delegation
Skill5 starsChanged 38 days agoMITView on GitHub
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.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- jean1880/nuvek-agent-configtheir own version, first seen Nov 1, 2026
- PanPanFR/oh-my-openkilotheir own version, first seen Oct 22, 2026
- ihyonoo/skillstheir own version, first seen Oct 20, 2026
- godilley/agent-tierstheir own version, first seen Oct 20, 2026
- QuixiAI/Hexistheir own version, first seen Oct 8, 2026
- QuixiAI/agi-memorytheir own version, first seen Oct 8, 2026
Other versions12 projects use a version of this.
Word for word · 1
- ilya-kozyrev/delamain★ 5100% same
Edited · 0
None found.
Wrote their own version · 11
- nearai/ironclaw★ 13ksame name
- QuixiAI/agi-memory★ 623same name
- QuixiAI/Hexis★ 623same name
- manager-dot-dev/manager-skills★ 114same name
- PanPanFR/oh-my-openkilo★ 9same name
- godilley/agent-tiers★ 1same name
- Onkarj012/skills★ 1same name
- zinan92/skills-repo★ 1same name
- ihyonoo/skills★ 0same name
- jean1880/nuvek-agent-config★ 0same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- agy-reviewSkill
- handoffSkill
- hubSkill
- progress-reportSkill
- setupSkill
- statusSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 9
Run bundled commands with the host's shell tool.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.