MCP Server Builder with mcp-use
mcp-use/mcp-use
Builds, modifies, debugs, migrates and verifies TypeScript MCP servers and MCP Apps with the mcp-use framework, treating the installed package's types as the source of truth.
Verify whether a CAO session is actually alive and what it really said, before reporting progress or completion to a user.
Install Cao Session Liveness
$ npx skills add awslabs/cli-agent-orchestrator --skill cao-session-liveness -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install awslabs/cli-agent-orchestrator cao-session-liveness --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/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cao-session-liveness .claude/skills/cao-session-liveness && 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 "cao-session-liveness" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-session-liveness into .claude/skills/cao-session-liveness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-session-liveness", 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/awslabs/cli-agent-orchestrator/tree/main/skills/cao-session-livenessType 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 awslabs/cli-agent-orchestrator --skill cao-session-liveness -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install awslabs/cli-agent-orchestrator cao-session-liveness --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/cao-session-liveness .agents/skills/cao-session-liveness && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "cao-session-liveness" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-session-liveness into .agents/skills/cao-session-liveness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-session-liveness", 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 awslabs/cli-agent-orchestrator --skill cao-session-liveness -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install awslabs/cli-agent-orchestrator cao-session-liveness --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/cao-session-liveness .cursor/skills/cao-session-liveness && 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 "cao-session-liveness" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-session-liveness into .cursor/skills/cao-session-liveness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-session-liveness", 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/awslabs/cli-agent-orchestrator.git --path skills/cao-session-liveness--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 awslabs/cli-agent-orchestrator --skill cao-session-liveness -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install awslabs/cli-agent-orchestrator cao-session-liveness --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/cao-session-liveness .gemini/skills/cao-session-liveness && 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 "cao-session-liveness" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-session-liveness into .gemini/skills/cao-session-liveness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-session-liveness", 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 awslabs/cli-agent-orchestrator cao-session-livenessInstalls 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 awslabs/cli-agent-orchestrator --skill cao-session-liveness -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/cao-session-liveness .github/skills/cao-session-liveness && 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 "cao-session-liveness" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-session-liveness into .github/skills/cao-session-liveness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-session-liveness", 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 awslabs/cli-agent-orchestrator --skill cao-session-liveness -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install awslabs/cli-agent-orchestrator cao-session-liveness --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/awslabs/cli-agent-orchestrator.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/cao-session-liveness .opencode/skills/cao-session-liveness && 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 "cao-session-liveness" agent skill from https://github.com/awslabs/cli-agent-orchestrator/tree/main/skills/cao-session-liveness into .opencode/skills/cao-session-liveness/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "cao-session-liveness", 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
cao-session-liveness- GitHub stars
- 1.4k
- Token cost
- ~1.5k tokens
- SKILL.md length
- 846 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Verify whether a CAO session is actually alive and what it really said, before reporting progress or completion to a user.
- Works in 3 steps: Read the status (get_terminal_status, or… → Read the output tail… → If the two disagree, the output wins.
- Tasks that involve Authentication
- SKILL.md covers Why this matters, The two-signal rule, Dead-session discriminators and Verify a provider before…, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Cao Session Liveness is an agent skill from awslabs/cli-agent-orchestrator, published by the product's own GitHub organization. Verify whether a CAO session is actually alive and what it really said, before reporting progress or completion to a user. Use alongside cao-session-management whenever you launch, poll, or report on a CAO session — especially when a session appears stalled, a send times out, or a status value looks inconsistent with the output.
Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Authentication. It works with Model Context Protocol. The repository describes itself as: Multi-agent orchestration for AI coding CLIs — Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Authentication
Example prompts
- “/cao-session-liveness”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Read the status (get_terminal_status, or cao session status SESSION).
- Read the output tail (read_session_output / get_terminal_output, or
- If the two disagree, the output wins.
What it can do on your machine
Read from SKILL.md and the folder at commit 4fc75df. 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.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Cao Session Liveness loads about 1.5k tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 846 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 awslabs/cli-agent-orchestrator at commit 4fc75df, republished under its Apache-2.0 licence (© awslabs). 846 words, ~1,518 tokens.
Download SKILL.mdSave it as
.claude/skills/cao-session-liveness/SKILL.md (or your agent's skills folder).- name
- cao-session-liveness
- description
- Verify whether a CAO session is actually alive and what it really said, before reporting progress or completion to a user. Use alongside cao-session-management whenever you launch, poll, or report on a CAO session — especially when a session appears stalled, a send times out, or a status value looks inconsistent with the output.
CAO Session Liveness
Companion to cao-session-management, which covers the mechanics of launching
and messaging sessions. This skill covers a single question that mechanics alone
cannot answer: is the session actually alive, and is the status telling me the
truth?
Why this matters
Every CAO provider infers agent state by pattern-matching the rendered terminal
screen. There is no structured protocol between CAO and the provider CLI. A
provider that has exited, crashed, or stalled on an unanswerable dialog can
leave a screen that still matches an idle or processing pattern.
The consequence is specific and it is the failure this skill exists to prevent: reporting progress on a session that is already dead.
The two-signal rule
Never report readiness, progress, or completion from a status value alone. Always corroborate with output before you tell a user anything:
- Read the status (
get_terminal_status, orcao session status SESSION). - Read the output tail (
read_session_output/get_terminal_output, orcao session status SESSION --jsonand inspectlast_output). - If the two disagree, the output wins.
A status of idle with an output tail showing a shell prompt means the CLI
exited. Report the session as dead, not as ready.
Dead-session discriminators
Treat any of the following in the output tail as proof the provider is no longer running, regardless of the reported status:
| Signal | Means |
|---|---|
Session ended. / Resume with: <cli> --resume-id ... | The CLI exited on its own |
error: Conflicting options: or a usage/help banner | The CLI rejected its launch flags and never started |
API Error (...), 400, or a model/auth failure | The provider started but cannot reach a model |
| A bare shell prompt with a directory and timestamp, no agent chrome | The pane fell back to the shell |
| An output read that fails with an extraction error | No response boundary on screen; corroborate before trusting |
A session parked in waiting_user_answer that never advances is usually stalled
on a dialog nothing will answer. Treat it as dead weight, report it to the user,
and do not silently kill it.
Not a dead session: a finished handoff worker
A blocking handoff tears its worker down once it returns. The worker terminal
ID the conductor reports was valid during the call and is gone afterwards, so
querying it later is expected to fail:
get_terminal_status/GET /terminals/<id>returns not-foundcao session status SESSION --workerslists no workers
Neither is evidence the conductor invented the delegation. Confirm a handoff from
the conductor's own transcript — a full-mode output read showing the
handoff tool call, its agent_profile, and the returned output — not from the
terminal registry. Only a non-blocking assign leaves a worker alive to query.
Do not accuse a conductor of fabricating a delegation on the strength of a missing terminal alone.
Show full SKILL.md (396 more words)Show less
Verify a provider before depending on it
Provider reliability varies, is version-sensitive, and changes as upstream CLIs release new dialogs and flags. Do not assume; verify once per environment:
- Launch a throwaway session in a scratch directory.
- Apply the two-signal rule.
- Send a trivial task with a short timeout and confirm output returns.
- Shut the session down.
Known reliability characteristics, as context for interpreting what you see:
| Provider | Detection basis | What to watch for |
|---|---|---|
kiro_cli | Version-specific prompt, credits, and separator patterns | New startup dialogs that default to a decline option; flag combinations the installed CLI rejects |
hermes | Idle timer stable across repeated polls | Custom themes break prompt matching; slowest to confirm completion. Patterns are overridable by environment variable |
opencode_cli | Alt-screen TUI completion marker | Scrollback is roughly one viewport; a long single response can lose its own top and fail extraction |
claude_code, codex | Rendered-screen detection | Generally stable headless; still apply the two-signal rule |
If a provider fails to launch headlessly, report the exact signature to the user and offer a different provider. Do not retry the same launch repeatedly — a flag rejection or a declining dialog will fail identically every time.
Interpreting a send that does not return
- A timeout is not a failure. The agent is still working; the caller stopped waiting. Say so, and check again later.
- Never re-send a task after a timeout. The original may still be running, and a duplicate risks conflicting work in the same directory.
- A busy terminal refuses input. Wait for
idleorcompleted; do not force. - An async send returns nothing by design. Poll afterwards, applying the two-signal rule.
Record what each session is for
CAO stores a session's name, not its purpose. An inventory of live sessions cannot tell you which is safe to touch.
Keep a short registry outside CAO — one line per session you launch: name, provider, working directory, purpose, date. Update it on launch and on shutdown, and read it before answering any question about what a session is doing or before acting on one.
Do not act on sessions you did not launch
Long-running sessions may hold real, unrecoverable work. Reads are always safe. Before sending to or shutting down a session you did not start yourself, ask the user first. Never issue a shutdown that targets all sessions at once.
Related
- cao-session-management — launching, messaging, and worker communication mechanics
© awslabs, Apache-2.0. 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 skills/cao-session-liveness of awslabs/cli-agent-orchestrator.
Open the folder on GitHubat commit 4fc75df
Compare with similar skills
Cao Session Liveness 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 |
|---|---|---|---|---|---|---|
| Cao Session Liveness this skillawslabs/cli-agent-orchestrator | 1.4k | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| MCP Server Builder with mcp-usemcp-use/mcp-use | 11k | — | ~923 | Automated safety check: Pass | Apache-2.0 | |
| Cross Origin Iframe Probejumodada/Drissionpage-MCP-Server | 487 | — | ~1.2k | Automated safety check: Pass | Custom licence | |
| Githits Onboardinggithits-com/githits-cli | 115 | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | |
| Fastmcp Serverdavila7/claude-code-templates | 33k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Copilot SDKintellectronica/agent-skills | 295 | — | ~3.2k | Automated safety check: Pass | CC0-1.0 |
Similar skills
Cross Origin Iframe Probe
jumodada/Drissionpage-MCP-Server
A skill your agent uses when a drissionpage-mcp task targets an iframe such as a payment widget, challenge, SSO flow, or embedded checkout.
Githits Onboarding
githits-com/githits-cli
A skill your agent uses when the user asks to install, connect, configure, sign in to, sign up for, or start using GitHits.
Fastmcp Server
davila7/claude-code-templates
Complete guide for building MCP servers with FastMCP 3.0 - tools, resources, authentication, providers, middleware, and deployment.
Copilot SDK
intellectronica/agent-skills
This skill helps with GitHub Copilot SDK work across Node.js/TypeScript, Python, Go, .NET, and Java.
Copilot SDK
aiskillstore/marketplace
Build applications that programmatically interact with GitHub Copilot.
More from awslabs/cli-agent-orchestrator
All 14 skills in this repo- Official
Cao MCP Apps
awslabs/cli-agent-orchestrator
Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman).
- Official
Agui Author
awslabs/cli-agent-orchestrator
Author live dashboard UI from an agent via the emitui MCP tool.
- Official
MCP Apps Builder
awslabs/cli-agent-orchestrator
Load the official MCP Apps builder skills (create-mcp-app, migrate-oai-app, add-app-to-server, convert-web-app) from github.com/modelcontextprotocol/ext-apps.
- Official
Cao Plugin
awslabs/cli-agent-orchestrator
Create a new CAO (CLI Agent Orchestrator) plugin. An agent skill from awslabs/cli-agent-orchestrator.
- Official
Cao Provider
awslabs/cli-agent-orchestrator
Create a new CLI agent provider for CAO (CLI Agent Orchestrator).
- Official
Cao Agent Routing
awslabs/cli-agent-orchestrator
Find and select the best installed CAO agent profile for a task before delegating with assign or handoff.
Related
Works with
Categories
Questions about Cao Session Liveness
What does Cao Session Liveness do?
Verify whether a CAO session is actually alive and what it really said, before reporting progress or completion to a user. Cao Session Liveness is an agent skill from awslabs/cli-agent-orchestrator, published by the product's own GitHub organization. Verify whether a CAO session is actually alive and what it really said, before reporting progress or completion to a user.
When should I use Cao Session Liveness?
Cao Session Liveness fits situations like: tasks that involve Authentication.
How do I install Cao Session Liveness in Claude Code?
Run `npx skills add awslabs/cli-agent-orchestrator --skill cao-session-liveness -a claude-code`. Or copy the skill folder (skills/cao-session-liveness in awslabs/cli-agent-orchestrator) into .claude/skills/cao-session-liveness in your project. Claude Code loads it when a task matches its description.
How do I install Cao Session Liveness in Codex?
Run `npx skills add awslabs/cli-agent-orchestrator --skill cao-session-liveness -a codex`. Or copy the skill folder (skills/cao-session-liveness in awslabs/cli-agent-orchestrator) into .agents/skills/cao-session-liveness in your project. Codex loads it when a task matches its description.
Can I use Cao Session Liveness 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 awslabs/cli-agent-orchestrator --skill cao-session-liveness -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cao-session-liveness, .gemini/skills/cao-session-liveness, .github/skills/cao-session-liveness and .opencode/skills/cao-session-liveness in your project.
What does Cao Session Liveness need to run?
SKILL.md names no scripts, command-line tools or credentials: Cao Session Liveness is instructions for the agent only.
Does Cao Session Liveness access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Cao Session Liveness 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 Cao Session Liveness use?
Cao Session Liveness is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Cao Session Liveness use?
About 1.5k tokens (SKILL.md is roughly 6.1k 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 Cao Session Liveness?
Skills that share tags, products or a category with Cao Session Liveness: MCP Server Builder with mcp-use (mcp-use/mcp-use, 11k stars), Cross Origin Iframe Probe (jumodada/Drissionpage-MCP-Server, 487 stars), Githits Onboarding (githits-com/githits-cli, 115 stars) and Fastmcp Server (davila7/claude-code-templates, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Cao Session Liveness?
awslabs (a GitHub organization, an official publisher) maintains it in awslabs/cli-agent-orchestrator, which has 1,402 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 10, 2026.
Source: awslabs/cli-agent-orchestrator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.