Skip to content
Back to skills

Dayan Agent Factory

ASecurity

Compile an approved agent design into a portable, inspectable agent package with bounded tools, fixtures, and handoff instructions.

  • 4 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 9, 2026
ai-agents

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned October 9, 2026

npx -y skills add Kosmoray/dayan-agent-skills --skill dayan-agent-factory --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Dayan Agent Factory?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Dayan Agent Factory
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kosmoray-dayan-agent-factory/badge)](https://www.skillsdirectory.com/skills/kosmoray-dayan-agent-factory)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: dayan-agent-factory
description: Compile an approved agent design into a portable, inspectable agent package with bounded tools, fixtures, and handoff instructions.
---

# Dayan Agent Factory

Use this Skill only after an agent design has a stable objective, role boundary, tool policy, output contract, and evaluation plan.

## Package

Create one directory containing:

- `AGENT.md`: role, objective, inputs, output, exclusions, and stop conditions;
- `tool-policy.json`: allowlisted capabilities and forbidden external effects;
- `output-schema.json`: machine-readable result contract;
- `examples/accepted.json` and `examples/rejected.json`;
- `EVALUATION.md`: tests, human takeover, cost/latency limits, and unresolved risks;
- `README.md`: install, run, verify, and remove instructions.

Reject packages with broad filesystem access, hidden state ownership, unbounded retries, self-approval of consequential actions, or no rejected fixture. Generate the package; do not install or deploy it without separate authorization.

Files in this skill

  • PROVENANCE.md163 B
  • SANITIZATION.md146 B
  • SKILL.md1 KB
  • examples/starter.json471 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.