Refinement — Security skill for Claude Code
Refine the codebase by performing code simplification and a security review in parallel, then applying any necessary security fixes.
How to install Refinement
Installs to ~/.claude/commands/thibautbaissac-react-express-ai-kit-refinement.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/ThibautBaissac/react-express-ai-kit/HEAD/.claude/commands/refinement.md -o ~/.claude/commands/thibautbaissac-react-express-ai-kit-refinement.md Restart Claude Code, or start a new session, for it to be picked up.
What Refinement does
name: refinement description: Refine the codebase by performing code simplification and a security review in parallel, then applying any necessary security fixes. argument-hint: "[task-number]" arguments: [task]
**Task selector:** `$task` is the task number passed to this command (e.g. `/refinement 2`). Everything below targets `tasks/task-$task.md`. If `/refinement` was invoked with no number, treat the task number as `1`.
You are a refinement agent. Your job is to improve the code
Alternatives in Security
- Deepsec — Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents 7.8k ★
- Tier 3 Code Refinement Report — Date: 2026-03-20 Status: ALL 54 FINDINGS IMPLEMENTED Scope: Full codebase (18 plugins, 888 files, ~266K lines) 222 ★
- Gdpr Review — Audit the codebase (or a given path/feature) for GDPR compliance and produce a prioritized findings report 172 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
UI Refine
Iterative UI refinement: audit existing UI, select issues to fix, apply fixes, re-audit. Provide file paths or
Dotnet Review
Multi-agent .NET code review - up to five reviewers in parallel (correctness, performance, security/observabil
Production Readiness Review
Parallel multi-agent readiness gate — fan blind reviewers across performance, security, UI/UX, test coverage,
iOS Design Review
Interactive HIG/UX design review of an iOS screen (screenshot + code), then a 12-dimension audit, phased polis
Review Implementation
Independent implementation audit of uncommitted code by Codex CLI against a plan doc, then apply agreed fixes
Code Review Simplify
Use when reviewing code changes for quality, security, performance, or maintainability issues and identifying
Related Agents
Backlog Grooming
Use when the user needs to groom, refine, or clean up a product backlog. Triggers on: 'groom backlog', 'backlo
Shadowcat Code Reviewer
Read-only code-quality review — bugs, logic errors, security, project-convention adherence, simplification and
Correctness Reviewer
Reviews code changes for logic errors, race conditions, security vulnerabilities, and edge cases. Use when per