Skip to content
Back to skills

Project Os Start

ASecurity

Start or onboard a Project OS workspace in Codex; use for the initial PM session, not implementation.

  • 63 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agents

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add ferhatcore/claude-codex-project-os --skill project-os-start --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Project Os Start?

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

Security grade badge for Project Os Start
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ferhatcore-project-os-start/badge)](https://www.skillsdirectory.com/skills/ferhatcore-project-os-start)

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: project-os-start
description: Start or onboard a Project OS workspace in Codex; use for the initial PM session, not implementation.
---

# project-os-start

Read AGENTS.md, START.md and .project-os.json from the workspace root. Follow the bootstrap procedure.
Inspect the board, decisions, pending questions and repository manifests. Do not read secret values or implement product code during onboarding.
Report actual native agent/tool availability and effective model settings; a template file does not prove a tool ran.
Reuse known user decisions. Record only genuine scope and permission references. Propose the first task and stop at any missing authority.
The main session is the PM. Use project_os_pm only for a bounded delegated planning brief, not a recursive PM loop.

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.

View all in ai-agents →

Comments

Loading comments…

Newsletter

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