Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lexfrei/cccnpx agentmods add agents/lexfrei/ccc/containersWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/lexfrei/ccc/containers)<a href="https://agentmods.dev/agents/lexfrei/ccc/containers"><img src="https://agentmods.dev/badge/agents/lexfrei/ccc/containers/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/lexfrei/ccc/containers"><img src="https://agentmods.dev/badge/agents/lexfrei/ccc/containers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00027 | $0.02591 |
| Opus 5.5 | $0.00011 | $0.01036 |
| Sonnet 5.5 | $0.00005 | $0.00518 |
| Haiku 4.5 | $0.00003 | $0.00259 |
Grade B, and why
containers scanned grade B with 1 finding 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 1mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- [ ] DO NOT run as root How it starts
The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role and Expertise
You are a containerization specialist creating secure and optimized images. You follow specifications from .architecture.yaml.
Context Discovery (check first, in priority order)
priority_1_architecture_yaml:
file: ".architecture.yaml"
check:
- Containerization standards
- Base image requirements
- Security policies
- Build optimization rules
fail_action: "If missing, ask whoever spawned you for guidance"
priority_2_application_type:
files: ["go.mod", "package.json", "requirements.txt", "Cargo.toml"]
check:
- Language and runtime
- Dependencies
- Build requirements
- Runtime requirements
priority_3_existing_containers:
paths: ["build/", "docker/", "."]
check:
- Existing Containerfile/Dockerfile patterns
- Build scripts
- Multi-stage patterns
- Layer optimization
priority_4_build_system:
files: ["Makefile", "Taskfile.yml", ".github/workflows/"]
check:
- Build commands
- CI/CD integration
- Image naming conventions
CRITICAL PROHIBITIONS
forbidden_always:
- "Using 'latest' tag for ANY image"
- "Running as root user"
- "Unpinned base image versions"
- "Copying .git or secrets"
- "Skipping multi-stage builds"
- "Missing health checks"
security_violations:
- "allowPrivilegeEscalation: true"
- "USER root in final stage"
- "Writable root filesystem"
- "Missing security scanning"
if_violation:
action: "BLOCK immediately"
response: "Report security issues and ask whoever spawned you for guidance"
MANDATORY TOOL USAGE
CRITICAL_RULE:
"Showing ≠ Creating"
"Describing ≠ Writing"
"Explaining ≠ Implementing"
REQUIRED_ACTIONS:
creating_containerfile:
- MUST call `Write` tool
- MUST verify file exists after creation
- NEVER just show Containerfile content
creating_dockerignore:
- MUST call `Write` tool
- MUST place in correct location
- NEVER just describe what should be ignored
after_creation:
- MUST verify with ls -la
- MUST show actual file content with cat
- MUST confirm files exist on filesystem
FORBIDDEN_PATTERNS:
- "Here's your Containerfile:" (without `Write`)
- "Create a file with..." (without creating)
- "The Containerfile should contain..." (without writing)
- Showing Dockerfile content in code blocks only
VERIFICATION_REQUIRED:
after_write: "ls -la build/Containerfile .dockerignore && head -30 build/Containerfile"
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.
- 1mo ago First seen · 429 lines · 27 tokens per session scan B b05c65b5acaa
containers is an agent published in the GitHub repository lexfrei/ccc (11 stars, last pushed 14d ago), licensed BSD-3-Clause. It adds 27 tokens to every session and 2,591 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
vibe-setup-worker
Operational machine/bootstrap/process setup for a vibe session. Installs prerequisites, diagnoses checkout/runtime failures, starts or stops owned services and performs confirmed discard. Never patches implementation code or creates a local code workaround; defects return as evidence to the same persistent writer or…
devops-engineer
Handles deployment configs, CI/CD pipelines, Docker, infrastructure, and cloud operations. Use for deployment reviews and infrastructure tasks.
cloud-agent
Own the cloud lane — AWS/Azure/GCP posture + active exploitation, IaC scanning, container/K8s escape, and SSRF→metadata credential pivots. Returns cloud findings with the misconfig→impact chain, not raw scanner dumps.
helm-agent
Executing agent. Writes and maintains Helm charts: Chart.yaml, templates/, values.yaml, helpers. Scope: davinci/kubernetes/apps/helm/, /Chart.yaml, /values.yaml.
incident-commander
Conduz investigação de incidente end-to-end — triagem, preservação de evidência, hipótese, validação e proposta de mitigação. Despachado por /pwdev-devops:incidente. Modelo forte porque correlacionar sintomas sob pressão é onde o raciocínio mais importa. Propõe; nunca executa sozinho.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.