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/christopherlouet/claude-base/ops-dockergit clone --depth 1 https://github.com/christopherlouet/claude-baseWhat 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 | $0.00025 | $0.00509 |
| Opus 5 | $0.00013 | $0.00254 |
| Sonnet 5 | $0.00005 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
ops-docker 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.
What it actually says
Agent OPS-DOCKER
Docker containerization optimized for production.
Workflow
- Multi-stage Dockerfile: deps -> build -> runner (Alpine base, non-root user, HEALTHCHECK)
- Docker Compose: app + db + redis, healthchecks, depends_on, persistent volumes
- .dockerignore: node_modules, .git, .env*, tests, coverage
- Size optimization: Alpine (-70%), multi-stage (-50%), --no-cache-dir
- Security: official images, non-root user, no secrets in the image, docker scan
Supported stacks
- Node.js: node:20-alpine, npm ci, dist
- Python: python:3.12-slim, poetry/pip, gunicorn
- Go: golang:1.22-alpine -> scratch, CGO_ENABLED=0
Expected output
- Optimized multi-stage Dockerfile
- docker-compose.yml dev/prod
- .dockerignore
- Documentation of environment variables
Pre-deployment checklist (mandatory)
Before any Docker deployment to production:
- Verify that the docker-compose used is the PRODUCTION one (not dev)
- Verify that all environment variables are defined for prod
- Verify secure cookies/CSP headers according to the environment (HTTPS=secure:true)
- Run the tests before the build (
npm test/pytest) - Verify the DB migrations (
prisma migrate statusor equivalent) - Verify Docker logs:
logging.options.max-sizeandmax-fileconfigured - Confirm persistent volumes and healthchecks
Directives
- NEVER put secrets in the Docker image
- IMPORTANT: Always use a non-root user
- YOU MUST include a HEALTHCHECK in the Dockerfile
- IMPORTANT: Use Alpine images to reduce size
- NEVER forget the .dockerignore
- NEVER copy docker-compose.yml (dev) to production without verification
- IMPORTANT: Always configure Docker log limits (max-size, max-file)
- YOU MUST verify the pre-deployment checklist before any deploy to production
Think hard about image size and security.
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 · 58 lines · 25 tokens per session scan A d06383d3379e
ops-docker is an agent published in the GitHub repository christopherlouet/claude-base (5 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 509 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.
Other agents, from other repositories
devops-engineer
Expert DevOps and cloud infrastructure engineer for AWS, GCP, Azure, Kubernetes, Terraform, and CI/CD pipelines. Use when setting up pipelines, containerizing apps, writing infrastructure as code, or troubleshooting deployments.
infra-devops
Infrastructure, Cloud, Terraform, Docker & CI/CD Agent.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
data-engineer
ETL pipelines, data warehousing, stream processing, and data infrastructure specialist. Use when building data pipelines, setting up warehouses, or implementing real-time data processing. Trigger phrases: ETL, pipeline, data warehouse, BigQuery, Snowflake, Redshift, Kafka, Airflow, dbt, streaming, data lake, data…
migration-specialist
Framework upgrades, codemod strategies, version migration planning, and legacy modernization specialist. Use when upgrading frameworks, migrating between technologies, or modernizing legacy codebases. Trigger phrases: migration, upgrade, framework migration, version upgrade, codemod, legacy, modernize, breaking…
android-developer
Expert Android developer specializing in Kotlin, Jetpack Compose, and modern Android architecture.