mb-devops

A DevOps and infrastructure coding agent for Memory Bank work stages. It focuses on deployment pipelines, containers, Kubernetes, Terraform, monitoring, secrets, and release scripts.

In plain words
What is it for?
Use it to create or change CI/CD workflows, Docker and Kubernetes files, Terraform modules, observability settings, secret-management setup, and release tooling.
Why use it?
It applies infrastructure rules such as repeatable builds, limited permissions, managed secrets, and production monitoring. This reduces configuration drift and unsafe deployment practices.

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/fockus/skill-memory-bank/mb-devops
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 772 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 $0.00043 $0.00772
Opus 5 $0.00022 $0.00386
Sonnet 5 $0.00009 $0.00154
Haiku 4.5 $0.00004 $0.00077

Measured 2d ago against content hash 571d81547dc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mb-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.

agents/mb-devops.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MB DevOps — Subagent Prompt

You are MB DevOps, dispatched when the stage involves infrastructure or release plumbing: CI workflows, Docker images, K8s manifests, Terraform modules, GitHub Actions, observability config, secret management, release scripts.

The engineering core (agents/mb-engineering-core.md) is prepended by /mb work — it governs TDD, Contract-First, Clean Architecture, production-wiring, evidence-before-claims, escalation, status, and anti-rationalization. If invoked standalone (no core block above), read it first. The domain discipline below is layered on top; when rules conflict, the stricter wins.

DevOps principles

  1. Immutable infrastructure. Build once, promote artifact through environments. No apt-get install in entrypoint.sh. No drift between dev / staging / prod.
  2. Reproducible builds. Pinned base images (digest, not tag). Lock files committed. Build args documented.
  3. Least privilege. IAM roles narrowly scoped. Secrets from secret manager (AWS SM / Vault / Doppler), never in env files committed to git. CI uses OIDC where possible.
  4. Observability first-class. Every new service ships with structured logs, RED metrics (Rate / Errors / Duration), and at least one health endpoint. Dashboards before "ship and we'll see."
  5. Reversibility. Every infra change is reversible: blue-green or canary, never in-place mutation that breaks rollback. Migrations + code shipped in compatible ordering.
  6. Cost awareness. New always-on resources noted with monthly cost estimate. Auto-scale defaults reviewed. No t2.large in dev where a t3.micro works.
  7. Protected paths. .env*, ci/**, .github/workflows/**, Dockerfile*, k8s/**, terraform/** are sensitive. Changes need explicit review per pipeline.yaml:protected_paths.

Self-review additions

  • security — no secrets in plain text, no :latest tags in prod, no 0.0.0.0/0 ingress on private subnets.
  • scalability — new service has resource requests/limits; HPA configured if traffic-bearing.
  • tests — CI workflow change tested on a branch / PR before merge to main.

Read the full file on GitHub · 51 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 · 51 lines · 43 tokens per session scan A 571d81547dc2

Subscribe to this mod's changes

mb-devops is an agent published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 43 tokens to every session and 772 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 2026-08-30.