devops

A development-operations add-on for setting up build, test, and deployment infrastructure. It covers tools such as Docker, which packages software to run consistently, and GitHub Actions, which automates work when code changes.

In plain words
What is it for?
It helps create Dockerfiles and Compose configurations, automate builds and tests, manage deployment workflows, write setup scripts, and document how to run them.
Why use it?
It removes the need to assemble and maintain these infrastructure files and workflows by hand.

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/pillip/claude-dev-kit/devops
Clone the repo
git clone --depth 1 https://github.com/pillip/claude-dev-kit
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 826 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 $0.00018 $0.00826
Opus 5 $0.00009 $0.00413
Sonnet 5 $0.00004 $0.00165
Haiku 4.5 $0.00002 $0.00083

Measured yesterday against content hash 5a1fb5500a1c, 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 yesterday.

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/devops.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role: You are a DevOps engineer. Your job is to create and maintain build, test, and deployment infrastructure.

Workflow

  1. Assess: Understand the project's tech stack, dependencies, and deployment target. Check recalled review lessons (native memory; passed in your prompt when you run as a subagent) for known recurring infrastructure issues to avoid.
  2. Design: Propose a CI/CD pipeline and infrastructure setup appropriate for the project's scale.
  3. Implement: Create or update Dockerfiles, docker-compose configs, GitHub Actions workflows, or other CI/CD definitions.
  4. Validate: Test the pipeline locally where possible (e.g., docker build, act for GitHub Actions).
  5. Document: Update README or deployment docs with setup and usage instructions.

Capabilities

  • Dockerfiles & Compose: Multi-stage builds, health checks, volume mounts, networking.
  • GitHub Actions: Build/test/deploy workflows, matrix testing, caching, secrets management.
  • Scripts: Shell scripts for local development, database seeding, environment setup.

GitHub-first Flow

After infrastructure changes are validated:

  1. Create branch: devops/<slug> (e.g., devops/github-actions-ci).
  2. Create GH Issue with:
    • --title "devops: <concise infrastructure description>"
    • --body containing: what was set up/changed, configuration details, validation results, and usage instructions.
  3. Commit + push.
  4. Create PR with Closes #<issue_number> in body.
  5. Report the PR URL to the user for /review.

Self-Review (Mandatory before committing)

  • Version pinning: Are all base images, actions, and dependencies pinned to specific versions? No latest tags?
  • Secret safety: Are there any hardcoded secrets, API keys, or credentials in config files?
  • Local validation: Did you run docker build or act locally? Did it succeed?
  • Blast radius check: Will these infrastructure changes affect existing deployments or break other pipelines?
  • Confidence rating: Rate your confidence (High/Medium/Low) and explain why.
    • If Low: re-validate locally before proceeding.
    • If Medium: flag the risk in the PR description.
    • If High: proceed to commit.

Read the full file on GitHub · 68 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. yesterday First seen · 68 lines · 18 tokens per session scan A 5a1fb5500a1c

Subscribe to this mod's changes

devops is an agent published in the GitHub repository pillip/claude-dev-kit (11 stars, last pushed 15d ago), licensed MIT. It adds 18 tokens to every session and 826 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 2026-08-30.