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 skills add CUHK-AIM-Group/NeuroClaw --skill docker-env-managergit clone --depth 1 https://github.com/CUHK-AIM-Group/NeuroClawWrote 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/skills/cuhk-aim-group/neuroclaw/docker-env-manager)<a href="https://agentmods.dev/skills/cuhk-aim-group/neuroclaw/docker-env-manager"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/docker-env-manager/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/skills/cuhk-aim-group/neuroclaw/docker-env-manager"><img src="https://agentmods.dev/badge/skills/cuhk-aim-group/neuroclaw/docker-env-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 27 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 345 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 44 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 45 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 200 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 291 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- low Tool Misuse · line 50 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00217 | $0.03547 |
| Opus 5 | $0.00109 | $0.01774 |
| Sonnet 5 | $0.00043 | $0.00709 |
| Haiku 4.5 | $0.00022 | $0.00355 |
Grade A, and why
docker-env-manager scanned grade A 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 10d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
version = subprocess.check_output(["docker", "--version"]).decode().strip() How it starts
The opening of the file, as written. The whole thing — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Docker Environment Manager (Tool Layer)
Overview
Docker is the backbone for reproducible, containerized, GPU-accelerated environments in NeuroClaw — especially for deep-learning and neuroimaging skills (MARS-WMH nnU-Net, future nnU-Net models, containerized FreeSurfer, etc.) that require exact runtime isolation, NVIDIA GPU passthrough, and large pre-built images.
This skill acts as the interface-layer orchestrator for all common Docker operations, preventing permission issues, GPU misconfiguration, port conflicts, and storage bloat while enforcing best practices (named containers, volume mounts, --gpus all, docker-compose for multi-service stacks, dry-run previews, and safe pruning).
Strict workflow (never skipped):
- Parse user intent from the request or context (pull / run / build / compose / prune / list / cleanup).
- Detect current Docker setup (
docker --version,docker info, NVIDIA Container Toolkit vianvidia-smithroughclaw-shell, available disk space, GPU status). - Propose a safe, best-practice plan:
- Always prefer named containers/volumes over anonymous ones
- Suggest
--gpus all+ volume mounts for NeuroClaw GPU skills - Recommend
docker-compose.ymlfor reproducible multi-container stacks - Use
--dry-runequivalents and plan preview by default - Warn about large image pulls (several GB), permission issues (
chmod -R 777on data dirs), and GPU driver mismatches - Route all actual
docker run/pull/buildcommands throughclaw-shell
- Show numbered plan + exact commands + estimated time/size + risks.
- Wait for explicit user confirmation (“YES”, “execute”, “proceed”).
- On approval: delegate execution safely to
claw-shell(with logging), capture output, report success/failure, and suggest next steps.
Core safety & best-practice rules
- Never run destructive commands (
docker system prune -a,docker rm -f) without double confirmation - All shell-level Docker commands must go through
claw-shell(centralized logging + safety gate) - Prefer
docker composeover legacydocker-compose - Integrate with
dependency-plannerfor installing Docker + NVIDIA Container Toolkit - Log all actions to
./logs/docker_YYYYMMDD_HHMMSS.log
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.
- 10d ago First seen · 370 lines · 217 tokens per session scan A 8c3a49d05bd1
docker-env-manager is a skill published in the GitHub repository CUHK-AIM-Group/NeuroClaw (84 stars, last pushed 3d ago), licensed MIT. It adds 217 tokens to every session and 3,547 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
compute-env-setup
Set up a reproducible Feynman compute environment for research jobs. Use when a task needs Python/R packages, GPU libraries, containers, Modal, SSH, caches, or managed model runtime setup.
securing-kubernetes-on-cloud
This skill covers hardening managed Kubernetes clusters on EKS, AKS, and GKE by implementing Pod Security Standards, network policies, workload identity, RBAC scoping, image admission controls, and runtime security monitoring. It addresses cloud-specific security features including IRSA for EKS, Workload Identity for…
detecting-privilege-escalation-in-kubernetes-pods
Detect and prevent privilege escalation in Kubernetes pods by monitoring security contexts, capabilities, and syscall patterns with Falco and OPA policies.
implementing-rbac-hardening-for-kubernetes
Harden Kubernetes Role-Based Access Control by implementing least-privilege policies, auditing role bindings, eliminating cluster-admin sprawl, and integrating external identity providers.
docker-socket-mount
Docker / containerd socket mounted into a container → host RCE. Common in CI runners, GitOps controllers (ArgoCD, Flux), and 'Docker-in-Docker' setups. Single-command escape via docker run --rm --privileged -v /:/host alpine chroot /host.