Agent skill

Windsurf Enterprise Rbac

by jeremylongshore in jeremylongshore/tons-of-skills-marketplace

Analyze and design Devin Desktop (formerly Windsurf) enterprise SSO, SCIM, RBAC, and team controls.

MITAuto-check passedBackend & APIs

Install Windsurf Enterprise Rbac

skills CLI
$ npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-enterprise-rbac -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jeremylongshore/tons-of-skills-marketplace windsurf-enterprise-rbac --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/.curated/windsurf-enterprise-rbac .claude/skills/windsurf-enterprise-rbac && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
windsurf-enterprise-rbac
GitHub stars
2.8k
Token cost
~2k tokens
SKILL.md length
962 words
Files
2 (incl. references)
Skills in repo
3,342
Repo updated
First seen
Licence
MIT

At a glance

Analyze and design Devin Desktop (formerly Windsurf) enterprise SSO, SCIM, RBAC, and team controls.

  • Works in 7 steps: Establish the administrative boundary → Design roles from documented permissions → Connect SSO and SCIM lifecycle → …
  • Defining least-privilege roles
  • SKILL.md covers Overview, Prerequisites, Authentication and Tool Use, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Windsurf Enterprise Rbac is an agent skill from jeremylongshore/tons-of-skills-marketplace. Analyze and design Devin Desktop (formerly Windsurf) enterprise SSO, SCIM, RBAC, and team controls. Use when defining least-privilege roles, identity lifecycle, model or terminal policy, MCP access, or organization-wide rollout governance. Trigger with "Windsurf SSO", "Devin Desktop RBAC", "enterprise rollout", or "team permissions".

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/official-docs.md`). Compatibility notes: Designed for Claude Code

It sits in Backend & APIs, covering Authorization and RBAC and Authentication. It works with Model Context Protocol. The repository describes itself as: Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com. The licence is MIT.

When your agent uses it

  • Defining least-privilege roles
  • Identity lifecycle
  • Terminal policy
  • Organization-wide rollout governance

Example prompts

  • “Windsurf SSO”
  • “Devin Desktop RBAC”
  • “enterprise rollout”
  • “/windsurf-enterprise-rbac”

Requirements

  • Compatibility (from SKILL.md): Designed for Claude Code
  • Pre-approved tools (allowed-tools): Read, Write, Edit

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Establish the administrative boundary
  2. Design roles from documented permissions
  3. Connect SSO and SCIM lifecycle
  4. Configure team feature controls
  5. Separate product controls from external enforcement
  6. Pilot and verify
  7. Define recurring review

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Edit

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • docs.devin.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Designed for Claude Code

    From compatibility in the SKILL.md frontmatter.

Context cost

Windsurf Enterprise Rbac loads about 2k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 962 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 962 words, ~2,042 tokens.

Download SKILL.mdSave it as .claude/skills/windsurf-enterprise-rbac/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
windsurf-enterprise-rbac
description
Analyze and design Devin Desktop (formerly Windsurf) enterprise SSO, SCIM, RBAC, and team controls. Use when defining least-privilege roles, identity lifecycle, model or terminal policy, MCP access, or organization-wide rollout governance. Trigger with "Windsurf SSO", "Devin Desktop RBAC", "enterprise rollout", or "team permissions".
allowed-tools
Read, Write, Edit
compatibility
Designed for Claude Code
argument-hint
[organization, identity provider, and access-policy requirements]
version
1.12.0
license
MIT
author
Jeremy Longshore <jeremy@intentsolutions.io>
tags
saas, windsurf, enterprise, sso, rbac, admin

Devin Desktop Enterprise Access Control

Overview

Build an evidence-backed enterprise access model for Devin Desktop, the current name for Windsurf. RBAC is an Enterprise feature; verify plan eligibility and current control labels in the admin console before promising a capability.

Prerequisites

  • An Enterprise organization and an authenticated administrator
  • Named identity, security, billing, and developer-experience owners
  • The organization's identity lifecycle, least-privilege, and break-glass requirements
  • Current first-party documentation and contract terms for any mutable product claim

Authentication

Perform administrative changes only from a protected enterprise-admin session. Treat SAML metadata, SCIM tokens, service keys, recovery codes, cookies, and exported member data as secrets; keep values in approved identity or secret systems and place only redacted references in deliverables.

Tool Use

  • Use Read to inspect only the repository policy and configuration files needed for the access design.
  • Use Write only for a new access matrix or rollout artifact explicitly requested by the user.
  • Use Edit for bounded changes to existing policy documents, preserving unrelated work and all credential boundaries.

Instructions

Step 1: Establish the administrative boundary

Record the organization, administrator group, identity provider, affected teams, repositories, and environments. Use the Devin Desktop admin console under the team settings surface; do not invent SAML endpoints or API scopes from examples.

Step 2: Design roles from documented permissions

Devin Desktop provides default Admin and User roles and supports custom Enterprise roles. Start the User role with no administrative permissions, then grant only the documented actions required for the job.

Map needs against the current permission families:

  • Attribution and analytics read access
  • Team read, update, delete, and invite actions
  • Index read, create, update, delete, and management actions
  • SSO read and write actions
  • Service-key read, create, update, and delete actions
  • Billing read and write actions
  • Role read, create, update, and delete actions

Never copy a role name from this skill without checking the live permissions list. The product can add, rename, or split permissions.

Step 3: Connect SSO and SCIM lifecycle

Use SSO for authentication and SCIM for automated provisioning, deprovisioning, and group-to-team mapping where supported. Define:

  1. The IdP group that grants base access.
  2. The IdP groups that map to Devin Desktop teams.
  3. The role each team receives.
  4. The offboarding event and maximum revocation time.
  5. A tested break-glass path with a named owner and audit requirement.

Enable enforcement only after a pilot administrator and a non-administrator complete sign-in, role, and recovery tests.

Step 4: Configure team feature controls

Review each organization-level control in the current admin guide and record the chosen state, owner, and reason. Current control families include:

  • Model access by specific model or provider, plus the initial Cascade default
  • Maximum terminal auto-execution level: Disabled, Allowlist Only, Auto, or Turbo
  • Team terminal allowlists and denylists, with deny taking precedence
  • MCP availability and approved-server policy
  • App Deploys, conversation sharing, PR-review integration, and knowledge-base access

Prefer the lowest terminal level that supports the workflow. Review MCP servers as external capabilities because they may create or mutate resources outside Devin Desktop.

Step 5: Separate product controls from external enforcement

For every requirement, identify the authoritative enforcement point. Repository permissions, branch protection, identity-provider policy, secret management, deployment approval, and data-loss controls remain authoritative even when Devin Desktop provides a related toggle.

RequirementDevin Desktop controlExternal controlOwnerEvidence
Member lifecycleSCIM team mappingIdP group and termination workflowIdentityProvision/deprovision test
Model accessModel/provider filterApproved-model policySecurityAdmin export or screenshot
Terminal safetyMaximum level and listsRepository permissions and CIDevExAllowed/denied canary
MCP accessMCP toggle and allowlistVendor review and scoped credentialsPlatformServer inventory and test
Production deployApp Deploys toggleProtected deployment environmentSREApproval and rollback receipt
Show full SKILL.md (353 more words)Show less
Step 6: Pilot and verify

Test at least one user in every proposed role. Verify allowed and denied admin pages, team membership, analytics visibility, indexing controls, SSO recovery, SCIM deprovisioning, terminal policy, MCP policy, and any enabled sharing or deployment feature.

Stop rollout on unexpected privilege, failed deprovisioning, missing audit evidence, or a control whose behavior cannot be confirmed from the current console and documentation.

Step 7: Define recurring review

Set review owners and intervals for privileged roles, service keys, team membership, model/provider access, terminal lists, MCP allowlists, feature toggles, billing access, and break-glass accounts. Record changes as reviewable evidence rather than embedding secrets in the report.

Output

Deliver an access-control matrix, IdP-to-team mapping, role definitions, feature-control decisions, pilot evidence, offboarding test, break-glass procedure, exceptions, and recurring review schedule. Label every item as a Devin Desktop control, an external enforcement control, or an unverified contract-dependent claim.

Error Handling

IssueSafe response
A documented permission is absentStop and re-check the live Enterprise console and current first-party docs
SSO blocks all administratorsUse the pre-tested break-glass path, then repair IdP configuration before enforcement
SCIM leaves a terminated user activeDisable access directly, preserve evidence, and investigate the identity lifecycle
A role grants unexpected accessRemove the grant, compare the effective role, and rerun the denied-path test
An MCP or deploy control is ambiguousKeep it disabled until ownership, credential scope, and rollback are approved

Examples

For an engineering lead who needs team analytics but no billing or identity access, create a custom role with the current analytics-read permission only, assign it through the appropriate team, and prove both the allowed analytics view and denied billing, SSO, service-key, and role-management paths.

For automated offboarding, map an IdP group to the target Devin Desktop team through SCIM, remove a synthetic pilot identity from the IdP group, and record the observed revocation time without exposing the SCIM credential.

Resources

See references/official-docs.md for the maintained first-party source list.

Continue with windsurf-migration-deep-dive for staged adoption and windsurf-policy-guardrails for repository, terminal, MCP, and deployment enforcement.

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/.curated/windsurf-enterprise-rbac of jeremylongshore/tons-of-skills-marketplace.

  • SKILL.md
  • references/official-docs.md

Open the folder on GitHubat commit cfae287

Compare with similar skills

Windsurf Enterprise Rbac next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Windsurf Enterprise Rbac compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Windsurf Enterprise Rbac this skilljeremylongshore/tons-of-skills-marketplace2.8k—~2kAutomated safety check: PassMIT
Frontmcp Authoritiesagentfront/frontmcp146—~7.1kAutomated safety check: PassApache-2.0
Workosusenotra/notra260—~6.2kAutomated safety check: PassAGPL-3.0
Fastmcp Serverdavila7/claude-code-templates33k—~1.9kAutomated safety check: PassMIT
Supabase Development and Debuggingsupabase/agent-skills2.7k3 repos~3.6kAutomated safety check: PassMIT
Supabasecurvenote/curvenote1705 repos~2.2kAutomated safety check: PassCustom licence

Similar skills

  • Frontmcp Authorities

    agentfront/frontmcp

    A skill your agent uses when implementing authorization and access control for FrontMCP tools, resources, prompts, or skills, deciding who may invoke what.

    146 GitHub stars~7.1k tokensUpdated today
    Backend & APIsAuto-check passed
  • Workos

    usenotra/notra

    A skill your agent uses when the user asks for a WorkOS docs URL, term, or dashboard field (Sign-in endpoint, initiateloginuri, Redirect URI, WORKOS env vars), or is implementing, debugging, or…

    260 GitHub stars~6.2k tokensUpdated today
    Backend & APIsAuto-check passed
  • Fastmcp Server

    davila7/claude-code-templates

    Complete guide for building MCP servers with FastMCP 3.0 - tools, resources, authentication, providers, middleware, and deployment.

    33k GitHub stars~1.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Official

    General Supabase skill for database, auth, Edge Functions, Realtime and storage work, plus client libraries, migrations, security audits, debugging and reading logs.

    2.7k GitHub starsUsed in 3 repos~3.6k tokens
    Backend & APIsAuto-check passed
  • Supabase

    curvenote/curvenote

    A skill your agent uses when doing ANY task involving Supabase.

    170 GitHub starsUsed in 5 repos~2.2k tokens
    Backend & APIsAuto-check passed
  • Cognito

    itsmostafa/aws-agent-skills

    AWS Cognito user authentication and authorization service. An agent skill from itsmostafa/aws-agent-skills.

    1.2k GitHub starsUsed in 1 repo~2.3k tokens
    Backend & APIsAuto-check passed

More from jeremylongshore/tons-of-skills-marketplace

All 3,342 skills in this repo
  • Performing Security Code Review

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin.

    2.8k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check: notes
  • Adapting Transfer Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill automates the adaptation of pre-trained machine learning models using transfer learning techniques.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Agent Context Loader

    jeremylongshore/tons-of-skills-marketplace

    Execute proactive auto-loading: automatically detects and loads agents.md files.

    2.8k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Aggregating Performance Metrics

    jeremylongshore/tons-of-skills-marketplace

    Aggregate and centralize performance metrics from applications, systems, databases, caches, and services.

    2.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Analyzing Capacity Planning

    jeremylongshore/tons-of-skills-marketplace

    Execute this skill enables AI assistant to analyze capacity requirements and plan for future growth.

    2.8k GitHub stars~947 tokensUpdated today
    Auto-check passed
  • Analyzing Database Indexes

    jeremylongshore/tons-of-skills-marketplace

    Process use when you need to work with database indexing. An agent skill from jeremylongshore/tons-of-skills-marketplace.

    2.8k GitHub stars~2k tokensUpdated today
    Auto-check passed

Categories

Questions about Windsurf Enterprise Rbac

What does Windsurf Enterprise Rbac do?

Analyze and design Devin Desktop (formerly Windsurf) enterprise SSO, SCIM, RBAC, and team controls. Windsurf Enterprise Rbac is an agent skill from jeremylongshore/tons-of-skills-marketplace. Analyze and design Devin Desktop (formerly Windsurf) enterprise SSO, SCIM, RBAC, and team controls.

When should I use Windsurf Enterprise Rbac?

Windsurf Enterprise Rbac fits situations like: defining least-privilege roles; identity lifecycle; terminal policy; organization-wide rollout governance.

How do I install Windsurf Enterprise Rbac in Claude Code?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-enterprise-rbac -a claude-code`. Or copy the skill folder (skills/.curated/windsurf-enterprise-rbac in jeremylongshore/tons-of-skills-marketplace) into .claude/skills/windsurf-enterprise-rbac in your project. Claude Code loads it when a task matches its description.

How do I install Windsurf Enterprise Rbac in Codex?

Run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-enterprise-rbac -a codex`. Or copy the skill folder (skills/.curated/windsurf-enterprise-rbac in jeremylongshore/tons-of-skills-marketplace) into .agents/skills/windsurf-enterprise-rbac in your project. Codex loads it when a task matches its description.

Can I use Windsurf Enterprise Rbac in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-enterprise-rbac -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/windsurf-enterprise-rbac, .gemini/skills/windsurf-enterprise-rbac, .github/skills/windsurf-enterprise-rbac and .opencode/skills/windsurf-enterprise-rbac in your project.

What does Windsurf Enterprise Rbac need to run?

SKILL.md names no scripts, command-line tools or credentials: Windsurf Enterprise Rbac is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit. Compatibility (from SKILL.md): Designed for Claude Code.

Does Windsurf Enterprise Rbac access the network?

SKILL.md names 1 domain. As links in the text: docs.devin.ai. This is read from the text; nothing was executed.

Is Windsurf Enterprise Rbac safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Windsurf Enterprise Rbac use?

Windsurf Enterprise Rbac is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Windsurf Enterprise Rbac use?

About 2k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 104 tokens, read only when the agent opens those files.

What are the alternatives to Windsurf Enterprise Rbac?

Skills that share tags, products or a category with Windsurf Enterprise Rbac: Frontmcp Authorities (agentfront/frontmcp, 146 stars), Workos (usenotra/notra, 260 stars), Fastmcp Server (davila7/claude-code-templates, 33k stars) and Supabase Development and Debugging (supabase/agent-skills, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Windsurf Enterprise Rbac?

jeremylongshore (a GitHub user) maintains it in jeremylongshore/tons-of-skills-marketplace, which has 2,827 GitHub stars. The repository holds 3,342 skills in this directory. The repository was last updated on October 10, 2026.

Source: jeremylongshore/tons-of-skills-marketplace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.