象
└─ 合规影响:是否影响合规要求
影响等级:
- 高影响:核心功能/大量用户/收入相关
- 中影响:次要功能/部分用户
- 低影响:边缘功能/少量用户
灰度策略设计
📌 本节与 qa-shift-right「阶段1:灰度发布」内容同步,修改时请同步更新两处。
灰度维度
灰度策略:
├─ 用户灰度:按用户ID/比例
│ ├─ 内部员工 → 白名单用户 → 10% → 50% → 100%
│ └─ 适用:新功能/高风险功能
│
├─ 流量灰度:按流量比例
│ ├─ 1% → 10% → 30% → 50% → 100%
│ └─ 适用:性能优化/算法变更
│
├─ 地域灰度:按地域
│ ├─ 某城市 → 某省份 → 全国
│ └─ 适用:地域性功能
│
└─ 时间灰度:按时间段
├─ 低峰期 → 高峰期
└─ 适用:定时任务/批处理
灰度监控指标
监控指标:
├─ 业务指标:
│ ├─ 订单量/交易量
│ ├─ 转化率/成功率
│ └─ 用户活跃度
│
├─ 技术指标:
│ ├─ 错误率/异常率
│ ├─ 响应时间/吞吐量
│ └─ 资源使用率
│
└─ 用户反馈:
├─ 投诉量
├─ 客服咨询量
└─ 社交媒体反馈
灰度回滚条件
回滚触发条件:
├─ 业务指标异常:
│ ├─ 订单量下降 > 20%
│ ├─ 成功率下降 > 5%
│ └─ 用户投诉增加 > 50%
│
├─ 技术指标异常:
│ ├─ 错误率 > 1%
│ ├─ 响应时间增加 > 50%
│ └─ CPU/内存使用率 > 80%
│
└─ 用户反馈异常:
├─ 投诉量激增
└─ 负面舆情
回滚方案设计
回滚类型
回滚方式:
├─ 代码回滚:回滚代码版本
│ ├─ 适用:代码变更导致的问题
│ ├─ 步骤:git revert → 部署 → 验证
│ └─ 风险:可能影响数据兼容性
│
├─ 配置回滚:回滚配置
│ ├─ 适用:配置变更导致的问题
│ ├─ 步骤:恢复配置 → 重启服务
│ └─ 风险:配置丢失
│
├─ 数据回滚:回滚数据
│ ├─ 适用:数据变更导致的问题
│ ├─ 步骤:数据备份恢复 → 验证
│ └─ 风险:数据丢失
│
└─ 服务回滚:回滚服务版本
├─ 适用:服务升级导致的问题
├─ 步骤:部署旧版本 → 验证
└─ 风险:版本兼容性
回滚检查清单
回滚前检查:
├─ [ ] 回滚方案确认
├─ [ ] 回滚权限准备
├─ [ ] 数据备份完成
├─ [ ] 相关方通知
└─ [ ] 回滚时间窗口
回滚执行:
├─ [ ] 执行回滚操作
├─ [ ] 验证服务状态
├─ [ ] 验证业务功能
├─ [ ] 验证数据一致性
└─ [ ] 监控系统指标
回滚后处理:
├─ [ ] 通知相关方
├─ [ ] 记录回滚原因
├─ [ ] 分析问题根因
├─ [ ] 制定修复方案
└─ [ ] 安排重新发布
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago Changed ca60760d8fa5
- 12d ago First seen · 314 lines · 121 tokens per session scan A b30a50584abc
qa-release-risk-governance is a skill published in the GitHub repository Kokxi/qa-test-skills (27 stars, last pushed 10d ago), licensed MIT. It adds 121 tokens to every session and 2,843 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
sparc-methodology
SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration.
swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows.
code-review
Reviews Spec Kit code changes for positive and negative test coverage, regression evidence for bug fixes, and consistent repository terminology. Use when reviewing a diff or pull request. Do not use for implementing changes or posting GitHub review actions.
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
lovable
Lovable MCP tool usage — deploy projects, message agent, test with agent-browser. Minimize credits by delegating to local repo.
agent-browser
Browser automation via Chrome/Chromium CDP — open, snapshot, click, screenshot. For testing web apps, mobile layouts, and automated interactions without Playwright/Puppeteer.