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 joao-aires/agent-skills-public --skill runbook-engineeringgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/runbook-engineering)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/runbook-engineering"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/runbook-engineering/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/joao-aires/agent-skills-public/runbook-engineering"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/runbook-engineering.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 | $0.00035 | $0.00650 |
| Opus 5.5 | $0.00014 | $0.00260 |
| Sonnet 5.5 | $0.00007 | $0.00130 |
| Haiku 4.5 | $0.00003 | $0.00065 |
Grade A, and why
runbook-engineering 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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Runbook engineering
Read composition guidance for optional expertise, fallback and scope.
Write for a responder who needs to choose the next action under pressure. Give them a starting condition they can recognize, a check whose result distinguishes plausible causes, and a next decision for each relevant observation. Explain what the check establishes so someone can recognize when the evidence does not fit the documented branch.
Keep operational knowledge close to its action: the exact target, prerequisites, expected effect, stop condition and independent recovery check. Where that knowledge is missing, mark the gap and provide a reachable escalation path. A complete-looking template without established diagnostic knowledge creates false confidence.
Modes and inputs
- Interactive: inspect the service/alert/procedure evidence, then ask for missing owner decisions and known handling.
- Setup/feature: create/update the affected procedures alongside monitors, contracts and release/recovery changes.
- Recurring review: audit changed or high-impact runbooks, broken links, stale signal identities and validation dates; patch evidenced gaps and track unresolved knowledge. Use a quality ratchet so unrelated legacy debt does not block every change.
Discover local publishing/navigation conventions, actual service/target identity, alert query/semantics, verified actions, dependencies and escalation. Preserve existing service-specific knowledge. For a live incident prioritize response; capture lessons for the runbook after stabilization.
Consult references/runbook-guide.md for deeper implementation details when needed.
Author and validate
- State trigger/symptom, impact and applicability. Explain exactly what the signal measures and does not establish.
- Provide numbered first checks with direct scoped queries/links/commands and expected observations. Resolve identity from contracts/configuration/live evidence, not shorthand naming.
- Build diagnostic branches: observation -> hypothesis -> discriminating check -> next decision. Avoid “check logs” without specifying what to look for.
- Give verified corrective actions with target, prerequisites, expected effect, blast radius, reversibility and stop conditions. Label untested procedures as such.
- Define independent post-action verification and restoration of temporary controls. Pod readiness/alert recovery alone is not customer recovery.
- State reachable owner/escalation routes and the evidence required for handoff; identify when escalation is the correct action.
- Publish through the project's documentation workflow and connect alerts to the exact page. Renames need link migration, not assumptions based on monitor naming.
- Check structure, placeholders, local links/navigation, provider query syntax and published reachability. Exercise representative steps in a suitable environment; record actual verification date/coverage.
What ships with it
1 file 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.
- yesterday Changed · +2 lines 7eb778b1705d
- 2d ago Changed · +2 lines 2a230974bbb2
- 7d ago First seen · 41 lines · 35 tokens per session scan A 263af4424fd9
runbook-engineering is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 35 tokens to every session and 650 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 2026-10-15.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…