devops-skills AGENTS.md

devops-skills AGENTS.md is an instructions file for Codex, OpenCode from arjunprabhulal/devops-skills. It costs 2,168 tokens per session, scanned A, original, MIT.

Repository instructions for maintaining a collection of DevOps agent skills. Each skill is an on-demand instruction set stored in its own SKILL.md file.

In plain words
What is it for?
It is for creating or reviewing skills in the repository, including their frontmatter, introductory principle, numbered sections, completion checks, and final report.
Why use it?
It gives contributors clear rules for skill structure, descriptions, cross-references, implementation sections, and reporting before changes are committed.

Instructions file for CodexOpenCode

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 instructions/arjunprabhulal/devops-skills/agents-md
Clone the repo
git clone --depth 1 https://github.com/arjunprabhulal/devops-skills

Made for: Codex, OpenCode.

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 devops-skills AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/arjunprabhulal/devops-skills/agents-md.svg)](https://agentmods.dev/instructions/arjunprabhulal/devops-skills/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/arjunprabhulal/devops-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/arjunprabhulal/devops-skills/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,168 This file is loaded in full into every session.
When invoked 2,168 The same file — it is already loaded in full.
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 $0.02168 $0.02168
Opus 5 $0.01084 $0.01084
Sonnet 5 $0.00434 $0.00434
Haiku 4.5 $0.00217 $0.00217

Measured 3d ago against content hash 82ce4576d186, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops-skills AGENTS.md 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 3d 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.

AGENTS.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Guidance for AI agents (and humans) working in this repository: the required shape of a skill, the workflow for changing one, and the reasoning behind both. README.md describes what the collection contains and how to install it.

What this repo is

A collection of 88 DevOps Agent Skills across 15 categories. Each skill is a single SKILL.md under skills/<category>/<skill-name>/, loaded on demand when a matching task appears.

The shape of every skill

  1. Frontmatter — exactly three keys: name (must equal the folder name), description (one paragraph with concrete "Use this whenever…" triggers and "For X use sibling" cross-references), and license: MIT.
  2. Intro — one or two paragraphs framing the core principle, ending in a single bold principle line.
  3. 5–6 numbered ## N. Imperative heading sections — each explains the why, may carry at most one or two code blocks or tables total, and ends with a concrete Done when: line.
  4. ## Report — closes by stating the key decisions and, explicitly, the honest remaining gap.

Rules

  • One responsibility per skill. Cross-reference siblings by name instead of repeating them.
  • Be opinionated and explain why. A rule without a reason is not memorable.
  • Principles over vendors. Name tools to illustrate; never tie a skill to one product.
  • No placeholders. Every skill must be complete and technically correct.

Before committing

Run the validator:

python3 scripts/check-skills.py

It checks frontmatter, name/folder match, description length and triggers, the presence of a Report section and Done-when checkpoints, balanced code fences, eval files, reference links, that .claude-plugin/plugin.json matches the skills on disk, and that the Antigravity .agents/skills/ layout is in sync. When you add a skill, add its path to plugin.json and to the README catalogue.

Two layouts, one source

The canonical skills live under skills/<category>/<skill>/ (the Claude Code plugin layout). Google Antigravity discovers skills from a flat .agents/skills/<skill>/ layout, which is generated from the canonical tree and not committed.agents/ is gitignored. After adding or editing any skill, regenerate it locally:

Read the full file on GitHub · 167 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. 3d ago First seen · 167 lines · 2,168 tokens per session scan A 82ce4576d186

Subscribe to this mod's changes

devops-skills AGENTS.md is an instructions file published in the GitHub repository arjunprabhulal/devops-skills (2 stars, last pushed 9d ago), licensed MIT. It adds 2,168 tokens to every session, about $0.0108 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.