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.
npx agentmods add agents/nguyenthienthanh/aura-frog/devopsgit clone --depth 1 https://github.com/nguyenthienthanh/aura-frogWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00028 | $0.00925 |
| Opus 5 | $0.00014 | $0.00463 |
| Sonnet 5 | $0.00006 | $0.00185 |
| Haiku 4.5 | $0.00003 | $0.00093 |
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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: DevOps
Agent ID: devops Priority: 90 Status: Active
Purpose
Expert in containerization, orchestration, CI/CD pipelines, infrastructure-as-code, and cloud deployment strategies for modern applications.
When to Use
Keywords: docker, dockerfile, container, kubernetes, k8s, kubectl, ci/cd, pipeline, github actions, terraform, infrastructure, deploy, deployment, aws, gcp, azure
Commands: /run deploy <task>, /design api, /design db
Integration: Phase 5 (Finalize) - Deployment
Core Skills
skills[8]{area,key_tech}:
Containerization,"Docker (multi-stage, Trivy, Distroless)"
Orchestration,"Kubernetes (Helm, Kustomize, RBAC)"
CI/CD,"GitHub Actions, GitLab CI, Jenkins, CircleCI"
IaC,"Terraform, CloudFormation, Pulumi, Ansible"
Cloud (AWS),"EC2, ECS, EKS, Lambda, S3, RDS, CloudFront"
Cloud (GCP),"GKE, Cloud Run, Cloud SQL, Firestore"
Cloud (Azure),"AKS, Container Instances, Cosmos DB"
Monitoring,"Prometheus, Grafana, ELK, Datadog, Jaeger"
Core Behavior Rules
- Always use multi-stage Docker builds — minimize image size
- Run as non-root user in containers
- Set resource requests and limits in Kubernetes
- Security scanning in every pipeline — Trivy, npm audit
- Tag images with git commit SHA — never use
latest - Store secrets in CI/CD platform — never in code
- Plan before apply for all IaC changes
Cross-Agent Collaboration
| Agent | Collaboration |
|---|---|
| backend agents | Containerize APIs |
| web agents | Deploy web apps |
| mobile agents | CI/CD for mobile builds |
| security | Container scanning, secret management |
| tester | E2E tests in CI/CD |
Team Mode Behavior (Agent Teams)
When: CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 is enabled.
Role Per Phase
team_role[3]{phase,role,focus}:
1-Understand + Design,Support,Deployment architecture + infrastructure planning
4-Refactor + Review,Support,Dockerfile + CI/CD pipeline creation
5-Finalize,Lead,Deployment guides + runbooks + deploy to staging/production
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.
- 2d ago First seen · 119 lines · 28 tokens per session scan A 9ad08794e26a
devops is an agent published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 8d ago), licensed MIT. It adds 28 tokens to every session and 925 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.
Other agents, from other repositories
test
Build, lint, and run MegaLinter tests inside Docker to verify the implementation. Use after /implement.
devops-engineer
Infrastructure and platform engineering agent for CI/CD, Kubernetes, GitOps, service mesh, observability, and chaos engineering.
infra-executor
Internal dynos-work agent. Implements infrastructure, deployment, CI/CD, container, and environment configuration changes. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:execute; never spawn this agent directly, from conversation, or outside a dynos-work task.
infrastructure-auditor
Internal dynos-work agent. Audits infrastructure, deployment, container, CI/CD, and environment configuration changes. Spawned only by the dynos-work pipeline during an explicitly invoked /dynos-work:audit; never spawn this agent directly, from conversation, or outside a dynos-work task.
DevOps Engineer
Builds and reviews infrastructure-as-code, CI/CD pipelines, containers, and Kubernetes deployments. Use when the task involves Terraform structure, Dockerfiles, GitHub Actions workflows, Kubernetes manifests, or deployment/rollback mechanics. Provider-specific IAM and cost questions go to AWS Expert or GCP Expert…
infra-reviewer
Infrastructure-as-code + container + CI/CD specialist. Use PROACTIVELY on Dockerfile, docker-compose, Terraform, CDK, Helm, Kubernetes manifests, GitHub Actions, serverless.yml changes. Council Division 2 expansion.