deploy-pipeline-runbook

deploy-pipeline-runbook is a skill for Claude Code from yeaight7/agent-powerups. It costs 41 tokens per session (764 once invoked), scanned A, original, Apache-2.0.

A step-by-step guide for releasing changes across multiple systems or service providers. It includes checks, human approval before changes, and a plan for undoing risky steps.

In plain words
What is it for?
Use it to plan releases involving services such as billing, databases, applications, or notifications, especially when the order of changes matters.
Why use it?
It reduces the chance that a failed deployment leaves connected systems in an inconsistent or damaged state.

Skill for Claude Code

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

Part of the connected-apps plugin — 1 skill shipped together

Good fit Use it to plan releases involving services such as billing, databases, applications, or notifications, especially when the order of changes matters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yeaight7/agent-powerups/deploy-pipeline-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 yeaight7/agent-powerups --skill deploy-pipeline-runbook
Clone the repo
git clone --depth 1 https://github.com/yeaight7/agent-powerups

Made for: Claude Code.

Or install connected-apps, the plugin that ships this one along with the rest of its 1 skill.

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 deploy-pipeline-runbook

README.md
[![agentmods](https://agentmods.dev/badge/skills/yeaight7/agent-powerups/deploy-pipeline-runbook/github.svg)](https://agentmods.dev/skills/yeaight7/agent-powerups/deploy-pipeline-runbook)
Your own site
<a href="https://agentmods.dev/skills/yeaight7/agent-powerups/deploy-pipeline-runbook"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/deploy-pipeline-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 deploy-pipeline-runbook

Your own site · 80×15
<a href="https://agentmods.dev/skills/yeaight7/agent-powerups/deploy-pipeline-runbook"><img src="https://agentmods.dev/badge/skills/yeaight7/agent-powerups/deploy-pipeline-runbook.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 764 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 $0.00041 $0.00764
Opus 5 $0.00020 $0.00382
Sonnet 5 $0.00008 $0.00153
Haiku 4.5 $0.00004 $0.00076

Measured 9d ago against content hash e984ffb49385, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

deploy-pipeline-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 9d 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/connected-apps/skills/deploy-pipeline-runbook/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deploy Pipeline Runbook

This is a trust-sensitive runbook for multi-system deployments. Every write or promotion action requires explicit human approval.

When to Use

  • A release spans multiple systems or vendors (billing, database, app, notifications).
  • Order of operations matters and rollback must be planned before execution starts.
  • A failed step in one system could corrupt state in a downstream system.

Core Rules

  • Inspect current state before each external step.
  • Dry-run whenever the target system supports it.
  • Show side effects before asking for approval — never surprise.
  • Require explicit approval before every write, promotion, or announcement.
  • Define the rollback path before the first irreversible step.

Runbook Structure

1. Preparation

  • List every system touched.
  • State the exact intended change per system (e.g., "bump subscription plan from X to Y in billing API").
  • Confirm credentials, access paths, and required permissions.
  • Identify which steps are reversible and which are not.

2. Sequence the rollout

  1. Config or billing prerequisites.
  2. Schema migrations or data backfills.
  3. Application deploy or feature promotion.
  4. Smoke checks and health validation.
  5. Stakeholder notifications.

3. Approval checkpoint (required before every write)

Use this exact format:

NEXT ACTION: [exact command or API call]
SYSTEM: [target system / environment]
SIDE EFFECTS: [what changes, what is created, what is sent]
IRREVERSIBLE: yes/no — [why]
ROLLBACK: [exact steps to undo this if it fails]

Approve? (yes to proceed)

4. Execute one step at a time

  • Run the approved action.
  • Verify the outcome before moving to the next step.
  • Stop immediately on any unexpected state or error.

5. Closeout

COMPLETED: [timestamp]
CHANGES MADE: [summary of what changed per system]
FOLLOW-UP CHECKS: [monitoring, alerts, or manual verifications needed]
ROLLBACK STATUS: available / partially available / consumed

Rollback Plan Template

Read the full file on GitHub · 97 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. 9d ago First seen · 97 lines · 41 tokens per session scan A e984ffb49385

Subscribe to this mod's changes

deploy-pipeline-runbook is a skill published in the GitHub repository yeaight7/agent-powerups (6 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 764 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.