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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/awslabs/cli-agent-orchestratornpx agentmods add skills/awslabs/cli-agent-orchestrator/cao-agent-plugin-auditWrote 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-agent-plugin-audit)<a href="https://agentmods.dev/skills/awslabs/cli-agent-orchestrator/cao-agent-plugin-audit"><img src="https://agentmods.dev/badge/skills/awslabs/cli-agent-orchestrator/cao-agent-plugin-audit/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-agent-plugin-audit"><img src="https://agentmods.dev/badge/skills/awslabs/cli-agent-orchestrator/cao-agent-plugin-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00218 | $0.03564 |
| Opus 5.5 | $0.00087 | $0.01426 |
| Sonnet 5.5 | $0.00044 | $0.00713 |
| Haiku 4.5 | $0.00022 | $0.00356 |
Grade B, and why
cao-agent-plugin-audit scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$W" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit an Agent Plugin
Check an existing Agent Plugins 1.0.0 package against two things: the vendored manifest schemas, and the Agent Skills limits. The second half is the reason this skill exists. CAO's own validator does not check four of the five skill rules below (the name pattern, the 64-character name bound, the 1024-character description limit and the 500-line body limit), and no other artifact CAO ships enforces them mechanically.
This skill audits a package that already follows the Agent Plugins 1.0.0
structure. It is not a pre-migration review of a client-specific agent plugin;
that is migrate-agent-plugin's job.
What CAO checks, and what it does not
CAO's package validation (cao plugin validate, and the loader behind it) checks
a skill for exactly three things:
- frontmatter
nameis present and not blank; - frontmatter
descriptionis present and not blank (src/cli_agent_orchestrator/models/skill.py); - the folder name equals the frontmatter
name(src/cli_agent_orchestrator/utils/skills.py).
It does not check the Agent Skills name pattern, the 64-character name bound, the 1024-character description limit, or the 500-line body limit. Apart from this skill, nothing else CAO ships checks them either.
What CAO does with a skill that breaks those limits was at first only inferred
from models/skill.py. It has since been observed, in the over-limit experiment
run for issue #1153 (task T3) and again when this skill was written: a package
with one skill whose description is 2000 characters, or whose body is 600
lines, validates as "loadable": true with "findings": [] and exit 0, and the
skill is loaded. That observation covers only the two length limits. T3 did
not test a skill that breaks the name pattern or the 64-character name bound, so
what CAO does with one is inferred, not observed: it is read from
models/skill.py:12-19, which checks only that name and description are not
blank, and utils/skills.py:66-69, which checks only that the folder name equals
name. Neither applies the pattern or the bound. Reproduce the length case in a
temporary directory:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 269 lines · 218 tokens per session scan B 4d0e7bcc7598
cao-agent-plugin-audit is a skill published in the GitHub repository awslabs/cli-agent-orchestrator (1,515 stars, last pushed yesterday), licensed Apache-2.0. It adds 218 tokens to every session and 3,564 once invoked, about $0.0009 per session on Opus 5.5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-05.
cao-agent-plugin-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cao-agent-plugin-auditawslabs/cli-agent-orchestrator | Skill | 1.5k | yesterday | Apache-2.0 | B | 218 | Claude Code |
| tool-selectionlakpriya1s/agent-rack | Skill | 2 | 3mo ago | MIT | A | 53 | Claude Code |
| reviewlakpriya1s/agent-rack | Skill | 2 | 3mo ago | MIT | A | 18 | Claude Code |
| session-sendlakpriya1s/agent-rack | Skill | 2 | 3mo ago | MIT | A | 15 | Claude Code |
| review-handlinglakpriya1s/agent-rack | Skill | 2 | 3mo ago | MIT | A | 38 | Claude Code |
| runlakpriya1s/agent-rack | Skill | 2 | 3mo ago | MIT | A | 19 | Claude Code |
| session-logslakpriya1s/agent-rack | Skill | 2 | 3mo ago | MIT | A | 19 | Claude Code |