Skip to content
Back to skills

Contextos Workspace

ASecurity

Run Context OS continuity and lifecycle workflows in a user-selected Context OS workspace. Use when asked to inspect, set up, update, or close a Context OS session.

  • 29 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added September 20, 2026
ai-agents

Security analysis

A100/100

Scanned September 20, 2026

npx -y skills add conorbronsdon/agent-context-os --skill contextos-workspace --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Contextos Workspace?

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

Security grade badge for Contextos Workspace
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/conorbronsdon-contextos-workspace/badge)](https://www.skillsdirectory.com/skills/conorbronsdon-contextos-workspace)

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: contextos-workspace
description: Run Context OS continuity and lifecycle workflows in a user-selected Context OS workspace. Use when asked to inspect, set up, update, or close a Context OS session.
license: MIT
---

# Context OS workspace companion

1. Identify the user's intended Context OS workspace. Ask for its path if it is
   not explicit or unambiguous. Never use the plugin installation/cache as a
   workspace, and never create a workspace or import context implicitly.
2. Verify the selected root contains `AGENTS.md`, `ROUTING.md`,
   `scripts/contextos.sh`, and `.agents/skills/`. If not, stop and explain the
   repository-native setup in the bundled `docs/codex-onboarding.md` (relative
   to the plugin root, two directories above this file).
3. Read that workspace's `AGENTS.md`, `ROUTING.md`, and
   `docs/safety-contract.md` completely. Use that workspace as the working
   directory. Do not mix installed-plugin code with another workspace's state.
4. For the operation the user requested, read its canonical
   `.agents/skills/context-setup/SKILL.md`, `context-start/SKILL.md`,
   `context-update/SKILL.md`, or `context-end/SKILL.md` in the selected workspace.
   Follow that file; do not substitute a plugin-local copy or infer an operation
   that would expand the request.
5. Start is read-only. Setup, update and end require a displayed proposal and
   explicit approval of its exact digest before apply. Never write lifecycle
   state directly, install hooks, or commit/push implicitly. Report receipts
   and verification limits. Plugin installation grants no extra authority.

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.