write-ops-runbook

write-ops-runbook is a skill for Claude Code from jeffreytse/grimoire-core. It costs 24 tokens per session (967 once invoked), scanned A, original, MIT.

A step-by-step operations guide for on-call engineers or operators to follow during a known problem, often under time pressure. It records the symptoms, impact, checks, and recovery actions.

In plain words
What is it for?
Use it to document alert responses, troubleshooting checks, recovery steps, escalation contacts, and post-incident tasks.
Why use it?
It turns expert knowledge into instructions that another qualified engineer can follow without relying on memory or informal help during an incident.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grimoire-business plugin — 145 skills shipped together

Good fit Use it to document alert responses, troubleshooting checks, recovery steps, escalation contacts, and post-incident tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/write-ops-runbook
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.

Any agent
npx skills add jeffreytse/grimoire-core --skill write-ops-runbook
Clone the repo
git clone --depth 1 https://github.com/jeffreytse/grimoire-core

Made for: Claude Code.

Or install grimoire-business, the plugin that ships this one along with the rest of its 145 skills.

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-ops-runbook

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/write-ops-runbook/github.svg)](https://agentmods.dev/skills/jeffreytse/grimoire-core/write-ops-runbook)
Your own site
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/write-ops-runbook"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/write-ops-runbook/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.

agentmods 80×15 button for write-ops-runbook

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/write-ops-runbook"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/write-ops-runbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 967 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00024 $0.00967
Opus 5 $0.00012 $0.00483
Sonnet 5 $0.00005 $0.00193
Haiku 4.5 $0.00002 $0.00097

Measured 6d ago against content hash 1b8a65681305, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

write-ops-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 6d 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/business/operations/skills/write-ops-runbook/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write Ops Runbook

Create an operational runbook that any qualified engineer can execute correctly under pressure without prior context.

Why This Is Best Practice

Adopted by: Google SRE teams, AWS operations, Cloudflare, PagerDuty — all treat runbooks as living operational documentation Impact: Google SRE reports that documented runbooks reduce mean time to resolution (MTTR) by 40–60% for known failure modes; they also reduce on-call burnout by eliminating repeated tribal-knowledge lookups

Why best: A good runbook transfers expert knowledge into a form that a competent non-expert can execute at 2 AM during an incident. Every step of ambiguity in a runbook multiplies the risk of error under stress.

Steps

  1. Write the header block — Include: Alert name or trigger condition, severity level, service owner, last reviewed date, and link to the service dashboard. Someone opening this runbook needs orientation in under 10 seconds.
  2. State the symptoms — List the exact alert text, error messages, or observable behaviors that bring someone to this runbook. Include screenshot or log snippet if available.
  3. Define the impact — Who is affected? What is degraded? What is the customer-visible symptom? One paragraph, no jargon.
  4. List prerequisites — Tools, permissions, VPN access, environment variables, or credentials required before starting. Do not assume the reader has these set up.
  5. Write numbered steps — Each step is one action. Include the exact command to run (copy-pasteable), the expected output, and what to do if the output differs. Steps must be in order; no "see also" references mid-procedure.
  6. Add decision branches — At key points, add "If X, go to Step 8. If Y, go to Step 12." Avoid branching more than twice in a single runbook; split into separate runbooks instead.
  7. Document escalation — At what point does the responder escalate? To whom? With what information? Include Slack channel, PagerDuty escalation policy, and on-call contact.
  8. Include rollback steps — For any action that modifies state (restart, deploy, config change), provide the exact rollback command. Never leave the operator without an undo.

Read the full file on GitHub · 56 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. 6d ago First seen · 56 lines · 24 tokens per session scan A 1b8a65681305

Subscribe to this mod's changes

write-ops-runbook is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 21d ago), licensed MIT. It adds 24 tokens to every session and 967 once invoked, about $0.0001 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.