write-runbook

write-runbook is a skill for Claude Code, Codex from cpliakas/claude-code-engineering-leaders. It costs 49 tokens per session (3,075 once invoked), scanned A, original, MIT.

A structured guide for writing an operational runbook, which is a step-by-step reference for handling alerts, diagnosing failures, or performing planned maintenance.

In plain words
What is it for?
Use it for scenarios such as high CPU, intermittent 502 errors, certificate renewal, deployments, scaling changes, or database migrations. Provide an alert, service, or procedure description.
Why use it?
It makes response procedures consistent and easier to follow when someone is investigating a problem or carrying out a risky operational task. It also identifies whether the procedure is for incident response, diagnosis, or maintenance.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cpliakas/claude-code-engineering-leaders/write-runbook
Any agent
npx skills add cpliakas/claude-code-engineering-leaders --skill write-runbook
Clone the repo
git clone --depth 1 https://github.com/cpliakas/claude-code-engineering-leaders

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for write-runbook

README.md
[![agentmods](https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/write-runbook.svg)](https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/write-runbook)
Your own site
<a href="https://agentmods.dev/skills/cpliakas/claude-code-engineering-leaders/write-runbook"><img src="https://agentmods.dev/badge/skills/cpliakas/claude-code-engineering-leaders/write-runbook.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,075 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00049 $0.03075
Opus 5 $0.00024 $0.01537
Sonnet 5 $0.00010 $0.00615
Haiku 4.5 $0.00005 $0.00308

Measured 5d ago against content hash f72d548161b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

write-runbook 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 5d 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.

skills/write-runbook/SKILL.md · 479 lines

How it starts

The opening of the file, as written. The whole thing — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Runbook

Generate a fully structured operational runbook from a scenario description.

Input

$ARGUMENTS = description of the operational scenario — alert name, service name, and/or procedure type (e.g., "high CPU on payment-api", "certificate rotation for api.example.com", "diagnose intermittent 502s from ALB").

Process

1. Handle Missing Input

If $ARGUMENTS is empty or contains no actionable description, prompt the user for the minimum information needed:

  • What operational scenario does this runbook cover? — Provide an alert name, service name, or description of the procedure (e.g., "high CPU on payment-api", "certificate rotation for api.example.com").

Do not proceed until the user has provided a scenario description.

2. Determine Runbook Type

Select the type based on the scenario:

  • Incident response — a known failure mode triggered by an alert or symptom with understood remediation paths
  • Diagnostic — unknown root cause; the goal is symptom-to-cause investigation
  • Maintenance — planned operational task (deployment, certificate rotation, scaling change, database migration)

If the scenario is ambiguous, default to incident response.

3. Generate a Runbook ID

Assign a unique ID using the pattern RUN-[SERVICE-PREFIX]-[NNN] where:

  • SERVICE-PREFIX is a 2–4 letter abbreviation of the primary service (e.g., PAY for payment-api, DB for database, CERT for certificate, GEN for general)
  • NNN is a sequential number starting at 001

4. Produce the Runbook

Use the template for the selected type below. Fill every section with specifics derived from $ARGUMENTS. Do not leave placeholder text that requires the user to fill in — infer reasonable defaults and mark them with [VERIFY] where validation against the real system is required.

If this procedure is normally executed by automation or a script: Ask: What steps does the normal automation perform implicitly that a responder would miss if bypassing it? Incorporate every answer as an explicit numbered step. Common hidden steps: loading environment variables, validating credentials, acquiring locks, checking prerequisites, taking a pre-operation backup. Never write "run the script" — list what the script does so a responder can execute the procedure without it.

Read the full file on GitHub · 479 lines

Changes

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.

  1. 5d ago First seen · 479 lines · 49 tokens per session scan A f72d548161b7

Subscribe to this mod's changes

write-runbook is a skill published in the GitHub repository cpliakas/claude-code-engineering-leaders (4 stars, last pushed 14d ago), licensed MIT. It adds 49 tokens to every session and 3,075 once invoked, about $0.0002 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens