/security
Security best practices
$ npx -y skills add AgriciDaniel/claude-code-essentials-vs-code --skill security --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/security
Context preview
The summary Claude sees to decide when to auto-load this skill.
Security best practices
SKILL.md
security.SKILL.mdname: security description: Security best practices
Always check for and prevent:
1. SQL injection - use parameterized queries only 2. XSS - escape all user input in HTML output 3. CSRF - use tokens for state-changing requests 4. Hardcoded secrets - use environment variables 5. Insecure dependencies - use the project's existing dependency-audit tool; report missing tooling instead of installing it automatically 6. Missing input validation - validate all user inputs 7. Improper error exposure - don't leak stack traces 8. Missing authentication - verify auth on all protected routes 9. Broken access control - check authorization for every action 10. Sensitive data exposure - encrypt at rest and in transit
A small, opt-in setup helper for Claude Code and selected VS Code extensions. The January 2026 tutorial's “26 extensions in one command” is historical: this refresh installs nothing by default. Review your choices before applying them.

