npx claudepluginhub krishnendu409/everything-claude-free-versionThis skill uses the workspace's default tool permissions.
- When working on production systems
Provides deployment strategies (rolling, blue-green, canary), multi-stage Dockerfiles for Node.js, health checks, rollback plans, and production checklists for web apps.
Interactively installs Everything Claude Code skills and rules to user-level (~/.claude) or project-level (.claude) directories, verifies paths, and optimizes files. Activate on 'configure ecc' or setup requests.
Provides security checklist and hardened patterns for Solidity DeFi AMM contracts, liquidity pools, and swap flows. Covers reentrancy, CEI ordering, donation attacks, oracle manipulation, slippage, admin controls, and integer math.
Three modes of protection:
Intercepts destructive commands before execution and warns:
Watched patterns:
- rm -rf (especially /, ~, or project root)
- git push --force
- git reset --hard
- git checkout . (discard all changes)
- DROP TABLE / DROP DATABASE
- docker system prune
- kubectl delete
- chmod 777
- sudo rm
- npm publish (accidental publishes)
- Any command with --no-verify
When detected: shows what the command does, asks for confirmation, suggests safer alternative.
Locks file edits to a specific directory tree:
/safety-guard freeze src/components/
Any Write/Edit outside src/components/ is blocked with an explanation. Useful when you want an agent to focus on one area without touching unrelated code.
Both protections active. Maximum safety for autonomous agents.
/safety-guard guard --dir src/api/ --allow-read-all
Agents can read anything but only write to src/api/. Destructive commands are blocked everywhere.
/safety-guard off
Uses PreToolUse hooks to intercept Bash, Write, Edit, and MultiEdit tool calls. Checks the command/path against the active rules before allowing execution.
codex -a never sessions~/.claude/safety-guard.log