sk8 🛹

// the idea

delegate, don't context-switch

sk8 runs claude headless on a remote box and returns the final answer. It's deliberately tiny: synchronous and blocking — no queue, no streaming, no status polling. Fire a task, get the result.

🛰️

One tool: run_task

The remote agent runs your prompt in its cwd and hands back the final text answer. That's the whole API surface.

🧬

Profiles baked in

Customize each agent per profile — extra Python packages, bundled Claude Code skills, and a tool / MCP / system-prompt spec compiled into the image at build time.

⚙️

Powered by the Agent SDK

server_sdk.py drives the agent loop through the Claude Agent SDK — a typed async message stream with structured permission control.

📦

Files in & out (optional)

GCS-backed signed URLs move inputs and artifacts around run_task without bloating the prompt or hitting the 32 MB request cap.

// 60 seconds

quickstart

Install the CLI, provision an agent on Cloud Run, and wire it into Claude Code.

install the sk8 CLI

# install the `sk8` command from this repo (uv / pipx / pip all work)
uv tool install .

# build the agent image (first time) + provision on Cloud Run
sk8 create iris --build

# custom deps / skills / tools via a profile
sk8 create iris --profile ./profiles/data-analyst --build

connect it to Claude Code & verify

# `sk8 create` prints the exact `claude mcp add ...` line — run it, then:
claude mcp list      # sk8 should show as connected

Then, in a Claude Code session on your laptop:

delegate a task

Use the sk8 run_task tool with prompt:
"list the files in the current directory and summarize them"

// the lifecycle

the sk8 CLI

Scriptable for humans and agents alike — it emits JSON so a running agent can spawn and register its own sub-agents.

sk8 <cmd>

sk8 create iris --build     # build image (first time) + provision
sk8 create iris             # subsequent agents reuse the image
sk8 create iris --json      # {url, token, mcp_add_command} for agents
sk8 create iris --dry-run   # preview the gcloud commands offline
sk8 list                    # list deployed agents in the region
sk8 delete iris --yes       # tear down service + token secret
sk8 suggest 5              # propose adjective-noun names

// under the hood

architecture

The GCP services (Cloud Build, Artifact Registry, Secret Manager, IAM, Cloud Run) and the agent lifecycle — image build → token mint → a run_task call triggering Cloud Run.

// fine print

limitations

⏳ Synchronous only

run_task blocks until the agent finishes (up to a 600s timeout). No streaming, no progress, no status to poll.

🚦 One task at a time

No queue or concurrency management — fire tasks serially.

🧠 Stateless across calls

Each call is a fresh headless claude with no memory of prior tasks. Put all context in the prompt.

⚠ Arbitrary code execution. claude can do anything the host user can. Treat reaching this endpoint as equivalent to a shell on the box — secure it accordingly.