- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add docker/skills --skill docker-agent-run -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add docker/skills --skill docker-agent-run -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add docker/skills --skill docker-agent-run -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add docker/skills --skill docker-agent-run -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/docker/skills/tree/HEAD/skills/docker-agent-runDe l'éditeur
This skill owns the operational side of Docker Agent: invoking docker agent run against a local config, an alias, or a registry reference; choosing how
much autonomy the agent gets over tool calls; isolating it in a sandbox VM;
and diagnosing why a run fails. It assumes the agent.yaml already exists —
see Related skills for authoring it.
Activate this skill when:
--exec).--safety, --yolo, or approval behavior for tool calls.--sandbox, or hit a sandbox network-policy error.docker agent alias), a scoped git worktree (--worktree), or is debugging credentials/model availability (docker agent doctor).Do not use this skill when:
sbx run/create/stop/rm rather than
docker agent run --sandbox — use docker-sandboxes-lifecycle.sbx policy or sbx secret configuration — use
docker-sandboxes-network-credentials. Establish which CLI is in use
before recommending commands when the request only says "my sandbox".agent.yaml itself (models, toolsets, sub_agents) — use docker-agent-config.serve), sharing it via a registry (share), or evaluating it (evaluation sessions, --baseline regression gates) — use docker-agent-deploy.docker agent run supports four --safety modes; choose the least
permissive one that still lets the task finish:
strict — ask for approval before every tool call.balanced — auto-approve calls classified as safe, ask for the rest.restricted — auto-approve safe calls, deny the rest outright. Use
for unattended/CI runs where no human can answer a prompt.autonomous — approve everything automatically. Equivalent to --yolo.autonomous/--yolo. Use restricted for unattended runs so an
unexpected tool call fails closed instead of running unreviewed; reserve
autonomous/--yolo for a sandboxed or fully trusted interactive session.
# CI-safe: unreviewed tool calls are denied, not silently approved.
docker agent run --exec --safety restricted ./agent.yaml "Triage the failing test"
--safety/--yolo on docker agent run
still overrides the alias:
docker agent alias add safe-coder myorg/coder --safety balanced
--sandbox runs the agent inside an isolated microVM managed by the sbx
CLI (a separate prerequisite — install and configure it first). All shell,
filesystem, and process activity started by built-in toolsets happens
inside the VM; only the working directory (and, unless --no-kit, a
staged "kit" of skills/prompt files) is mounted in. Exception: a local
stdio MCP server declared on the agent runs as a host process outside
the sandbox VM — treat any such MCP server as a trusted host integration,
not a sandboxed one.
docker agent run --sandbox ./agent.yaml
models.dev, and hosts the toolset resolver can infer are open. A custom
MCP server or third-party API often needs an explicit allowlist entry —
add it permanently rather than re-discovering it every run:
docker agent sandbox allow api.example.com
docker agent sandbox list
docker agent sandbox deny api.example.com
runtime: {sandbox: true} into the agent's own agent.yaml
over remembering --sandbox on every invocation of that agent; an
explicit --sandbox=false on the CLI still overrides the config default
for a single debug run.docker agent alias add code myorg/notion-expert
docker agent run code
docker agent run discovers
docker-agent.yaml, then docker-agent.yml, then docker-agent.hcl in
the current directory (first match wins). Only if none exists does it
resolve the default alias, falling back to the built-in default agent.
The agent.yaml examples in these skills pass a filename explicitly;
agent.yaml is not an auto-discovery name.default alias. To select it even when a project config exists, pass
default explicitly:
docker agent alias add default ./my-agent.yaml
docker agent run default
docker agent run <alias> always override the alias's own
stored options (e.g. docker agent run yolo-coder --yolo=false).--worktree (-w) to isolate an agent's file edits from your current
checkout — it runs the agent inside a fresh git worktree. For an
interactive session, a clean worktree (no uncommitted changes,
untracked files, or new commits) is removed automatically when the
session ends; one with work prompts you to keep or remove. A headless
run (--exec) never auto-cleans its worktree, regardless of state — it is
left in place for inspection:
docker agent run ./agent.yaml --worktree=auth-refactor --worktree-base origin/main
--worktree cannot be combined with --remote or --sandbox. To resume a
worktree run, pass --session -1 (or the session id) — do not re-pass
--worktree, which fails because the worktree already exists.dmr/) the model
hasn't been pulled. Run docker agent doctor ./agent.yaml first — it
reports the resolved model/provider and whether credentials were found —
before touching the YAML. If credentials are missing, export the provider's
API key; if a DMR model is missing, run docker model pull <model>. Rerun
doctor before retrying the task.type: shell or type: todo in
agent.yaml), not a model failure — hand this back to docker-agent-config.403 Blocked by network policy error inside a sandbox run means the
destination isn't allowlisted; use docker agent sandbox allow <host>.sbx lifecycle commands, use docker-sandboxes-lifecycle.sbx policy and sbx secret, use docker-sandboxes-network-credentials.agent.yaml (models, toolsets, sub_agents), use docker-agent-config.docker-agent-deploy.references/safety-and-sandbox.md — full safety-mode/flag interaction table and sandbox trust-boundary details.references/sources.md — provenance of every rule in this skill.checks/verification.md — Verification runbook for a docker agent run invocation.Use this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the `--sandbox` isolation flag, setting up aliases, or troubleshooting a run (missing credent
---name: docker-agent-rundescription: Use this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the…---# skills/docker-agent-run/SKILL.mdVue d'ensemble
Use this skill when running a Docker Agent with `docker agent run`, choosing a safety/approval mode, using the `--sandbox` isolation flag, setting up aliases, or troubleshooting a run (missing credentials, worktrees). Even if the user just says they want to "run my agent", "make my agent auto-approve tool calls", "run this agent safely", or "why can't my agent see my API key", this skill applies. Covers `--safety` (strict/balanced/restricted/autonomous), `--yolo`, `--sandbox` and its network allowlist, `--worktree`, `docker agent alias`, and `docker agent doctor`.
FAQ
Téléchargez skills/docker-agent-run/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/docker/skills.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.