Agent skill

Openhost Sculptor

by imbue-ai in imbue-ai/sculptor

Deploy, verify, and reset the self-hosted Sculptor app running as an OpenHost app (built from source via openhost.Dockerfile).

MITAuto-check: notesDevOps & Cloud

Install Openhost Sculptor

skills CLI
$ npx skills add imbue-ai/sculptor --skill openhost-sculptor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install imbue-ai/sculptor openhost-sculptor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/imbue-ai/sculptor.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/openhost-sculptor .claude/skills/openhost-sculptor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
openhost-sculptor
GitHub stars
238
Token cost
~2.4k tokens
SKILL.md length
1,121 words
Files
7 (incl. scripts)
Skills in repo
29
Repo updated
First seen
Licence
MIT

At a glance

Deploy, verify, and reset the self-hosted Sculptor app running as an OpenHost app (built from source via openhost.Dockerfile).

  • Works in 3 steps: It's up — oh app status "$APP" prints :… → It's serving — curl the live URL. → Clean boot — oh app logs "$APP" shows…
  • Tasks that involve Containers
  • SKILL.md covers Config, Prereqs, How it runs and Deploy / update, plus 4 more sections
  • Runs Shell scripts from its folder; calls git, python and just; reaches github.com

What it does

Openhost Sculptor is an agent skill from imbue-ai/sculptor. Deploy, verify, and reset the self-hosted Sculptor app running as an OpenHost app (built from source via openhost.Dockerfile). Covers fresh deploys, updating or switching the deployed branch while keeping data, health-checking the live instance, and a full CLI-only reset to a fresh-onboarding instance. Wraps the oh CLI; the app name and repo are hardcoded in the scripts and the only per-machine value (your instance host) lives in .sculptor/.env. The common flows are one-command scripts in this skill's scripts/…

Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts (for example `scripts/deploy.sh`, `scripts/redeploy.sh` and `scripts/reset.sh`).

It sits in DevOps & Cloud, covering Containers. It works with Docker. The repository describes itself as: Build product with grounded, parallel coding agents. The licence is MIT.

When your agent uses it

  • Tasks that involve Containers

Example prompts

  • “/openhost-sculptor”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. It's up — oh app status "$APP" prints : (expect
  2. It's serving — curl the live URL.
  3. Clean boot — oh app logs "$APP" shows Uvicorn running on http://0.0.0.0:5050

What it can do on your machine

Read from SKILL.md and the folder at commit f847102. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • git
    • python
    • just
    • pnpm
    • uvicorn

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Openhost Sculptor loads about 2.4k tokens when it runs. Until then it costs about 136 tokens; SKILL.md has 1,121 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~136
When it runs · the whole SKILL.md, loaded when a task matches
~2.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:9
    (your instance host) lives in .sculptor/.env. The common
  • NoteMentions a .env fileSKILL.md:37
    isn't committed. It lives in `.sculptor/.env` (gitignored via `**/.env`) as
  • NoteMentions a .env fileSKILL.md:39
    `.sculptor/.env` is the caller's job (see Verify below) — the script does no
  • NoteMentions a .env fileSKILL.md:42
    When you need `HOST` and `.sculptor/.env` doesn't have it yet, ask the user for
  • NoteMentions a .env fileSKILL.md:46
    T_HOST=sculptor.<your-zone>" >>.sculptor/.env   # gitignored
  • NoteMentions a .env fileSKILL.md:125
    an argument — load it from `.sculptor/.env` (see Config; add it there first if
  • NoteMentions a .env fileSKILL.md:129
    . .sculptor/.env   # sets OPENHOST_HOST

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from imbue-ai/sculptor at commit f847102, republished under its MIT licence (© imbue-ai). 1,121 words, ~2,448 tokens.

Download SKILL.mdSave it as .claude/skills/openhost-sculptor/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
openhost-sculptor
description
Deploy, verify, and reset the self-hosted Sculptor app running as an OpenHost app (built from source via openhost.Dockerfile). Covers fresh deploys, updating or switching the deployed branch while keeping data, health-checking the live instance, and a full CLI-only reset to a fresh-onboarding instance. Wraps the `oh` CLI; the app name and repo are hardcoded in the scripts and the only per-machine value (your instance host) lives in .sculptor/.env. The common flows are one-command scripts in this skill's scripts/ folder.
user-invocable
true

OpenHost Sculptor: deploy / verify / reset

Operate the self-hosted Sculptor app on an OpenHost compute space. Sculptor is deployed there as an OpenHost app built from source (not a released binary): OpenHost clones the repo at a branch, builds openhost.Dockerfile, runs the container under rootless podman, and reverse-proxies HTTPS to it behind OpenHost's owner login.

Everything here drives the oh CLI (OpenHost's app-management CLI) — no SSH into the host for any normal flow. The four common flows are wrapped in scripts under scripts/; the raw oh commands they run are shown alongside so you know what each does.

Config

This skill is Sculptor-specific, so the values are baked into the scripts — no config file to set up:

  • APP — sculptor, hardcoded in each script.
  • REPO — https://github.com/imbue-ai/sculptor, hardcoded in each script.
  • BRANCH — the repo's current git branch (git rev-parse --abbrev-ref HEAD).
  • HOST — the public URL host that verify.sh curls (e.g. sculptor.<your-zone>). This is the only per-machine value — it embeds a personal subdomain, so it isn't committed. It lives in .sculptor/.env (gitignored via **/.env) as OPENHOST_HOST. verify.sh takes it as an argument; getting it from .sculptor/.env is the caller's job (see Verify below) — the script does no file I/O or prompting.

When you need HOST and .sculptor/.env doesn't have it yet, ask the user for their instance host and save it so future runs don't have to ask:

bash
echo "OPENHOST_HOST=sculptor.<your-zone>" >>.sculptor/.env   # gitignored

To run ad-hoc oh commands in a shell, just use those values directly, e.g.:

bash
oh app status sculptor   # see "Gotchas": older instances need the app_id, not the name
oh app deploy "https://github.com/imbue-ai/sculptor@$(git rev-parse --abbrev-ref HEAD)" \
  --name sculptor --wait

Prereqs

  • oh CLI installed and authenticated on this machine.
    • Install (it's not on PyPI — installs from the private openhost repo):
      bash
      uv tool install "oh @ git+https://github.com/imbue-ai/openhost.git#subdirectory=compute_space_cli"
      uv drops the binary at ~/.local/bin/oh; add that to PATH if needed.
    • Authenticate once with oh login (prompts for the compute-space URL and a token). Sanity check: oh status should print <url> — up (HTTP 200). (Don't rely on oh app list for the check — it crashes against older instances; see "Gotchas".)
  • The branch must be pushed to GitHub first. The deploy builds from $REPO@$BRANCH — OpenHost clones from GitHub, so unpushed local commits are invisible to it. Push (with the user's permission) before deploying.
  • Repo root carries the deploy artifacts: openhost.toml (the app manifest — name, port 5050, health check, persistent app_data) and openhost.Dockerfile (the from-source build recipe). The build context is always the repo root.

How it runs

Knowing how the container is wired explains the deploy and reset behavior below.

  • The Dockerfile CMD runs python -m sculptor.cli.main --no-open-browser /workspace from the built uv venv at /app/.venv — the backend serves the bundled web UI itself. No Electron, no just start. It's effectively just backend with static serving on and /workspace (a minimal pre-initialized git repo) as the initial project.
  • The backend listens on 0.0.0.0:5050 inside the container; OpenHost proxies HTTPS at https://$HOST/ behind its SSO owner login.
  • Persistent state lives under /data/app_data/sculptor (env SCULPTOR_FOLDER) — DB, workspaces, downloaded agent binaries, and config. This dir is an OpenHost backed-up app_data mount, so it survives rebuilds and oh app remove --keep-data. Claude Code OAuth creds persist there too (CLAUDE_CONFIG_DIR=/data/app_data/sculptor/claude).

Deploy / update

Each script deploys the current git branch (BRANCH) and runs oh with --wait (the from-source build takes ~10 min — uv sync, frontend pnpm install / generate-api / build; don't assume it's instant).

Fresh deploy — app name not yet in use
bash
.claude/skills/openhost-sculptor/scripts/deploy.sh
# → oh app deploy "$REPO@$BRANCH" --name "$APP" --wait
Update, or switch branches — keep data

oh app deploy refuses an existing app name ("App name already in use"), so redeploys remove first. redeploy.sh removes with --keep-data (persistent app_data survives), then deploys the same or a different $BRANCH. oh app remove blocks until the app is gone, so the deploy reuses the name cleanly.

bash
.claude/skills/openhost-sculptor/scripts/redeploy.sh
# → oh app remove "$APP" --keep-data
# → oh app deploy "$REPO@$BRANCH" --name "$APP" --wait

Note: oh app reload "$APP" --update only git pulls and rebuilds the same branch already deployed — it does not switch branches. Switching branches always means remove + deploy (i.e. redeploy.sh).

Show full SKILL.md (528 more words)Show less

Verify

After a deploy, confirm all three with one script. It takes your instance host as an argument — load it from .sculptor/.env (see Config; add it there first if missing):

bash
. .sculptor/.env   # sets OPENHOST_HOST
.claude/skills/openhost-sculptor/scripts/verify.sh "$OPENHOST_HOST"

It checks:

  1. It's up — oh app status "$APP" prints <app>: <status> (expect running; building means the deploy is still in progress). To confirm which code is live (branch/SHA), check the deploy's build logs — oh app status reports only the status string. (On an instance older than the CLI this call needs the app_id, not the name — see "Gotchas".)
  2. It's serving — curl the live URL.
    • 302 = healthy. That's the OpenHost SSO login redirect, not an error.
    • 502 / 503 = down (still building, crashed, or failed to bind).
  3. Clean boot — oh app logs "$APP" shows Uvicorn running on http://0.0.0.0:5050 and Application startup complete.

(OpenHost's own readiness probe hits the unauthenticated /api/v1/health, per openhost.toml.)

Reset — fresh-onboarding instance (CLI only, no SSH)

To wipe everything (DB, workspaces, Claude auth, completed-onboarding state) and come back up at first-run onboarding, reset.sh removes the app without --keep-data — which deletes the persistent app_data — then redeploys fresh. It prompts for confirmation first, then rebuilds (~10 min).

bash
.claude/skills/openhost-sculptor/scripts/reset.sh
# → oh app remove "$APP"            # no --keep-data: deletes persistent app_data
# → oh app deploy "$REPO@$BRANCH" --name "$APP" --wait

oh app remove --keep-data (what redeploy.sh uses) preserves app_data, including a completed-onboarding config — so a redeploy drops you straight into the app. Use reset.sh when you specifically want fresh onboarding.

Escape hatch

A few things the oh CLI can't do — exec a command inside the running container, wipe only part of the data, or restart without a rebuild — require host access: oh instance ssh opens a shell on the instance, from which you can drive podman directly against the openhost-$APP container. You shouldn't need this for any flow above; reach for it only for one-off inspection or surgical fixes.

Gotchas

  • An instance older than the oh CLI breaks name-based app commands. The current CLI (and openhost repo HEAD) addresses apps by name and expects GET /api/apps to return a name-keyed dict. Older compute-space servers instead return a list of {app_id, name, status} and key app_status/app_logs on an opaque app_id. Against such an instance:

    • oh app list crashes with AttributeError: 'list' object has no attribute 'items' (it calls .items() on the list).
    • oh app status <name> / oh app logs <name> fail with Error (400): Invalid app_id — they need the app_id, which changes on every remove+redeploy.

    Fetch the current app_id (and a working list) by calling the API directly with the CLI's own saved auth, then pass the id to status/logs:

    bash
    ~/.local/share/uv/tools/oh/bin/python - <<'PY'
    import json
    from compute_space_cli import config
    from compute_space_cli.main import make_api_request
    mc = config.MultiConfig.load()
    inst = mc.instances[mc.default_instance or "default"]
    print(json.dumps(make_api_request(inst.url, inst.token, "GET", "/api/apps").json(), indent=2))
    PY
    # → oh app logs <app_id>

    The durable fix is to update the compute-space instance to current openhost; then the name-based commands (and these scripts) work as written.

  • A returning browser can skip onboarding/Add Workspace. Post-onboarding landing is driven by the browser's sculptor-tabs localStorage, not the server: the root route reopens the last active tab, and only with no saved tabs falls back to /ws/new. After a reset, a browser with stale tabs can land on home or a now-deleted workspace. Fix in the browser: localStorage.clear() in devtools, delete the sculptor-tabs key, or use an incognito window.

© imbue-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (scripts) in .claude/skills/openhost-sculptor of imbue-ai/sculptor.

  • SKILL.md
  • .gitignore
  • openhost.env.example
  • scripts/deploy.sh
  • scripts/redeploy.sh
  • scripts/reset.sh
  • scripts/verify.sh

Open the folder on GitHubat commit f847102

Compare with similar skills

Openhost Sculptor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Openhost Sculptor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Openhost Sculptor this skillimbue-ai/sculptor238—~2.4kAutomated safety check: NotesMIT
Iron Proxy Gateway for NanoClawnanocoai/nanoclaw31k—~4.6kAutomated safety check: NotesMIT
GreptimeDB Dev Docker ImageGreptimeTeam/greptimedb6.7k—~4kAutomated safety check: NotesApache-2.0
Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit2606 repos~1.1kAutomated safety check: NotesCustom licence
LangBot Deployment Guidelangbot-app/LangBot18k—~1.5kAutomated safety check: NotesApache-2.0
Build Openshell Mxc WindowsNVIDIA/OpenShell16k—~4.9kAutomated safety check: PassApache-2.0

Similar skills

  • Installs or refreshes Iron Proxy and its Iron Control web console for NanoClaw, with a local Docker setup, database, credentials and a human approval bridge.

    31k GitHub stars~4.6k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • GreptimeDB Dev Docker Image

    GreptimeTeam/greptimedb

    Packages a locally built GreptimeDB debug binary into a development-only Docker image for local-cluster testing, with an optional push to a dev registry.

    6.7k GitHub stars~4k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Senior DevOps Toolkit

    maslennikov-ig/claude-code-orchestrator-kit

    Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…

    260 GitHub starsUsed in 6 repos~1.1k tokens
    DevOps & CloudAuto-check: notes
  • LangBot Deployment Guide

    langbot-app/LangBot

    Deploys and configures a LangBot instance with Docker Compose or Kubernetes, covering config.yaml, the Box sandbox runtime, the plugin runtime and the global API key.

    18k GitHub stars~1.5k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Official

    Maintain and validate OpenShell's build-only Windows MSVC lane for x64 and ARM64.

    16k GitHub stars~4.9k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • Megatron-LM Base Image Bump

    NVIDIA/Megatron-LM

    Official

    Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up.

    18k GitHub stars~2.8k tokensUpdated today
    DevOps & CloudAuto-check passed

More from imbue-ai/sculptor

All 29 skills in this repo
  • Auto QA Iphone

    imbue-ai/sculptor

    QA the Sculptor mobile web UI on a real iOS Simulator, driven headlessly from a Mac.

    238 GitHub stars~3.1k tokensUpdated 2 days ago
    Auto-check passed
  • Measure React Renders

    imbue-ai/sculptor

    Compare React component render counts between origin/main and the current branch during a user-defined UI scenario (e.g.

    238 GitHub stars~603 tokensUpdated 2 days ago
    Auto-check passed
  • Post PR To Slack

    imbue-ai/sculptor

    Post a one-line PR announcement to a Slack channel, and mark it :merged: when the PR merges.

    238 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed
  • Batch Claude Runner

    imbue-ai/sculptor

    Run Claude programmatically against collections of files in the codebase.

    238 GitHub stars~308 tokensUpdated 2 days ago
    Auto-check passed
  • Build Sculptor Extension

    imbue-ai/sculptor

    Build or modify a Sculptor extension — a runtime ESM module loaded into the Sculptor UI.

    238 GitHub stars~3.4k tokensUpdated 2 days ago
    Auto-check passed
  • Code Review Checklist

    imbue-ai/sculptor

    Review a set of code changes against Sculptor's review categories and produce a markdown findings table.

    238 GitHub stars~3.6k tokensUpdated 2 days ago
    Auto-check passed

Works with

Categories

Questions about Openhost Sculptor

What does Openhost Sculptor do?

Deploy, verify, and reset the self-hosted Sculptor app running as an OpenHost app (built from source via openhost.Dockerfile). Openhost Sculptor is an agent skill from imbue-ai/sculptor.Dockerfile).

When should I use Openhost Sculptor?

Openhost Sculptor fits situations like: tasks that involve Containers.

How do I install Openhost Sculptor in Claude Code?

Run `npx skills add imbue-ai/sculptor --skill openhost-sculptor -a claude-code`. Or copy the skill folder (.claude/skills/openhost-sculptor in imbue-ai/sculptor) into .claude/skills/openhost-sculptor in your project. Claude Code loads it when a task matches its description.

How do I install Openhost Sculptor in Codex?

Run `npx skills add imbue-ai/sculptor --skill openhost-sculptor -a codex`. Or copy the skill folder (.claude/skills/openhost-sculptor in imbue-ai/sculptor) into .agents/skills/openhost-sculptor in your project. Codex loads it when a task matches its description.

Can I use Openhost Sculptor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add imbue-ai/sculptor --skill openhost-sculptor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/openhost-sculptor, .gemini/skills/openhost-sculptor, .github/skills/openhost-sculptor and .opencode/skills/openhost-sculptor in your project.

What does Openhost Sculptor need to run?

Going by SKILL.md and its folder, Openhost Sculptor needs a shell for the scripts in its folder and the command-line tools its instructions call (git, python, just, pnpm and uvicorn). Our summary lists: Python 3; A Bash shell.

Does Openhost Sculptor access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Openhost Sculptor safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Openhost Sculptor use?

Openhost Sculptor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Openhost Sculptor use?

About 2.4k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Openhost Sculptor?

Skills that share tags, products or a category with Openhost Sculptor: Iron Proxy Gateway for NanoClaw (nanocoai/nanoclaw, 31k stars), GreptimeDB Dev Docker Image (GreptimeTeam/greptimedb, 6.7k stars), Senior DevOps Toolkit (maslennikov-ig/claude-code-orchestrator-kit, 260 stars) and LangBot Deployment Guide (langbot-app/LangBot, 18k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Openhost Sculptor?

imbue-ai (a GitHub organization) maintains it in imbue-ai/sculptor, which has 238 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 9, 2026.

Source: imbue-ai/sculptor on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.