maintenance SKILL.md skillA

maintenance from jpeetz/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jpeetz/agent-skills/maintenance@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jpeetz/agent-skills
Path
skills/devops-infrastructure/maintenance/SKILL.md
Versions recorded
1
Latest version
v1.0.0, committed Oct 14, 2026
Size
6,157 bytes
Repository stars
14
License
none declared

Use this skill when operating a self-hosted customer web stack (Cal.diy / Typebot / n8n / Postgres / Stripe) that a maintenance agent must keep available, patched, and backed up automatically. JEV-first decisions, sparse LLM generation, health probes, weekly backups, JEV-gated updates, rollback.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Custodian Maintenance Runbook

Operates a client's self-hosted stack — booking engine (Cal.diy), automation
(n8n), chat (Typebot), Postgres, web/TLS, Stripe webhook. **Purpose: availability
+ recoverability + currency, at the lowest possible inference cost.**

## When to Use This Skill

Use this skill when:
- A customer stack must be monitored, backed up, and updated automatically.
- You need a repeatable, guardrailed maintenance loop (health → backup →
  update → rollback) that never breaks a live booking flow.
- Cost matters: the loop should run decisions on a cheap model and only summon
  a generation model for genuine language work.

## COST DISCIPLINE (first rule)
- Use **JEV** (`typesafe/jev-1.13`, endpoint `/api/alpha/decisions`) for EVERY decision
  (gate an update, classify an incident, pick retention).
- Use a cheap **flash model** ONLY for unavoidable language work: writing the human
  incident text, parsing an error JEV can't classify, composing an escalation, reading
  a release note for breaking-change judgment.
- A cycle that completes JEV-only is a WIN. Do not summon a generation model for
  anything a command, grep, or JEV resolves.

## JEV call shape (verified)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jpeetz/agent-skills/maintenance@sha256:3154d10e882b4dbd

The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_kjfrqoc2egxtd5wd.svg)](https://markdownregistry.com/a/art_kjfrqoc2egxtd5wd)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 14, 2026.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-14 ff2cfdc 6,157 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6157 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jpeetz/agent-skills · 14 stars · license none declared · pushed 2026-10-19 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_kjfrqoc2egxtd5wd
GET https://markdownregistry.com/api/v1/resolve?ref=jpeetz/agent-skills/maintenance
GET https://markdownregistry.com/api/v1/blob/3154d10e882b4dbdf4fc27744e70abd102d10a202601f1f167482038b8bdac72

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jpeetz/agent-skills

api-and-interface-design SKILL.md skill
jpeetz/agent-skills · skills/api-backend/api-and-interface-design/SKILL.md · Use this skill when designing APIs, module boundaries, or any public interface. Create stable, well-documented…
git:20261019.fbfaf1a · audit A · 14 stars
api-design-first SKILL.md skill
jpeetz/agent-skills · skills/api-backend/api-design-first/SKILL.md · Design-first API development skill. Generates OpenAPI 3.1 specifications, enforces REST design best practices…
v1.0.0 · audit A · 14 stars
graphql-api-development SKILL.md skill
jpeetz/agent-skills · skills/api-backend/graphql-api-development/SKILL.md · AI-powered GraphQL API design, implementation, and optimization. Covers schema-first design, resolver architecture…
v1.0.0 · audit A · 14 stars
har-api-reverse-engineering SKILL.md skill
jpeetz/agent-skills · skills/api-backend/har-api-reverse-engineering/SKILL.md · Use this skill when an agent needs to call a website's hidden or undocumented API: capture real browser requests into a…
v1.0.0 · audit A · 14 stars
image-to-image-character-generation SKILL.md skill
jpeetz/agent-skills · skills/api-backend/image-to-image-character-generation/SKILL.md · Use this skill when an agent needs to generate consistent character images via kie.ai grok-imagine image-to-image from…
v1.0.0 · audit A · 14 stars
kie-ai-platform SKILL.md skill
jpeetz/agent-skills · skills/api-backend/kie-ai-platform/SKILL.md · Use this skill when an agent needs to integrate with the Kie.ai API for image/video/audio generation, task management…
v1.0.0 · audit A · 14 stars
n8n-api-shape SKILL.md skill
jpeetz/agent-skills · skills/api-backend/n8n-api-shape/SKILL.md · Use this skill when working with the n8n REST API — read, update, or verify workflows on ANY n8n instance…
v1.0.0 · audit A · 14 stars
social-har-api-connectivity SKILL.md skill
jpeetz/agent-skills · skills/api-backend/social-har-api-connectivity/SKILL.md · Use this skill when an agent needs to connect to a social platform's API by prompting the user to pick a platform…
v3.0.0 · audit A · 14 stars
app-discovery-scrutiny SKILL.md skill
jpeetz/agent-skills · skills/business-strategy/app-discovery-scrutiny/SKILL.md · Use this skill when the user wants to evaluate a mobile app idea for commercial viability — whether it's a clone…
git:20260914.5722530 · audit A · 14 stars
enterprise-consulting-methods SKILL.md skill
jpeetz/agent-skills · skills/business-strategy/enterprise-consulting-methods/SKILL.md · Use when you need McKinsey/BCG-grade strategy work — problem decomposition, hypothesis testing, storyline building…
v1.0.0 · audit A · 14 stars
linear-project-management SKILL.md skill
jpeetz/agent-skills · skills/business-strategy/linear-project-management/SKILL.md · Use when driving Linear projects and issues from an agent.
v1.0.0 · audit A · 14 stars
clean-pro-review-gates SKILL.md skill
jpeetz/agent-skills · skills/code-quality/clean-pro-review-gates/SKILL.md · Combined 5-gate review framework that catches AI-generated code failures before shipping — code quality (15 LLM failure…
v1.0.0 · audit A · 14 stars

Every file in jpeetz/agent-skills

Other files named maintenance

maintenance SKILL.md skill
platonai/browser4 · coworker/skills/maintenance/SKILL.md · Orchestrates 30 check scripts across 9 categories (code, tests, docs, SKILLs, deps, infra). Use when asked to run…
git:20260714.a03c08f · audit A · 1,164 stars
maintenance SKILL.md skill
everruns/yolop · .agents/skills/maintenance/SKILL.md · Goal-oriented repository maintenance and release-readiness work for yolop. Use when the user asks for maintenance…
git:20260914.ff8c41f · audit A · 17 stars

Browse by kind, by grade A, or by owner.