100+ curated SOUL.md identity files for AI agents. Organized by role, industry, organization type, use case, and fleet. Every soul includes governance sections covering boundaries, domain knowledge, and harm avoidance.
# Generate from a tier template
$ npx hackmyagent harden-soul --template agentic
# Or copy a role-specific soul
$ curl -sO https://raw.githubusercontent.com/
opena2a-org/awesome-agent-souls/main/
souls/by-role/security-engineer.md
# Rename to SOUL.md in your project root
$ mv security-engineer.md SOUL.md
# Scan for governance coverage
$ npx hackmyagent scan-soulPlace SOUL.md in your project root -- the same directory as package.json, go.mod, or Cargo.toml. AI coding tools discover it automatically, just like .editorconfig for code formatting.
my-project/
SOUL.md # agent identity (who it is)
CLAUDE.md # tool-specific (optional)
AGENTS.md # tool-specific (optional)
package.json
src/| Tool | Native File | How to Use SOUL.md |
|---|---|---|
| Claude Code | CLAUDE.md | Reference SOUL.md from CLAUDE.md |
| Cursor | .cursorrules | Reference SOUL.md from .cursorrules |
| GitHub Copilot | copilot-instructions.md | Reference SOUL.md from instructions |
| Windsurf | .windsurfrules | Reference SOUL.md from rules file |
| Cline | .clinerules | Reference SOUL.md from rules file |
Souls are organized across five dimensions so you can find the right starting point for your agent.
Souls for specific professional roles: security engineer, DevOps specialist, data scientist, frontend architect, technical writer, and more.
Industry-specific governance with compliance requirements: healthcare (HIPAA), finance (SOX/PCI), government, education, and more.
Governance tuned for different org structures: startups, enterprises, open-source projects, consultancies, agencies, and more.
Task-specific souls for common workflows: code review, incident response, documentation, migration, testing, and security audit.
Coordinated multi-agent configurations where souls reference each other for delegation, escalation, and shared governance.
Start from a tier template that matches your agent's capability level. Each template pre-fills the governance domains relevant to that tier.
For agents that answer questions and generate text. No tool access. Covers trust hierarchy, honesty, and data handling.
For agents that call APIs, read files, or execute commands. Adds capability boundaries and injection hardening.
For autonomous agents that plan and execute multi-step workflows. Adds agentic safety and human oversight.
For fleet deployments where agents delegate to and coordinate with other agents. Full coverage across all nine domains.
Pick a template, customize it for your use case, and scan it for governance coverage.