Atlas / Skills / jeremylongshore / Cursor Team Setup

Cursor Team SetupSAFE

skills/jeremylongshore/cursor-team-setup

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Verdict
SAFE
Grade
B
Trust score
89 /100
Version
1.19.0
Hosts
2 documented
License
MIT
Stars
2,823
01

Overview

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Read from source at commit 4f83675ca38aOBSERVED · 2026-10-08
02

Host compatibility

What the documentation claims. We have not run a compatibility test.

HostStatusNotes
claude-codementioned
cursormentioned
03

What it tells the agent

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: cursor-team-setup
description: 'Set up Cursor for teams: plan selection, member management, shared rules,
  admin dashboard, and

  onboarding. Triggers on "cursor team", "cursor organization", "cursor business",
  "cursor enterprise setup",

  "cursor admin".

  '
allowed-tools: Read, Write, Edit, Bash(cmd:*)
version: 1.19.0
license: MIT
author: Jeremy Longshore <[email protected]>
tags:
- saas
- cursor
- cursor-team
compatibility: Designed for Claude Code
---
# Cursor Team Setup

## Overview

Onboard a Cursor team with approved identity, privacy, rules, repository access, and support ownership before broad AI-assisted development begins.

## Prerequisites

- A named tenant owner, identity source, approved plan, and data-use policy.
- Reviewed repository templates, ignore rules, and owner for onboarding/offboarding.

## Instructions

1. Pilot with a small group using SSO/SCIM or approved identity controls and least-privilege roles.
2. Publish reviewed shared rules and ignore files through source control, not untracked local instructions.
3. Train members on context boundaries, diff review, testing, escalation, and account recovery.
4. Review access, policy enforcement, and adoption evidence before expanding the rollout.

## Output

- A governed team rollout with ownership, onboarding evidence, and offboarding/access-review controls.

## Error Handling

| Condition | Safe response |
|---|---|
| A user receives excess access | Correct the identity/group mapping and record the access review. |
| Shared rules conflict with a repository | Use a reviewed scoped override; do not disable all team rules. |
| Privacy control cannot be verified | Hold expansion and escalate to the tenant/security owner. |

## Examples

Pilot one engineering group, verify SSO and Privacy Mode policy, open a template repository with reviewed rules, and collect a redacted onboarding receipt. Expand only after a new user and a departed user both pass the expected provisioning/deprovisioning checks.

Configure Cursor for teams and organizations. Covers plan selection, member management, shared configurations, Privacy Mode enforcement, and onboarding workflows.

## Plan Comparison

| Feature | Pro ($20/user/mo) | Business ($40/user/mo) | Enterprise (custom) |
|---------|-------------------|----------------------|---------------------|
| Fast requests | 500/mo | 500/mo/seat | Custom |
| Tab completion | Unlimited | Unlimited | Unlimited |
| Privacy Mode | Optional | Enforced by default | Enforced |
| SSO (SAML/OIDC) | No | Yes | Yes |
| SCIM provisioning | No | No | Yes |
| Admin dashboard | No | Yes | Yes |
| Usage analytics | No | Yes | Yes (advanced) |
| Priority support | No | No | Yes |
| Dedicated account mgr | No | No | Yes |
| SLA | No | No | Yes |
| SOC 2 report access | No | Request | Included |

## Team Setup Workflow

### Step 1: Create Organization

1. Go to [cursor.com/settings](https://cursor.com/settings)
2. Click "Create Team" or "Create Organization"
3. Enter organization name and billing details
4. Select plan (Business or Enterprise)

### Step 2: Configure Team Settings

**Admin Dashboard** (Business/Enterprise):

```
Dashboard Sections:
├── Members         → Invite, remove, assign roles
├── Usage           → Request counts, model usage, costs
├── Privacy         → Privacy Mode enforcement
├── Models          → Restrict available models
├── SSO             → SAML/OIDC configuration
└── Billing         → Plan, invoices, seat management
```

### Step 3: Invite Members

```
Methods:
1. Email invitation: Admin dashboard > Members > Invite by email
2. Domain auto-join: Allow anyone with @company.com to join
3. SSO provisioning: Users auto-join when they sign in via SSO
4. SCIM (Enterprise): Automatic sync from identity provider
```

**Roles:**

| Role | Permissions |
|------|------------|
| Owner | Full admin, billing, delete org |
| Admin | Manage members, settings, SSO |
| Member | Use Cursor with team settings |

### Step 4: Enforce Privacy Mode

For Business and Enterprise plans:

1. Admin Dashboard > Privacy
2. Enable "Enforce Privacy Mode for all members"
3. Team members cannot disable Privacy Mode locally
4. Verification: each client pings server every 5 minutes to check enforcement

Privacy Mode guarantees:

- Zero data retention at model providers (OpenAI, Anthropic)
- No code used for model training
- No plaintext code stored on Cursor servers

### Step 5: Configure Model Access

Admin Dashboard > Models:

```
Available models (toggle on/off per team):
  ✅ GPT-4o
  ✅ Claude Sonnet
  ✅ Auto mode
  ❌ Claude Opus (restricted to save costs)
  ❌ o1 (restricted to save costs)
  ✅ cursor-small
```

Restricting models helps control costs -- premium models consume fast requests faster.

## Shared Configuration (via Git)

Team settings that belong in the project repository:

### Project Rules

```
.cursor/rules/
├── project.mdc            # Stack, conventions (alwaysApply: true)
├── security.mdc           # Security constraints (alwaysApply: true)
├── code-style.mdc         # Naming, formatting (alwaysApply: true)
├── typescript.mdc         # TS patterns (glob: **/*.ts)
├── react.mdc              # React patterns (glob: **/*.tsx)
└── testing.mdc            # Test conventions (glob: **/*.test.ts)
```

Commit these to git. Every team member gets the same AI behavior.

### Ignore Files

```
.cursorignore              # Shared exclusions (commit to git)
.cursorindexingignore      # Shared indexing exclusions (commit to git)
```

### Machine-Local Settings

These are NOT shared via git:

- `settings.json` (editor preferences -- personal choice)
- `keybindings.json` (keyboard shortcuts -- personal choice)
- API keys (stored in Cursor's local settings database)

## Onboarding New Team Members

### Onboarding Checklist

```markdown
## New Team Member: Cursor Setup (20 minutes)

### Account
[ ] Download Cursor from cursor.com/download
[ ] Sign in with @company.com email
[ ] Verify Business plan ac
04

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 4f83675ca38afull audit observations/trust-audit/skill/jeremylongshore__cursor-team-setup.json · Report an issue / request a re-scan
05

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-084f83675ca38aSAFEB89first audit
06

Questions

What does the Cursor Team Setup skill do?

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

Is Cursor Team Setup safe to install?

The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.

What can Cursor Team Setup access on my machine?

The audit observed no filesystem, network or shell use at all in its source.

Which assistants does Cursor Team Setup work with?

Its documentation mentions claude-code and cursor. That is what the text claims, not a compatibility test we ran.

How current is this page?

The grade is for one exact copy of the source (4f83675ca38a), read on 2026-10-08. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement