deleg8
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@deleg8spawn agent "code-reviewer" to review the auth module and report findings"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
deleg8 — Persistent omp Subagents Plugin
Makes oh-my-pi persistent subagents the default delegation mechanism in Claude Code.
Bundles the deleg8 MCP server, an enforcement hook, and a skill that teaches the
orchestrator when and how to use persistent subagents instead of bare task() calls.
Components
Component | Purpose |
MCP server |
|
Hook |
|
Skill |
|
Related MCP server: claude-code-mcp
Install
cc --plugin-dir ~/projects/deleg8Or install from the project:
cd ~/projects/deleg8
cc --plugin-dir .Prerequisites
Bun ≥ 1.1.0 (
brew install bunorcurl -fsSL https://bun.sh/install | bash)omp on PATH (or set
OMP_BINin settings)Dependencies installed:
bun install
Configuration
Create .claude/deleg8.local.md in your project (or ~/.claude/ for global):
---
omp_bin: /opt/homebrew/bin/omp
default_model:
provider: deepseek
modelId: deepseek-v4-pro
---Field | Default | Description |
|
| Path to omp binary |
|
| Model provider for deleg8 agents |
|
| Model ID for deleg8 agents |
Usage
Once installed, the skill loads on phrases like "fan out", "parallelize", "waves",
"delegate", "subagents", or when the orchestrator considers spawning a bare task().
Basic fan-out:
spawn(agent_id="compiler", initial_prompt="Build the auth module")
spawn(agent_id="tester", initial_prompt="Write tests for auth", background=true)Multi-turn refinement:
spawn(agent_id="impl", initial_prompt="Implement payment processor")
→ review output
send(agent_id="impl", message="Add retry logic for timeout failures")Full workflow patterns: see the deleg8 skill output or references/when-to-use.md
in the skill directory.
MCP Tools
Tool | Purpose |
| Launch a new omp agent with optional initial prompt |
| Send follow-up to existing agent (auto-resumes idle agents) |
| Read buffered frames — digest/summary/raw with jq projection |
| Check one agent's state (running/idle/dead) |
| Snapshot of all registered agents |
| Abort, terminate, remove from registry |
| Drop dead/idle agents from registry |
Spawn Parameters (New in v0.2)
The spawn tool now supports these enforcement parameters:
Parameter | Type | Description |
|
| Regex patterns over tool commands. Prompt-level constraints + real-time violation monitoring. Note: omp runs Bash/Read/Edit internally — deleg8 cannot intercept before execution. |
|
| Glob patterns limiting write scope. Same injection + monitoring pattern. Same architectural constraint as denylist. |
|
| Shared context block every spawned agent receives before its prompt. |
|
| If the primary model fails to apply (e.g. budget exceeded), try this one. |
|
| Auto-reap idle agents after N ms of inactivity (registry-level, 0 = off). |
|
| Auto-reap dead agents after N ms (registry-level, 0 = off). |
|
| Cooperative agent protocol — agents acquire/release locks via host tools. Voluntary: agents must call |
Usage example:
spawn(
agent_id="builder",
initial_prompt="Compile the .csproj",
denylist=["git (stash|checkout)", "dotnet test"],
own=["src/**", "*.csproj"],
preamble="Friflo: Tags getter returns a struct copy — use AddTag/RemoveTag",
idle_ttl=300_000,
exclusive=[{pattern: "dotnet build", wait: true}]
)Host tools available to agents:
exclusive_acquire(pattern)— acquire an exclusive command lockexclusive_release(pattern)— release an exclusive command lockmsg(text)— send IRC message back to orchestratortask_create(label, note?)— create sub-task visible to orchestratortask_update(task_id, status?, note?)— update sub-task status
Enforcement Hook
The PreToolUse hook on task evaluates every subagent spawn:
Allows:
exploresubagents (read-only scouting), tasks with descriptiverolefieldsBlocks: Bare
task("do X")calls, unnamed/generic subagentsBlocked message: "Bare task() is banned. Use deleg8: spawn(agent_id='descriptive-name', initial_prompt='...')"
This server cannot be deployed
Maintenance
Related MCP Connectors
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
One MCP endpoint for Claude, GPT & Gemini: 100+ tools + no-code connectors + agent workers.
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
Related MCP Servers
- AlicenseAqualityCmaintenanceWraps the Claude Agent SDK as MCP servers, letting you spawn multiple specialized Claude Code agents — each with its own model, tools, system prompt, and personality — from any MCP client.581 npm21ISC
- AlicenseAqualityDmaintenanceWraps Claude Code as tools for MCP clients, enabling autonomous coding tasks via a 4-tool lifecycle with session management, async polling, and permission controls.443 npm20MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that lets any MCP-capable agent spawn and drive Claude Code sessions — effectively turning Claude Code into an orchestratable sub-agent fleet.72 npmMIT
- FlicenseNot gradedqualityBmaintenanceEnables MCP hosts like Claude Code and Codex to spawn, manage, and interact with persistent, reusable Pi coding-agent sessions, supporting task dispatch, status checks, and session lifecycle control.2 npm-