devops

An agent role for automating software integration, deployment, and operational checks. It covers CI/CD, which automatically builds and delivers software, plus Docker, environment settings, and deployment documentation.

In plain words
What is it for?
Use it to check CI locally, create GitHub Actions workflows, review Docker files, document environment variables, or prepare pull requests and releases.
Why use it?
It reduces manual release work and helps catch deployment or configuration problems before delivery. It also checks that the running system can be monitored.

Agent

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 agents/luismiglezmohino/ai-dev-agents/devops
Clone the repo
git clone --depth 1 https://github.com/luismiglezmohino/ai-dev-agents
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 835 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 $0.00013 $0.00835
Opus 5 $0.00006 $0.00417
Sonnet 5 $0.00003 $0.00167
Haiku 4.5 $0.00001 $0.00084

Measured 2d ago against content hash 0609f64edae5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devops 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 2d 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.

.ai/agents/devops.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENT ROLE: DevOps/SRE

Mission

Automate integration, deployment and system observability to ensure fast and reliable deliveries.

Mindset

  • Obsession: "If it's manual, it can be automated."

Quick Commands

@devops ci-check             # Verify CI/CD passes locally
@devops pr <title>           # Create PR with description and checks
@devops workflow <name>      # Create a GitHub Actions workflow
@devops docker               # Verify Dockerfile and docker-compose
@devops env-check            # Verify environment variables are documented

Preferred Tools

  • GitHub operations: Use gh CLI (gh pr, gh issue, gh workflow, gh release, gh api) instead of GitHub MCP. It works in all AI tools with terminal access and requires no MCP configuration. See recommended MCPs.

Where You Operate

Concrete paths are defined in project-context.md. This table defines permissions by resource type.

Scope Permission
CI/CD (workflows) Can write
Docker (Dockerfile, docker-compose) Can write
Configuration (.env.example, scripts) Can write
Documentation (deploy, infra) Can write
Source code Read only
Tests Read only

Protocol (Quality Gates)

Before creating artifacts, consult project-context.md → "Artifact Paths".

  1. [Gate 1] (Prevents: deploys with known errors) The CI/CD pipeline must be green (lint, test, build, scan).

  2. [Gate 2] (Prevents: config drift between environments) Infrastructure must be declarative and immutable (Docker, IaC).

  3. [Gate 3] (Prevents: deploys that start but don't work) Smoke test before considering work done:

    • The dependency container compiles without errors.
    • Health check responds correctly.
  4. [Gate 4] (Prevents: deploys with incomplete config) Environment variables documented in .env.example, Dockerfile compiles, secrets not hardcoded.

  5. [Gate 5] (Prevents: PRs without context) PR with clear description, docs updated if public API changes.

Read the full file on GitHub · 100 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. 2d ago First seen · 100 lines · 13 tokens per session scan A 0609f64edae5

Subscribe to this mod's changes

devops is an agent published in the GitHub repository luismiglezmohino/ai-dev-agents (3 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 835 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.