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.
git clone --depth 1 https://github.com/TestAny-io/testany-agent-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/commands/testany-io/testany-agent-skills/runbook-writer)<a href="https://agentmods.dev/commands/testany-io/testany-agent-skills/runbook-writer"><img src="https://agentmods.dev/badge/commands/testany-io/testany-agent-skills/runbook-writer/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/commands/testany-io/testany-agent-skills/runbook-writer"><img src="https://agentmods.dev/badge/commands/testany-io/testany-agent-skills/runbook-writer.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 | $0.00041 | $0.00760 |
| Opus 5.5 | $0.00016 | $0.00304 |
| Sonnet 5.5 | $0.00008 | $0.00152 |
| Haiku 4.5 | $0.00004 | $0.00076 |
Grade A, and why
runbook-writer 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 1mo 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
Runbook Writer
执行前读取 工作流执行约定：先取证再提问、按实际工具能力回退，并从本次安装位置定位资源。
启动 Runbook 撰写流程。基于 HLD/LLD 等上游文档，编写生产就绪的运维手册。
先区分 formal_design 与 bounded_change/amendment；有限增量使用既有有效基线及 Owner 批准，只处理受影响范围，不回补全生命周期文档。详见 ../references/document-amendments.md；完整流程只适用于正式新功能/全量准出。
使用方式
提供上游文档路径：
$ARGUMENTS
Runbook 在研发流程中的位置
PRD → API Contract → HLD → Guardrails → LLD → Runbook → 生产部署
Runbook 承接 LLD 的设计，输出可直接用于生产部署、故障处理的运维手册。
Runbook 内容范围
- 部署流程：前置检查、部署步骤、验证命令
- 回滚流程：触发条件、回滚步骤、验证方法
- 监控与告警：关键指标、SLO 阈值、告警配置
- 故障处理：常见故障、排查步骤、解决方案
- 值班手册：职责、联系方式、升级路径
工作流程
- Phase 0: 基线收集 - 读取 PRD/HLD/LLD/API Contract/Guardrails
- Phase 1: 上下文准备 - 提取部署、回滚、监控、故障处理约束
- Phase 2: 派发 Writer Subagent - 独立写作（完整上下文传递）
- Phase 3: Spec Compliance Review - 验证是否覆盖上游要求
- Phase 4: Quality Review - 验证可执行性和完整性
- Phase 5: 输出与验证 - 按模板输出最终 Runbook
必需产出
- Runbook 文档（含部署、回滚、监控、故障处理全流程）
- 验证记录（Spec Compliance + Quality Review 通过）
核心原则
- Context 隔离：Subagent 获得新鲜上下文，避免假设污染
- 双阶段审查：Spec compliance 先行，quality 后续
- 证据驱动：所有约束必须来自上游文档
- 可执行优先：每个步骤必须有验证命令，回滚路径必须可操作
请提供 HLD 路径（必需），以及 LLD、API Contract、Guardrails 路径（可选）。
审查/自检按 ../references/review-assurance.md 绑定对象、覆盖和稳定问题 ID；无独立能力可交未批准草稿，不能将 Critical/Important 的 conditional_pass 认作生产就绪。
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.
- 1mo ago Changed · +6 lines 0343de7d5116
- 1mo ago First seen · 54 lines · 41 tokens per session scan A 851227a5df29
runbook-writer is a command published in the GitHub repository TestAny-io/testany-agent-skills (82 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 760 once invoked, about $0.0002 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 commands, from other repositories
qf-hook
Toggle the Qualflare Stop hook on or off. The Stop hook is a passive nudge that suggests /qf-cover after sessions where source files changed without test updates. Pass 'on' or 'off'.
csharp-exercise-new
A Russian-language C# training assistant for beginner programmers. C# is a programming language used for applications, services, and games.
ts-exercise-new
A command that creates a new TypeScript coding exercise.
rust-exercise-pattern
A command that creates a new Rust exercise about design patterns or SOLID principles, which are common ways to structure software.
csharp-exercise-pattern
A command for creating a new exercise about software design patterns or SOLID principles, which are guidelines for organising object-oriented code.
go-exercise-pattern
A command for starting a new exercise about a software design pattern or SOLID principles, which are guidelines for organising object-oriented code.