Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Windsurf Data Handling

ASecurity

'Govern data processed through Devin Desktop (formerly Windsurf).

2,785 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentsgorailsgitsecuritydocumentation

Works with

claude codeterminalmcp

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/24/2026

$npx -y skills add jeremylongshore/claude-code-plugins-plus --skill windsurf-data-handling --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Windsurf Data Handling?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Windsurf Data Handling
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jeremylongshore-windsurf-data-handling-5add42e0/badge)](https://www.skillsdirectory.com/skills/jeremylongshore-windsurf-data-handling-5add42e0)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: windsurf-data-handling
description: 'Govern data processed through Devin Desktop (formerly Windsurf).
  Use when mapping sensitive data, configuring context exclusions, reviewing vendor
  controls, or preparing regulated-workload evidence. Trigger with "windsurf data
  privacy", "windsurf PII", "GDPR", "data residency", or "AI data boundary".'
allowed-tools: Read, Write, Edit
argument-hint: "[scope or requirements]"
version: 1.12.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
- saas
- windsurf
- privacy
- compliance
- data-handling
compatibility: Designed for Claude Code
---

# Devin Desktop Data Handling

## Overview

Build an evidence-backed data map for Devin Desktop. Do not infer retention, residency, training use, certification coverage, or zero-data-retention from plan names; verify mutable vendor claims against the current contract and security documentation.

## Prerequisites

- Data-classification policy and approved repository inventory
- Contract, DPA, or security evidence available to the authorized reviewer
- Named security, privacy, and legal decision owners

## Tool Use

- Use `Read` to inspect only the repository files and configuration needed for the request.
- Use `Write` only for a new artifact the user requested; never write credentials or unreviewed production configuration.
- Use `Edit` for bounded, reviewable changes and preserve unrelated user work.

## Instructions

### Step 1: Inventory data flows

For Cascade, autocomplete, indexing, remote indexing, MCP, Hooks, diagnostics, and App Deploys, record inputs, destination, purpose, identity, retention evidence, administrator, and applicable policy. Include metadata and logs, not only source files.

### Step 2: Minimize local context

Use `.gitignore` and repository `.codeiumignore` to exclude secrets, generated output, customer datasets, private keys, production exports, and irrelevant large files. Enterprise administrators may apply a global `.codeiumignore` under `~/.codeium/`.

Ignored paths are context controls. They do not revoke filesystem access, rotate secrets, satisfy least privilege, or prove a regulatory requirement.

### Step 3: Choose durable instructions

Put shared data-handling requirements in `AGENTS.md` or `.devin/rules/*.md`, for example:

```markdown
# Regulated data boundary
- Never paste customer records, access tokens, or production exports into prompts.
- Use synthetic fixtures in tests and examples.
- Require security review for changes under `src/payments/`.
- Stop and escalate if a requested artifact contains regulated data.
```

### Step 4: Review integrations

For every MCP server, Hook, deployment target, and analytics export, confirm an owner, authentication method, approved scopes, destination, log policy, revocation path, and incident contact. Disable integrations that lack an accountable owner.

### Step 5: Reconcile vendor evidence

Capture the URL or contract section, observation date, product/plan scope, and reviewer for each claim. Where public documentation and negotiated terms differ, label the applicable authority rather than blending them.

### Step 6: Test and approve

Use synthetic canaries to verify exclusions and policy behavior. Obtain the required security/privacy/legal approval before enabling regulated workloads, remote indexing, or external MCP access.

## Output

Produce a data-boundary record identifying data classes, indexed and excluded paths, integrations, organization controls, telemetry and logging decisions, retention or residency evidence, open questions, approvals, and validation results. Never reproduce sensitive values.

## Error Handling

| Issue | Response |
|---|---|
| Vendor claim lacks current evidence | Mark unverified and request contract/security review |
| Sensitive data entered Cascade | Stop, contain sharing, rotate affected secrets, and follow incident policy |
| Ignore test fails | Correct syntax or scope, refresh indexing through current controls, and retest |
| Integration owner is unknown | Disable or quarantine the integration until ownership is established |

## Examples

**Evidence row:** "Customer export; excluded by `.codeiumignore`; no MCP access; repository owner: Data Platform; retention claim pending DPA confirmation; synthetic canary passed during the recorded review run."

## Resources

- [Focused first-party references](references/official-docs.md)
- [Windsurf Ignore](https://docs.devin.ai/desktop/context-awareness/windsurf-ignore)
- [Windsurf security](https://windsurf.com/security)
- [Enterprise administration](https://docs.devin.ai/desktop/guide-for-admins)

## Related Skill

Continue with `windsurf-policy-guardrails` to turn approved data controls into enforceable repository, terminal, MCP, deployment, and organization policy.

Attribution

jeremylongshorejeremylongshore
View sourceSee grades on GitHubMore from jeremylongshore →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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 (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →