self-execute

A way for an agent to run another task in the background while the current chat stays responsive. The result can appear in the conversation when the background task finishes.

In plain words
What is it for?
Running background research or other agent work, tracking its progress, and receiving the result in the same conversation.
Why use it?
It avoids making the user wait in an active chat while a longer task runs.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/abilityai/trinity/self-execute
Clone the repo
git clone --depth 1 https://github.com/Abilityai/trinity
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 793 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00793
Opus 5 $0.00000 $0.00396
Sonnet 5 $0.00000 $0.00159
Haiku 4.5 $0.00000 $0.00079

Measured 2d ago against content hash 32304ba17c94, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self-execute scanned grade A with 0 findings 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/user-docs/agents/self-execute.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Execute (Background Tasks)

Allow an agent to run a background task on itself while keeping the chat responsive. The agent tells the user "I'm working on that in the background" and the result appears when ready.

How It Works

  1. Agent calls chat_with_agent targeting itself with parallel=true.
  2. Trinity creates a background execution tracked as a SELF_TASK activity.
  3. The chat session stays responsive.
  4. When complete, the result optionally injects into the chat.
Agent (in chat) → "Let me research that in the background"
       │
       ▼
MCP chat_with_agent(self, inject_result=true)
       │
       ▼
Background execution starts → Activity panel shows progress
       │
       ▼
Execution completes → Result appears in chat (collapsed)

For Agents

MCP Tool Usage

mcp__trinity__chat_with_agent({
  agent_name: "my-agent",      // Same as calling agent
  message: "Research the top 5 competitors",
  parallel: true,              // Required for background execution
  async: true,                 // Returns immediately
  inject_result: true,         // Insert result into chat when done
  chat_session_id: "session-abc-123"  // Current session ID
})

The call returns immediately with an execution_id. The result appears in chat when the task completes.

REST API

POST /api/agents/my-agent/task

Request:

{
  "message": "Research competitor pricing",
  "async_mode": true,
  "inject_result": true,
  "chat_session_id": "session-abc-123"
}

Activity Tracking

Self-tasks appear in the activity panel with:

  • Activity type: self_task
  • Triggered by: self_task
  • Agent name: The agent running the background work

WebSocket Events

Task started:

{
  "type": "agent_activity",
  "activity_type": "self_task",
  "activity_state": "started",
  "action": "Background task: Research competitor...",
  "details": {
    "execution_id": "exec-123",
    "inject_result": true
  }
}

Task completed:

{
  "type": "agent_activity",
  "activity_type": "self_task",
  "activity_state": "completed",
  "details": {
    "cost_usd": 0.05,
    "execution_time_ms": 45000,
    "result_injected": true
  }
}

Read the full file on GitHub · 126 lines

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. 2d ago First seen · 126 lines · 0 tokens per session scan A 32304ba17c94

Subscribe to this mod's changes

self-execute is an agent published in the GitHub repository Abilityai/trinity (496 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 793 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens