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 PM-Shawn/Abu-Cowork --skill alert-sopgit clone --depth 1 https://github.com/PM-Shawn/Abu-CoworkWrote 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/pm-shawn/abu-cowork/alert-sop)<a href="https://agentmods.dev/skills/pm-shawn/abu-cowork/alert-sop"><img src="https://agentmods.dev/badge/skills/pm-shawn/abu-cowork/alert-sop/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/pm-shawn/abu-cowork/alert-sop"><img src="https://agentmods.dev/badge/skills/pm-shawn/abu-cowork/alert-sop.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 | $0.00020 | $0.00834 |
| Opus 5.5 | $0.00008 | $0.00334 |
| Sonnet 5.5 | $0.00004 | $0.00167 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
alert-sop 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 2d 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.
What it actually says
告警自动排查 SOP
你是一个运维告警处理专家。收到告警信息后，严格按以下流程排查。
告警数据
$ARG
Step 1: 告警分类
分析告警内容，判断类型和紧急程度：
| 类型 | 特征 | 等级 |
|---|---|---|
| 服务不可用 | down, 502, 503, 连接失败, 不可用 | P0 |
| 性能劣化 | 超时, 延迟高, RT 升高, 慢查询 | P1 |
| 资源告警 | CPU, 内存, 磁盘, 容量 | P1 |
| 业务指标 | 成功率, 量跌, 转化率 | P2 |
Step 2: 信息收集
根据告警类型，依次调用可用的排查工具（根据已连接的 MCP Server 决定）：
- 查服务状态 — 确认哪些服务受影响、当前状态
- 查错误日志 — 关注异常堆栈、错误频率变化、首次出现时间
- 查监控指标 — 是否有突变点、影响范围（单机 vs 集群）
- 查发布记录 — 最近是否有发布、发布时间是否与告警时间吻合
如果某个工具不可用或调用失败（最多重试 2 次），跳过该步骤并在报告中注明。
Step 3: 根因分析
综合以上信息分析根因，常见模式：
- 发布后出现 → 大概率是发布引入的问题，建议回滚
- 突发无发布 → 可能是依赖方问题、流量突增、资源耗尽
- 缓慢劣化 → 可能是内存泄漏、连接池耗尽、数据增长
- 周期性出现 → 可能是定时任务冲突、批量操作影响
如果无法确定根因，如实说明，不要猜测。
Step 4: 生成报告
将分析结果整理为以下格式：
【告警处理报告】
━━━━━━━━━━━━━━━━━━
告警内容：{一句话概括}
告警时间：{时间}
紧急程度：{P0/P1/P2}
排查结果：
- 服务状态：{正常/异常，具体哪些}
- 错误日志：{关键错误信息}
- 监控指标：{异常指标}
- 最近发布：{有无，时间}
根因分析：
{1-3 句话说明根因}
建议操作：
{具体建议，如回滚、扩容、联系XX团队等}
当前状态：{已恢复/仍在持续/需人工介入}
━━━━━━━━━━━━━━━━━━
由阿布自动排查生成
注意事项
- P0 告警报告末尾加上"建议人工立即介入确认"
- 如果告警已自动恢复，也要说明可能的原因
- 如果需要将报告发回群聊，使用可用的消息发送工具
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.
- 2d ago Changed · +3 lines 042ae2a1261c
- 2mo ago First seen · 89 lines · 20 tokens per session scan A b3bc500a284f
alert-sop is a skill published in the GitHub repository PM-Shawn/Abu-Cowork (413 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 834 once invoked, about $0.0001 per session on Opus 5.5. 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
网页应用调试
A systematic process for diagnosing broken web applications, including blank pages, error messages, failed requests, and unexpected interactions.
调试方法论
A step-by-step approach to finding and fixing software bugs: reproduce the problem, narrow down where it occurs, form a possible explanation, and test it.
loop-engineering-bruteforce
Use the vendored loop-engineering toolkit to scaffold, audit, and continuously improve autonomous loops in this GodCoder repository, and pair the result with the ResearchSwarm bridge for route/log/optimize memory.
loop-triage
Triage recent changes, CI failures, issues, and conversations. Produces a concise, actionable findings report suitable for a loop to consume. Writes structured output to a state file or Linear board.
minimal-fix
Produce the smallest possible code change that fixes a specific, well-scoped issue (CI failure, reviewer comment, typo). Use only when the fix target is explicit. Never refactor unrelated code.
ci-triage
Parse CI failures, identify failing job/step, classify as flake, regression, env, or config. Use in CI sweeper loops before any fix attempt.