Gitagent create-agent

Creates and configures agent.yaml files, writes SOUL.md personality definitions, and sets up agent directory structures with skills, tools, and knowledge. Use when the user wants to configure an agent, create agent.yaml, write SOUL.md, set up agent directory structure, or customize agent settings.

install

source · Clone the upstream repo

git clone https://github.com/open-gitagent/gitagent

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/open-gitagent/gitagent "$T" && mkdir -p ~/.claude/skills && cp -r "$T/examples/gitagent-helper/skills/create-agent" ~/.claude/skills/open-gitagent-gitagent-create-agent && rm -rf "$T"

manifest: examples/gitagent-helper/skills/create-agent/SKILL.md

source content

Create & Configure Agents

Quick Start

Create directory structure:
```
mkdir -p my-agent/skills
```
Write
```
agent.yaml
```
with required fields (see below)
Create
```
SOUL.md
```
with agent identity
Add skills, tools, and knowledge as needed
Validate:
```
gitagent validate -d ./my-agent
```

agent.yaml Reference

Required Fields

spec_version: "0.1.0"
name: my-agent          # Unique identifier
version: 1.0.0          # Semantic version
description: What this agent does

Model Configuration

model:
  preferred: claude-sonnet-4-5-20250929
  fallback:
    - claude-haiku-4-5-20251001
  constraints:
    temperature: 0.2     # 0.0 - 1.0
    max_tokens: 4096
    top_p: 0.9

Skills & Tools

skills:
  - code-review          # Must match directory name in skills/
  - security-audit

tools:
  - lint-check           # Must match filename in tools/ (without .yaml)

Runtime

runtime:
  max_turns: 20          # Max conversation turns
  timeout: 120           # Seconds

Sub-Agents

agents:
  reviewer:
    description: Reviews code quality
    delegation:
      mode: auto
      triggers:
        - "review this"

Writing a Good SOUL.md

A SOUL.md should have these sections:

Core Identity — Who is this agent? One clear sentence.
Communication Style — How does it talk? (direct, friendly, formal, etc.)
Values & Principles — What does it prioritize?
Domain Expertise — What does it know?
Collaboration Style — How does it work with the user?

Writing RULES.md

Structure as:

Must Always — Non-negotiable behaviors
Must Never — Hard boundaries
Output Constraints — Formatting rules
Interaction Boundaries — Scope limits

Adding Skills

Create

skills/<name>/SKILL.md

---
name: my-skill
description: What this skill does
license: MIT
allowed-tools: Read Edit Grep
metadata:
  version: "1.0.0"
---

# Instructions
[Detailed instructions for using this skill]

Adding Tools

Create

tools/<name>.yaml

name: my-tool
description: What this tool does
input_schema:
  type: object
  properties:
    query:
      type: string
      description: Search query
  required:
    - query

Adding Knowledge

Create

knowledge/index.yaml

documents:
  - path: reference.md
    always_load: true    # Include in system prompt
  - path: appendix.md
    always_load: false   # Available on demand