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 serejaris/kimi-skills --skill incident-retrospectivegit clone --depth 1 https://github.com/serejaris/kimi-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/serejaris/kimi-skills/incident-retrospective)<a href="https://agentmods.dev/skills/serejaris/kimi-skills/incident-retrospective"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/incident-retrospective/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/serejaris/kimi-skills/incident-retrospective"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/incident-retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00164 | $0.03506 |
| Opus 5 | $0.00082 | $0.01753 |
| Sonnet 5 | $0.00033 | $0.00701 |
| Haiku 4.5 | $0.00016 | $0.00351 |
Grade A, and why
incident-retrospective 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 9d 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 — 282 lines — stays where its author put it; the contents beside it link to each section on GitHub.
postmortem-writer
基于 Google SRE 和行业最佳实践的 Blameless Postmortem 撰写流程。通过结构化的 SOP 引导你完成从事故信息收集、时间线梳理、5 Whys 根因分析到改进措施制定的完整复盘过程，输出专业的事故复盘文档。
核心理念：Blameless（无责文化） — 关注系统和流程的改进，而不是追责个人。
Quick Start
交互式复盘（推荐）：直接描述你的事故情况，Agent 将按照 SOP 流程引导你逐步完成复盘。
一键生成文档：如果你已经有完整的事故信息，可以用脚本快速生成格式化的复盘文档：
python3 scripts/generate_postmortem.py --interactive
或提供 JSON 输入直接生成：
python3 scripts/generate_postmortem.py --input incident.json --output postmortem.md
SOP 流程：六步完成专业复盘
第一步：事故概况收集
收集以下基本信息，构建事故全貌：
| 字段 | 说明 | 示例 |
|---|---|---|
| 事故标题 | 简明描述故障现象 | 支付服务 P99 延迟飙升至 30s |
| 严重等级 | P0 ~ P3（见下方分级标准） | P1 |
| 影响开始时间 | 用户首次受影响的时间 | 2024-03-15 14:32 UTC+8 |
| 影响结束时间 | 故障完全恢复的时间 | 2024-03-15 16:45 UTC+8 |
| 持续时长 | 自动计算或手动填写 | 2h13m |
| 影响范围 | 受影响的用户/服务/区域 | 华东区 ~30% 用户支付失败 |
| 值班人 / 响应团队 | 参与处理的关键人员 | SRE on-call: 张三, 支付团队: 李四 |
严重等级分级标准：
| 等级 | 定义 | 典型场景 |
|---|---|---|
| P0 | 全站/核心业务不可用，影响大量用户 | 主站宕机、数据库集群故障、支付系统全面瘫痪 |
| P1 | 核心功能严重降级，影响显著比例用户 | 搜索不可用、下单成功率下降50%、API 错误率 > 10% |
| P2 | 非核心功能受损，或核心功能轻微降级 | 推荐系统延迟升高、个别区域服务异常、后台管理页面不可用 |
| P3 | 轻微问题，用户基本无感知 | 日志采集延迟、内部监控页面异常、非关键定时任务失败 |
第二步：时间线梳理
按时间顺序记录事故全过程，精确到分钟。每个事件需标注类别：
| 类别标签 | 说明 |
|---|---|
| TRIGGER | 触发故障的事件 |
| DETECT | 发现/告警事件 |
| ACTION | 采取的应对操作 |
| RESOLVE | 恢复/修复事件 |
| INFO | 其他信息性事件 |
时间线示例：
14:25 ACTION 部署 payment-service v2.3.1 到生产环境
14:32 TRIGGER 支付成功率从 99.8% 开始下降
14:35 DETECT 监控告警：支付成功率 < 95%
14:38 DETECT 客服接到用户反馈支付失败
14:42 ACTION 值班 SRE 开始排查，定位到 payment-service
14:55 ACTION 尝试重启 payment-service pod（无效）
15:10 ACTION 分析日志发现数据库连接池耗尽
15:25 ACTION 回滚 payment-service 到 v2.3.0
15:30 RESOLVE 支付成功率恢复至 99.5%
16:45 RESOLVE 积压订单全部处理完毕，确认完全恢复
关键度量指标（梳理时间线时同步记录）：
- TTD (Time to Detect)：从故障发生到被发现的时间
- TTR (Time to Resolve)：从故障发现到恢复的时间
- TTN (Time to Notify)：从故障发现到通知相关方的时间
- 影响用户数 / 影响请求数 / 经济损失估算
第三步：5 Whys 根因分析
5 Whys 是一种通过反复追问"为什么"来穿透表面原因、找到根本原因的分析方法。
执行规则：
- 从直接原因开始，每次追问"为什么会发生这个？"
- 至少问 5 层，直到触及可改进的系统/流程层面
- 每一层的回答必须基于事实和证据，不是猜测
- 如果一个"为什么"有多个原因，分支展开分别分析
- 最终的根因应该指向系统或流程缺陷，而不是某个人的失误
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 282 lines · 164 tokens per session scan A b3beca143f29
incident-retrospective is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 3,506 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
investigate
Systematically investigate bugs, test failures, build errors, performance issues, or unexpected behavior by cycling through characterize-isolate-hypothesize-test steps. Use when the user asks to "investigate this bug", "debug this", "figure out why this fails", "find the root cause", "why is this broken"…
audit
Project-wide health audit pipeline that fans out to all analysis skills in parallel, evaluates findings, and produces a unified report at .turbo/audit.md. Use when the user asks to "audit the project", "run a full audit", "project health check", "audit my code", "codebase audit", or "comprehensive review".
consult-oracle
Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says "ask the oracle", "consult oracle", "consult chatgpt", "I'm completely…
find-dead-code
Find dead code using parallel subagent analysis and optional CLI tools, treating code only referenced from tests as dead. Use when the user asks to "find dead code", "find unused code", "find unused exports", "find unreferenced functions", "clean up dead code", or "what code is unused". Analysis-only — does not modify…
polish-code
Stage, format, lint, test, review, smoke test, and re-run itself until stable. Use when the user asks to "polish code", "refine code", "iterate on code quality", "review loop", "clean up, test, and review loop", or "run the polish loop".
simplify-code
Run a multi-agent review of changed files for scope, reuse, quality, efficiency, clarity, and altitude issues followed by fixes. Use when the user asks to "simplify code", "review changed code", "check for code reuse", "review code quality", "review efficiency", "simplify changes", "clean up code", "refactor changes"…