runbook-execute

runbook-execute is a command for coding agents from latestaiagents/agent-skills. It costs 12 tokens per session (1,011 once invoked), scanned A, original, MIT.

A command for following an operational runbook, meaning a written procedure for handling tasks such as restarts, scaling, deployments, or recovery.

In plain words
What is it for?
Use it to select and execute procedures in development, staging, or production, with checks before and after each action.
Why use it?
It reduces the risk of skipping safety checks or verification steps during potentially risky system operations.

Command

Part of the devops-sre plugin — 8 skills, 6 commands shipped together

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 commands/latestaiagents/agent-skills/runbook-execute
Clone the repo
git clone --depth 1 https://github.com/latestaiagents/agent-skills

Or install devops-sre, the plugin that ships this one along with the rest of its 8 skills, 6 commands.

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 runbook-execute

README.md
[![agentmods](https://agentmods.dev/badge/commands/latestaiagents/agent-skills/runbook-execute.svg)](https://agentmods.dev/commands/latestaiagents/agent-skills/runbook-execute)
Your own site
<a href="https://agentmods.dev/commands/latestaiagents/agent-skills/runbook-execute"><img src="https://agentmods.dev/badge/commands/latestaiagents/agent-skills/runbook-execute.svg" alt="Measured on agentmods" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,011 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 $0.00012 $0.01011
Opus 5 $0.00006 $0.00505
Sonnet 5 $0.00002 $0.00202
Haiku 4.5 $0.00001 $0.00101

Measured 5d ago against content hash 31934d06688c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

runbook-execute 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.

plugins/devops-sre/commands/runbook-execute.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/runbook-execute

Execute runbook procedures with guided steps, safety checks, and verification at each stage.

What I Need

Tell me:

  • Which runbook to execute (or describe the problem)
  • Target environment (prod/staging/dev)
  • Any context about current state

How It Works

Step 1: Runbook Selection

I'll help identify the right runbook:

Available Runbooks:
├── Service Restart
│   ├── api-service-restart
│   ├── worker-restart
│   └── cache-flush-restart
├── Scaling
│   ├── horizontal-scale-up
│   ├── horizontal-scale-down
│   └── vertical-resize
├── Database
│   ├── connection-pool-reset
│   ├── slow-query-kill
│   └── replica-failover
├── Deployment
│   ├── rollback-deployment
│   ├── canary-promote
│   └── feature-flag-toggle
└── Recovery
    ├── circuit-breaker-reset
    ├── queue-drain
    └── cache-invalidation

Step 2: Pre-Execution Checks

Before any action:

┌─────────────────────────────────────────────────────────────┐
│                    PRE-EXECUTION CHECKLIST                  │
├─────────────────────────────────────────────────────────────┤
│  ✓ Runbook: [name]                                         │
│  ✓ Environment: [prod/staging]                             │
│  ✓ Current on-call: [name]                                 │
│  ✓ Active incidents: [none / INC-XXX]                      │
│  ✓ Recent deployments: [list last 24h]                     │
│  ✓ Change freeze: [not active / ACTIVE - requires approval]│
├─────────────────────────────────────────────────────────────┤
│  ⚠️  Impact Assessment:                                     │
│     - Expected downtime: [X seconds/minutes]               │
│     - Affected services: [list]                            │
│     - User impact: [description]                           │
└─────────────────────────────────────────────────────────────┘

Proceed with execution? [y/N]

Step 3: Guided Execution

Each step runs with verification:

Step 1 of 5: Drain connections
├── Command: kubectl drain node-1 --grace-period=30
├── Expected: Node marked as unschedulable
├── Timeout: 60 seconds
│
├── Executing... ████████████████████ 100%
├── Result: ✓ Success
├── Verification: Node status is "SchedulingDisabled"
│
└── Continue to Step 2? [y/N/abort]

Read the full file on GitHub · 138 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 · 138 lines · 12 tokens per session scan A 31934d06688c

Subscribe to this mod's changes

runbook-execute is a command published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 1,011 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 2026-08-31.