# Task Graph

> Use this tool when you need to manage complex agent workflows with structured phases and task dependencies. It solves problems of coordination, quality control, and cost tracking in multi-agent environments, providing a robust framework for solo, swarm, relay, and hierarchical agent coordination patterns. With inputs of task definitions and dependencies, and outputs of tracked costs, times, and workflow status, Task Graph is ideal for use cases requiring reliable and efficient workflow management.

Canonical page: https://skillsregistry.net/skills/oortonaut-task-graph  
JSON: https://api.skillsregistry.net/v1/skills/oortonaut-task-graph

## Description

Task Graph provides coordination primitives for complex agent workflows. It supports structured phases (explore, implement, review, test), DAG-based task dependencies with cycle detection, quality gates for enforcing transition requirements, atomic task claiming with tag-based routing, advisory file locks, and built-in cost and time tracking. Multiple pre-built workflow topologies are included for solo, swarm, relay, and hierarchical agent coordination patterns, all backed by SQLite with WAL mode.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/oortonaut-task-graph)
- **Repository:** <https://github.com/oortonaut/task-graph-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "oortonaut-task-graph"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/oortonaut-task-graph` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/oortonaut-task-graph/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt