Skip to content
Back to skills

Delegation

ASecurity

Show or change the delegation level 0-5 (0 - do everything yourself, subagents blocked by a hook; 3 - the default; 5 - orchestrator). Invoked as /delegation, /delegation 3, /delegation global 4, /delegation clear. Needs the delegation dial switched on in the hub home's config.json.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 7, 2026
ai-agentsrustshell

Security analysis

A100/100

Scanned October 7, 2026

npx -y skills add ilya-kozyrev/claude-agent-hub --skill delegation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Delegation?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Delegation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ilya-kozyrev-delegation/badge)](https://www.skillsdirectory.com/skills/ilya-kozyrev-delegation)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: delegation
description: Show or change the delegation level 0-5 (0 - do everything yourself, subagents blocked by a hook; 3 - the default; 5 - orchestrator). Invoked as /delegation, /delegation 3, /delegation global 4, /delegation clear. Needs the delegation dial switched on in the hub home's config.json.
argument-hint: "[N | global N | clear | try TYPE MODEL]"
---

# Delegation level

Run bundled commands with the host's shell tool. Resolve the plugin root from `PLUGIN_ROOT`,
`CLAUDE_PLUGIN_ROOT`, or this skill's installed path; use `<plugin-root>/bin/<tool>` when PATH is missing
or shadowed. Session identity comes from the current host; use `self` where supported.

The level sets how much work this session hands to subagents; which model and effort they run at is decided by
your subagent rules (`AGENT_HUB_EFFORT_RULES`). The plugin's hooks inject the level's policy into the context at
session start and whenever the level changes; at level 0 a trusted hook denies the host's subagent-spawn tools.

Parse the user's arguments and run exactly one command (the plugin's `bin/` is on PATH):

| Arguments | Command |
|---|---|
| none | `delegation show` |
| `N` (0-5) | `delegation set N` — this session only |
| `global N` | `delegation set N --global` — every session without its own level |
| `clear` | `delegation clear` — back to the global level |
| `try <type> [<model>]` | `delegation try <type> [<model>]` — what the rules would say about such a native subagent call (no model: the definition's or inherited) |

The output holds the effective level and its policy. Work by it from this turn on: the command prints it exactly so
that a change applies now, not from the next message.

Answer in one or two lines: the effective level, where it comes from (session / global / default), and what it means
in practice. If the output says the dial is off, say so and name the setting (`"AGENT_HUB_DELEGATION": "on"` in the
hub home's `config.json`). On a non-zero exit show the error and do not change the level any other way.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.