skills.rest
Cogni-AI-OU
Cogni-AI-OUOFFICIAL
Explore all skills by this author →
Website𝕏@Cogni_AI_OUGitHub

dot-claude

Configures Claude Code workspace permissions and hooks to prevent unsafe Bash commands.

3|1|Updated Apr 12, 2026
Search Tags:#claude code#posttooluse#pretooluse#tool permissions#workspace settings#hook auditing#safe bash
One-click install
npx skills add https://github.com/Cogni-AI-OU/cogni-ai-agent-skills --skill dot-claude
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: dot-claude
Source: https://github.com/Cogni-AI-OU/cogni-ai-agent-skills/tree/main/dot-claude
Command: npx skills add https://github.com/Cogni-AI-OU/cogni-ai-agent-skills --skill dot-claude

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

dot-claude solves the problem of safely configuring Claude Code’s workspace permissions and tool execution behavior so agent-driven edits and command runs don’t hang, over-permission, or perform unintended actions.

Core Features & Use Cases

  • Explicit tool permissions: Define which Bash commands Claude Code is allowed to run using precise glob patterns in .claude/settings.json to prevent blocked or stalled tool use.
  • PreToolUse/PostToolUse safety hooks: Add guardrails and audit logging via PreToolUse and PostToolUse to block dangerous commands (e.g., rm -rf, SQL drops) and trace side effects.
  • Hook-based automation for edits: Trigger follow-up checks (like parsing/edit validation based on file patterns) after commands that modify files.
  • Environment & plugin enablement: Enable required environment variables and language server plugins (e.g., pyright-lsp) to support better tooling during development.

Quick Start

Configure .claude/settings.json by setting narrow Bash permissions, then add a PreToolUse matcher for Bash that blocks destructive command patterns while enabling PostToolUse logging for edit/write actions.

Frequently Asked Questions about dot-claude

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure Claude Code workspace settings to restrict Bash command permissions?▼

To restrict Claude Code Bash permissions, define narrow allowlists using precise glob patterns in your root `.claude/settings.json` file. This prevents the agent from executing blocked, stalled, or unintended commands during automated file edits.

What are PreToolUse and PostToolUse hooks used for in Claude Code?▼

PreToolUse and PostToolUse hooks provide guardrails and audit logging for Claude Code. PreToolUse blocks dangerous command patterns like `rm -rf`, while PostToolUse traces side effects and triggers follow-up checks after commands that modify files.

Can I block destructive commands like rm -rf when Claude Code runs Bash scripts?▼

Yes, you can block destructive commands by adding a PreToolUse matcher for Bash in `.claude/settings.json` that specifically targets and prevents dangerous patterns like `rm -rf` or SQL drops before they execute.

How do I enable language server plugins like pyright-lsp for Claude Code development?▼

You can enable language server plugins like `pyright-lsp` and set required environment variables within the `.claude/settings.json` configuration file to support better tooling and validation during Claude Code development sessions.

Why do my Claude Code agent edits hang or perform unintended actions in my repository?▼

Claude Code agent edits hang or perform unintended actions when workspace tool permissions lack strict, explicit allowlists. Configuring deterministic `.claude/settings.json` with PreToolUse safety hooks prevents over-permission and blocking behavior.

Related Skills

Explore More Software Engineering Skills→
kivo360kivo360
1

moai-cc-settings

Configure Claude Code settings.json, tool permissions, and environment variables.

Community
Advanced
greenheadHQgreenheadHQ
4

parallel-audit

Execute parallel-agent audits to surface side effects and regressions from code changes.

Community
Advanced
tarrragontarrragon
1

lsp-first

Configure language servers and navigate code using LSP protocols.

Community
Intermediate
guille-galloguille-gallo

git-guardrails-claude-code

Block dangerous git commands before execution using Claude Code PreToolUse hooks.

Community
Intermediate