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 skills/atomicbot-ai/atomic-agent/dockernpx skills add AtomicBot-ai/atomic-agent --skill dockergit clone --depth 1 https://github.com/AtomicBot-ai/atomic-agentWhat 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 | $0.00044 | $0.02131 |
| Opus 5 | $0.00022 | $0.01066 |
| Sonnet 5 | $0.00009 | $0.00426 |
| Haiku 4.5 | $0.00004 | $0.00213 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docker
Drive local containers with the docker CLI. Reads
(ps, images, logs, inspect) are safe to run directly; writes
(run, build, stop, rm, rmi, prune, compose down) mutate state and
surface the runtime approval gate — confirm intent with the user first.
Setup health check (run first, every session)
Verify with one solo step:
[{ "tool": "os.shell.run", "args": { "cmd": "docker", "args": ["version", "--format", "{{.Server.Version}}"] } }]
Outcome map:
exit 0+ version → daemon reachable, proceed.command not found: docker→ enter Setup playbook → "docker missing".Cannot connect to the Docker daemon→ enter Setup playbook → "daemon not running".
Setup playbook (when prerequisites are missing)
OFFER help; do not dump docs on the user.
docker missing
Reply (solo reply step):
"Docker is not installed. On macOS, install Docker Desktop (https://docker.com/products/docker-desktop) or run
brew install --cask docker, then launch the app. Tell me when it is running and I will re-check."
Do NOT attempt to install Docker Desktop silently — it needs a GUI launch and privileged setup.
daemon not running
"Docker is installed, but the daemon is not running. Open Docker Desktop (or run
systemctl start dockeron Linux), then tell me when it is up."
Do not try to start the daemon via os.shell.run on macOS — it requires the
Desktop app.
When to use
- "List running containers / images", "show logs for ".
- "Run / build / stop / remove a container", "bring a compose stack up/down".
- Inspecting container config, ports, networks, volumes.
When NOT to use
- Pushing to a registry or production deploys — confirm explicitly; high risk.
- Editing Dockerfiles — use
os.fs.*tools, thendocker build. - Orchestration beyond Compose (Kubernetes) — out of scope; use a
kubectlskill.
Common operations
All examples invoke os.shell.run with cmd: "docker". Reads are listed first.
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 · 198 lines · 44 tokens per session scan A 1b0dd260fece
docker is a skill published in the GitHub repository AtomicBot-ai/atomic-agent (2,425 stars, last pushed 4d ago), licensed MIT. It adds 44 tokens to every session and 2,131 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.
Other skills, from other repositories
harness-init-runner
Initialize a lightweight repo-local Node.js harness (harness/ + .harness/) WITHOUT AIOS dependency. Use ONLY when you need a standalone, portable harness. If AIOS is installed, use aios-long-running-harness instead — it has rex Command hosting, ContextDB integration, and checkpoint recovery.
brand-asset-retrieval
Professional retrieval of corporate brand assets from URLs. Use this skill to automatically identify and extract high-resolution logos, favicons, and primary brand colors from a website to ensure consistency in generated deliverables.
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
pinchtab-stealth-score
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…