ai-maestro-agents-management

ai-maestro-agents-management is a skill for Claude Code from 23blocks-OS/ai-maestro-plugins. It costs 79 tokens per session (1,964 once invoked), scanned A, original, MIT.

A tool for managing AI agents through the AI Maestro command line, including creating, viewing, updating, stopping, and restarting them. It also handles agent installation, import, export, and marketplace tasks.

In plain words
What is it for?
Use it to create agents, list or inspect them, change their state or settings, remove them, and manage agent plugins or transfers.
Why use it?
It replaces separate manual steps for controlling many agents with a consistent command-based workflow.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/dev/projects/my-api.

Part of the ai-maestro plugin — 8 skills, 3 hooks shipped together

Good fit Use it to create agents, list or inspect them, change their state or settings, remove them, and manage agent plugins or transfers.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add 23blocks-OS/ai-maestro-plugins
Claude Code
/plugin install ai-maestro

Made for: Claude Code.

Or install ai-maestro, the plugin that ships this one along with the rest of its 8 skills, 3 hooks.

Wrote 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.

agentmods badge for ai-maestro-agents-management

README.md
[![agentmods](https://agentmods.dev/badge/skills/23blocks-os/ai-maestro-plugins/ai-maestro-agents-management/github.svg)](https://agentmods.dev/skills/23blocks-os/ai-maestro-plugins/ai-maestro-agents-management)
Your own site
<a href="https://agentmods.dev/skills/23blocks-os/ai-maestro-plugins/ai-maestro-agents-management"><img src="https://agentmods.dev/badge/skills/23blocks-os/ai-maestro-plugins/ai-maestro-agents-management/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.

agentmods 80×15 button for ai-maestro-agents-management

Your own site · 80×15
<a href="https://agentmods.dev/skills/23blocks-os/ai-maestro-plugins/ai-maestro-agents-management"><img src="https://agentmods.dev/badge/skills/23blocks-os/ai-maestro-plugins/ai-maestro-agents-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,964 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.01964
Opus 5 $0.00039 $0.00982
Sonnet 5 $0.00016 $0.00393
Haiku 4.5 $0.00008 $0.00196

Measured 11d ago against content hash 73b7f8702973, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-maestro-agents-management scanned grade A 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Requirements:** macOS or Linux, Bash 4.0+, tmux 3.0+, jq, curl
plugins/ai-maestro/skills/ai-maestro-agents-management/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Maestro Agent Management

Purpose

Manage AI agents through the AI Maestro CLI. This skill provides commands for creating, updating, deleting, hibernating, and waking agents. It also handles plugin management and agent import/export.

CRITICAL: This is an Agent Management Skill

This skill is for managing other agents, not for inter-agent communication (use agent-messaging skill for that).

CLI Script

Script: aimaestro-agent.sh (Bash, macOS/Linux)

Installation: ./install-agent-cli.sh

Requirements: macOS or Linux, Bash 4.0+, tmux 3.0+, jq, curl


PART 1: AGENT LIFECYCLE

1. List Agents

aimaestro-agent.sh list [--status online|offline|hibernated|all] [--format table|json|names] [-q|--quiet] [--json]

Examples: list, list --status online, list --format json, list -q

2. Show Agent Details

aimaestro-agent.sh show <agent> [--format pretty|json]

3. Create Agent

--dir is required.

aimaestro-agent.sh create <name> --dir <path> [options] [-- <program-args>...]

Options: -p/--program, -m/--model, -t/--task, --tags, -T/--trust-level, --no-session, --no-folder, --force-folder

Trust levels: supervised (default), planOnly, trustEdits, smartAuto, fullAutonomy

Examples:

aimaestro-agent.sh create my-api --dir /Users/dev/projects/my-api
aimaestro-agent.sh create backend-service \
  --dir /Users/dev/projects/backend \
  --task "Implement user authentication with JWT" \
  --tags "api,auth,security"
aimaestro-agent.sh create debug-agent --dir /Users/dev/projects/debug -- --verbose --debug
aimaestro-agent.sh create auto-agent --dir ~/Code/auto --trust-level smartAuto

4. Update Agent

aimaestro-agent.sh update <agent> [options]

Options: -t/--task, -m/--model, --tags, --add-tag, --remove-tag, --args

Examples:

aimaestro-agent.sh update backend-api --task "Focus on payment integration"
aimaestro-agent.sh update backend-api --add-tag "critical"
aimaestro-agent.sh update backend-api --args "--continue --chrome"

Read the full file on GitHub · 281 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 11d ago First seen · 281 lines · 79 tokens per session scan A 73b7f8702973

Subscribe to this mod's changes

ai-maestro-agents-management is a skill published in the GitHub repository 23blocks-OS/ai-maestro-plugins (9 stars, last pushed 6d ago), licensed MIT. It adds 79 tokens to every session and 1,964 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

compose-next

Use this skill only when the user explicitly asks for the Compose Next delivery workflow, by name or in clear natural language. It carries one feature, fix, or refactor through requirement resolution, workspace setup, specification, implementation, verification, independent review, and hand-off in a single contract.…

evoelsewhere/evoflux · 96 tokens

coding-investigation

Investigate unfamiliar code behavior, or answer an exact symbol's definition, callers, callees, references, impact, and cross-repository relationship questions. Use it to trace activation, ownership, data flow, configuration, registration, and runtime wiring with bounded source evidence without mutating code; do not…

evoelsewhere/evoflux · 81 tokens

deep-research

Use this skill for a thorough multi-source investigation that must end in a cited report: competitive landscapes, technology comparisons across many candidates, market or policy questions where one search is not enough. It scopes a brief, gathers evidence into a durable workspace, and writes one coherent sourced…

evoelsewhere/evoflux · 85 tokens

skill-installer

Create, import, update, validate, or relocate portable Agent Skill bundles with SKILL.md, on-demand references, deterministic scripts, output assets, UI metadata, and EvoFlux mode settings. Use for explicit skill authoring or installation; do not use for invoking an existing skill, changing agent configuration, or…

evoelsewhere/evoflux · 71 tokens

pdf

Read, create and manipulate PDF files — extract text and tables, merge, split, rotate, reorder and delete pages, read and fill AcroForm fields, add or strip metadata, encrypt and decrypt, and generate new PDFs from HTML or from scratch. Also covers rasterising pages to images so a PDF can actually be looked at, and…

smith-network-solutions/threadknot · 88 tokens

easd-implement

Implement bounded work for an active EASD run under its accepted specification and AC ownership. Use only when EASD has authorized implementation; do not use while the run is Intent, authoring, draft, or merely accepted.

evoelsewhere/evoflux · 51 tokens