Start
Donchitos/Claude-Code-Game-Studios
First-time onboarding — asks where you are, then guides you to the right workflow.
Use AgentOS as the operator control plane above OpenClaw for starting, inspecting, and diagnosing a digital workforce.
MITAuto-check passed
Install Agentos
$ npx skills add SapienXai/AgentOS --skill agentos -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install SapienXai/AgentOS agentos --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/SapienXai/AgentOS.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/openclaw-agentos/skills/agentos .claude/skills/agentos && rm -rf skills-srcUse ~/.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/
Install the "agentos" agent skill from https://github.com/SapienXai/AgentOS/tree/main/packages/openclaw-agentos/skills/agentos into .claude/skills/agentos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentos", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/SapienXai/AgentOS/tree/main/packages/openclaw-agentos/skills/agentosType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add SapienXai/AgentOS --skill agentos -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install SapienXai/AgentOS agentos --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SapienXai/AgentOS.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/openclaw-agentos/skills/agentos .agents/skills/agentos && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agentos" agent skill from https://github.com/SapienXai/AgentOS/tree/main/packages/openclaw-agentos/skills/agentos into .agents/skills/agentos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentos", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add SapienXai/AgentOS --skill agentos -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install SapienXai/AgentOS agentos --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SapienXai/AgentOS.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/openclaw-agentos/skills/agentos .cursor/skills/agentos && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agentos" agent skill from https://github.com/SapienXai/AgentOS/tree/main/packages/openclaw-agentos/skills/agentos into .cursor/skills/agentos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentos", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/SapienXai/AgentOS.git --path packages/openclaw-agentos/skills/agentos--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add SapienXai/AgentOS --skill agentos -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install SapienXai/AgentOS agentos --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SapienXai/AgentOS.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/openclaw-agentos/skills/agentos .gemini/skills/agentos && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agentos" agent skill from https://github.com/SapienXai/AgentOS/tree/main/packages/openclaw-agentos/skills/agentos into .gemini/skills/agentos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentos", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install SapienXai/AgentOS agentosInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add SapienXai/AgentOS --skill agentos -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/SapienXai/AgentOS.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/openclaw-agentos/skills/agentos .github/skills/agentos && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agentos" agent skill from https://github.com/SapienXai/AgentOS/tree/main/packages/openclaw-agentos/skills/agentos into .github/skills/agentos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentos", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add SapienXai/AgentOS --skill agentos -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install SapienXai/AgentOS agentos --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/SapienXai/AgentOS.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/openclaw-agentos/skills/agentos .opencode/skills/agentos && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agentos" agent skill from https://github.com/SapienXai/AgentOS/tree/main/packages/openclaw-agentos/skills/agentos into .opencode/skills/agentos/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agentos", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agentos- GitHub stars
- 118
- Token cost
- ~679 tokens
- SKILL.md length
- 257 words
- Files
- 1
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Use AgentOS as the operator control plane above OpenClaw for starting, inspecting, and diagnosing a digital workforce.
- Works in 4 steps: Check that @sapienx/agentos is installed… → Confirm the agentos executable is on… → Run openclaw agentos doctor --deep after… → …
- SKILL.md covers Start here, What this gives the operator, Recovery and Learn more
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Agentos is an agent skill from SapienXai/AgentOS. Use AgentOS as the operator control plane above OpenClaw for starting, inspecting, and diagnosing a digital workforce.
Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: Run agents like a company. AgentOS is the native control plane for OpenClaw — manage agents, tasks, models, context, approvals, and runtime visibility from one place. The licence is MIT.
Example prompts
- “/agentos”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Check that @sapienx/agentos is installed separately.
- Confirm the agentos executable is on PATH, or set AGENTOS_BIN to an absolute executable path.
- Run openclaw agentos doctor --deep after AgentOS is available.
- Treat missing, degraded, or unknown OpenClaw state as a real diagnostic state; do not infer that a process is authenticated or healthy…
What it can do on your machine
Read from SKILL.md and the folder at commit 7dcb7fc. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
youtu.beagentos.sapienx.appclawhub.ai
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
Agentos loads about 679 tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 257 words of instructions outside code blocks.
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 passed
The automated check found no risky patterns in SKILL.md.
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from SapienXai/AgentOS at commit 7dcb7fc, republished under its MIT licence (© SapienXai). 257 words, ~679 tokens.
Download SKILL.mdSave it as
.claude/skills/agentos/SKILL.md (or your agent's skills folder).- name
- agentos
- description
- Use AgentOS as the operator control plane above OpenClaw for starting, inspecting, and diagnosing a digital workforce.
- user-invocable
- true
<div align="center"> <h1>AgentOS</h1> <p>
<strong>Run AI agents like a company.</strong><br />
The human operating layer above OpenClaw.
</p> <a href="https://youtu.be/ribFHZuKRos">
<img src="https://raw.githubusercontent.com/SapienXai/AgentOS/main/public/assets/screenshots/hero.jpeg" alt="AgentOS Mission Control product preview" width="100%" />
</a> <sub>Operator guide · OpenClaw-native · Human-controlled</sub>
</div>AgentOS operator guide
AgentOS is the operator-facing control plane above OpenClaw. OpenClaw remains authoritative for the Gateway, agents, sessions, tasks, models, channels, plugins, runtime skills, and native lifecycle.
Start here
Use the native OpenClaw plugin command when it is installed:
openclaw agentosThe command opens AgentOS in the default browser. For explicit operations:
openclaw agentos start --open
openclaw agentos status
openclaw agentos doctor --deep
openclaw agentos doctor --deep --json
openclaw agentos versionWhat this gives the operator
- A visual Mission Control surface for workspaces and digital workers.
- A direct path from OpenClaw runtime state to operator-facing diagnostics.
- Clear visibility into ready, degraded, unavailable, and unknown states.
- A safe place to inspect work before assigning more missions.
Recovery
If the command reports that AgentOS is unavailable:
- Check that
<code>@sapienx/agentos</code>is installed separately. - Confirm the
<code>agentos</code>executable is on<code>PATH</code>, or set<code>AGENTOS_BIN</code>to an absolute executable path. - Run
<code>openclaw agentos doctor --deep</code>after AgentOS is available. - Treat missing, degraded, or unknown OpenClaw state as a real diagnostic state; do not infer that a process is authenticated or healthy from liveness alone.
If the plugin itself is missing, inspect the native OpenClaw plugin inventory and install the ClawHub package:
openclaw plugins list
openclaw plugins install clawhub:@sapienx/openclaw-agentosDo not create a second AgentOS runtime, a parallel skill engine, or a local substitute for OpenClaw Gateway state. Use the native OpenClaw capability when available and report unsupported or degraded behavior clearly.
Learn more
© SapienXai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in packages/openclaw-agentos/skills/agentos of SapienXai/AgentOS.
Open the folder on GitHubat commit 7dcb7fc
Compare with similar skills
Agentos 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agentos this skillSapienXai/AgentOS | 118 | — | ~679 | Automated safety check: Pass | MIT | |
| StartDonchitos/Claude-Code-Game-Studios | 26k | — | ~6.5k | Automated safety check: Pass | MIT | |
| It Operationsdavila7/claude-code-templates | 32k | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| Planejeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Operator Approval Loopaffaan-m/ECC | 276k | — | ~3.3k | Automated safety check: Pass | MIT | |
| Business Operations Skillsalirezarezvani/claude-skills | 28k | — | ~2.3k | Automated safety check: Pass | MIT |
Similar skills
It Operations
davila7/claude-code-templates
Manages IT infrastructure, monitoring, incident response, and service reliability.
Plane
jeremylongshore/tons-of-skills-marketplace
Plane is a team behavior observatory — synthesize Plane API data into observations about how teams actually behave under pressure, not just ticket state.
Operator Approval Loop
affaan-m/ECC
Operator approval contract with internal filing notices for agent-drafted outbound messages, hashed drafts, epoch-keyed decisions, durable delivery claims and receipts, and a pre-draft baseline gate.
Business Operations Skills
alirezarezvani/claude-skills
A skill your agent uses when running, diagnosing, or designing internal business operations — process documentation, vendor SLAs, capacity planning, internal comms, SOP/runbook authoring…
Kubernetes Operator
alirezarezvani/claude-skills
A skill your agent uses when building a Kubernetes Operator — custom controllers that reconcile CRD state.
More from SapienXai/AgentOS
Agentos UI UX
SapienXai/AgentOS
Design, review, or implement AgentOS UI and UX work using the project’s operator-console visual system.
Questions about Agentos
What does Agentos do?
Use AgentOS as the operator control plane above OpenClaw for starting, inspecting, and diagnosing a digital workforce. Agentos is an agent skill from SapienXai/AgentOS. Use AgentOS as the operator control plane above OpenClaw for starting, inspecting, and diagnosing a digital workforce.
How do I install Agentos in Claude Code?
Run `npx skills add SapienXai/AgentOS --skill agentos -a claude-code`. Or copy the skill folder (packages/openclaw-agentos/skills/agentos in SapienXai/AgentOS) into .claude/skills/agentos in your project. Claude Code loads it when a task matches its description.
How do I install Agentos in Codex?
Run `npx skills add SapienXai/AgentOS --skill agentos -a codex`. Or copy the skill folder (packages/openclaw-agentos/skills/agentos in SapienXai/AgentOS) into .agents/skills/agentos in your project. Codex loads it when a task matches its description.
Can I use Agentos 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 SapienXai/AgentOS --skill agentos -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentos, .gemini/skills/agentos, .github/skills/agentos and .opencode/skills/agentos in your project.
What does Agentos need to run?
SKILL.md names no scripts, command-line tools or credentials: Agentos is instructions for the agent only.
Does Agentos access the network?
SKILL.md names 3 domains. As links in the text: youtu.be, agentos.sapienx.app and clawhub.ai. This is read from the text; nothing was executed.
Is Agentos safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Agentos use?
Agentos 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 Agentos use?
About 679 tokens (SKILL.md is roughly 2.7k 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 Agentos?
Skills that share tags, products or a category with Agentos: Start (Donchitos/Claude-Code-Game-Studios, 26k stars), It Operations (davila7/claude-code-templates, 32k stars), Plane (jeremylongshore/tons-of-skills-marketplace, 2.8k stars) and Operator Approval Loop (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agentos?
SapienXai (a GitHub organization) maintains it in SapienXai/AgentOS, which has 118 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 3, 2026.
Source: SapienXai/AgentOS on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.