OrgComputers
A shared workspace for your AI agents: projects, context and tools in one place, so the next agent starts where the last one stopped.
- What
- A shared workspace for your AI agents: projects, context and tools in one place, so the next agent starts where the last one stopped.
- Cost
- Free
- Needs
- Pinned version: install the code at commit d6589b3259ae007046ed9914d9070a9571094f92 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me.
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
OrgComputers is a shared workspace for your AI agents. Your team and every agent it uses share one place for projects, context and tools: repos and workstreams each with their own context, plus sessions, docs, code, notes and links, and the APIs, integrations and databases agents can call. Nothing is copied between tools, and nothing stays on one laptop. From Cursor, Claude Code or Codex, an agent pulls what the team already decided before changing code, and every answer cites where it came from. The workspace links your stack through one MCP server (GitHub, Linear, Slack, Notion, Jira, Confluence, PagerDuty, Google Drive and internal systems) and merges entities across systems, so one service known by five names in four tools becomes a single record with its PRs, tickets, incidents and decisions attached. Setup is one command per agent: sign in with Google, generate an API key from the dashboard (Connect, admin only), then install the Handoff plugin. Every answer points back to its source. OrgComputers does not replace GitHub, Linear or Slack, it links them. Honest caveats: this is a young third-party SaaS and no pricing page is published as of 2026-10-04, so the cost of running a team workspace is unknown. You are handing your team's code context, docs and integrations to a third-party service, so review their security posture before connecting production systems.
Version:
Quick answer
OrgComputers is a free Muse skill that gives your team and its AI agents one shared workspace for projects, context, and tools, so the next agent starts where the last one stopped. From Cursor, Claude Code, or Codex, an agent pulls what the team already decided before changing code, and every answer cites its source.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit d6589b3Pinned version: install the code at commit d6589b3259ae007046ed9914d9070a9571094f92 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. Give your agents a shared memory with OrgComputers. 1. Sign in with Google at orgcomputers.com and open the dashboard at app.orgcomputers.com. 2. Generate an API key: Connect, then Generate API key (admins only; the key is shown once, so store it somewhere durable). 3. Connect your agent. In Claude Code: run `claude plugin marketplace add kshitijg30/Handoff_plugins`, then `claude plugin install handoff`, start a session and run `/handoff:org-add my-org hk_your_api_key`. In Cursor or Codex: run `curl -fsSL https://raw.githubusercontent.com/kshitijg30/Handoff_plugins/d6589b3259ae007046ed9914d9070a9571094f92/install.sh | bash -s -- cursor` (swap `cursor` for `codex`), reload the editor, then `/handoff:org-add` in Cursor or `/org-add` in Codex. 4. Work as usual: the session shows up in the workspace for your whole team, and the next agent starts with what the last one found. The key is stored in `~/.handoff/orgs.json` and takes effect immediately. Never bake a key into a committed file.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
- It can run commands on your Muse’s computer.
- It works with an API key or a token that you provide.
What the scan found — excerpts from the install prompt
- runs commands — 3. Connect your agent. In Claude Code: run `claude plugin marketplace add kshitijg30/Handoff_plugins`, then `c · 3. Branchez votre agent. Dans Claude Code : lancez `claude plugin marketplace add kshitijg30/Handoff_plugins`,
- uses API keys or tokens — 2. Generate an API key: Connect, then Generate API key (admins only; the key is shown once, so store it somewh · 3. Connect your agent. In Claude Code: run `claude plugin marketplace add kshitijg30/Handoff_plugins`, then `c · 2. Générez une clé API : Connect, puis Generate API key (admins seulement ; la clé n'est affichée qu'une fois,
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- d6589b3 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: registry.npmjs.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : runs commands · uses API keys or tokens
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.