Multi-agent workspace awareness and safety system. Discovers, lists, switches, and validates projects using environment-based naming to prevent agent drift.
Scanned 9/19/2026
Install to Claude Code
Skills Directorynpx -y skills add rondoflow/rondoflow --skill unspecified-workspace-anchor-skill --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Unspecified Workspace Anchor Skill?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/rondoflow-unspecified-workspace-anchor-skill)More formats (shields.io, HTML) on the badges page.
---
name: unspecified-workspace-anchor-skill
description: "Multi-agent workspace awareness and safety system. Discovers, lists, switches, and validates projects using environment-based naming to prevent agent drift."
category: "AI & Agents"
author: community
version: "1.0.0"
icon: bot
---
# ⚓ Workspace Anchor
Multi-agent workspace awareness and safety system. Discovers, lists, switches, and validates projects using environment-based naming to prevent agent drift.
## 🤖 Agent Instruction (CRITICAL)
Before using this skill, you MUST identify the correct absolute paths for the user's environment. Use `exec` to find `.project-lock` files if paths are ambiguous.
## 📝 CLI Commands
- `discover`: Find all `.project-lock` files.
- `list`: Show formatted list of anchors.
- `create <path>`: Initialize a new anchor.
- `switch <name>`: Change active context.
- `validate <path>`: Check if path is within current anchor.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
