Click on "Install 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., "@deleg8 spawn 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.
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.
Component | Purpose |
MCP server |
|
Hook |
|
Skill |
|
Related MCP server: cc-agent
cc --plugin-dir ~/projects/deleg8Or install from the project:
cd ~/projects/deleg8
cc --plugin-dir .Bun ≥ 1.1.0 (brew install bun or curl -fsSL https://bun.sh/install | bash)
omp on PATH (or set OMP_BIN in settings)
Dependencies installed: bun install
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 |
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.
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 |
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 lock
exclusive_release(pattern) — release an exclusive command lock
msg(text) — send IRC message back to orchestrator
task_create(label, note?) — create sub-task visible to orchestrator
task_update(task_id, status?, note?) — update sub-task status
The PreToolUse hook on task evaluates every subagent spawn:
Allows: explore subagents (read-only scouting), tasks with descriptive role fields
Blocks: Bare task("do X") calls, unnamed/generic subagents
Blocked message: "Bare task() is banned. Use deleg8: spawn(agent_id='descriptive-name', initial_prompt='...')"
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
Agent-native collaboration network: orchestrate a team of long-running agents from any MCP client.
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/emmahyde/deleg8'
If you have feedback or need assistance with the MCP directory API, please join our Discord server