CLI Agent Orchestrator is a tool that coordinates multiple AI coding command-line programs by running them as separate workers in isolated terminal sessions. A supervisor uses it to delegate software tasks to specialist agents in parallel or in sequence while the workers retain their normal command-line capabilities. The catalogue skills operate this orchestration workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add awslabs/cli-agent-orchestrator --skill cao-session-livenessgit clone --depth 1 https://github.com/awslabs/cli-agent-orchestratorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/awslabs/cli-agent-orchestrator/cao-session-liveness)<a href="https://agentmods.dev/skills/awslabs/cli-agent-orchestrator/cao-session-liveness"><img src="https://agentmods.dev/badge/skills/awslabs/cli-agent-orchestrator/cao-session-liveness/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/awslabs/cli-agent-orchestrator/cao-session-liveness"><img src="https://agentmods.dev/badge/skills/awslabs/cli-agent-orchestrator/cao-session-liveness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.01336 |
| Opus 5 | $0.00035 | $0.00668 |
| Sonnet 5 | $0.00014 | $0.00267 |
| Haiku 4.5 | $0.00007 | $0.00134 |
Grade A, and why
cao-session-liveness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 127 lines · 70 tokens per session scan A c31bfc26f3ef
cao-session-liveness is a skill published in the GitHub repository awslabs/cli-agent-orchestrator (1,235 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 1,336 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tool-selection
Internal guidance for choosing between agent-rack's sync and background execution tools, and when to use per-agent shortcuts. Use whenever delegating a task to a claude/codex/opencode/Antigravity/custom sub-agent through agent-rack.
review
Run a structured, read-only code review through agent-rack's agentreview tool.
session-send
Send follow-up input to a running background agent-rack session.
review-handling
Internal guidance for presenting agent-rack's agentreview output back to the user. Use whenever an agentreview call (foreground or via agentsessionstatus) returns a result.
run
Run a one-shot task synchronously with a named CLI sub-agent via agent-rack.
session-logs
Read the raw stdout/stderr event stream from a background agent-rack session.