By theemilz
Architecture guardrails for AI-generated code. Catches function name drift, phantom imports, field mismatches, and contract violations that compile but fail at runtime.
Analyze the project's architecture: layer structure, dependency graph, naming conventions, and module coupling. Use this to understand the codebase before writing new code, or when planning refactoring. Invokes `camouf_analyze` via MCP.
Fix detected mismatches in AI-generated code: rename drifted functions, correct field names, add missing parameters, and resolve contract violations. Uses `camouf_suggest_fix` to get precise fix instructions, then applies edits. Use after running validate when ERROR violations are found.
Validate the current project for AI-generated code mistakes: function name drift, phantom imports, field mismatches, contract violations, and architectural issues. Use this skill BEFORE committing code, after generating new files, or when you suspect cross-file inconsistencies. Invokes `camouf_validate` via MCP.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Catches the mistakes AI coding assistants make — broken contracts, phantom imports, signature drift, and architectural violations that traditional linters miss entirely.
# Add the marketplace
claude plugin marketplace add TheEmilz/camouf-claude-plugin
# Install the plugin
claude plugin install camouf@camouf-marketplace
# Initialize camouf in your project
npx camouf init
Camouf detects the specific class of bugs that AI coding assistants create due to limited context windows:
| Error Type | Example |
|---|---|
| Function name drift | getUser() vs getUserById() |
| Phantom imports | import { x } from './nonexistent' |
| Field mismatch | user.userEmail vs user.email |
| Missing parameters | cancelOrder(id) vs cancelOrder(id, reason) |
| Context drift | Same concept named differently across files |
| Layer violations | Frontend importing from backend |
camouf_validate, camouf_analyze, camouf_suggest_fix)npx claudepluginhub theemilz/camouf-claude-pluginArchitecture guardrails for AI-generated code. Catches function name drift, phantom imports, field mismatches, and contract violations that compile but fail at runtime.
Memory compression system for Claude Code - persist context across sessions
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.