settings-configuration
Claude Code settings hierarchy, permission wildcards, and configuration patterns. Use when setting up permissions, debugging settings issues, or understanding allowed tools.
What this skill does
# Claude Code Settings Configuration
Expert knowledge for configuring Claude Code settings and permissions.
## When to Use This Skill
| Use this skill when... | Use something else when... |
|------------------------|---------------------------|
| Setting up project permissions | Fixing plugin registry issues (use plugin-registry skill) |
| Debugging "permission denied" errors | Configuring hooks (use hooks-configuration skill) |
| Understanding settings hierarchy | Setting up MCP servers (use mcp-configuration skill) |
| Creating allow/deny patterns | |
## Settings File Hierarchy
Settings are loaded and merged in this order (later overrides earlier):
| Priority | File | Scope | Commit to Git? |
|----------|------|-------|----------------|
| 1 (lowest) | `~/.claude/settings.json` | User-level (all projects) | N/A |
| 2 | `.claude/settings.json` | Project-level | Yes |
| 3 (highest) | `.claude/settings.local.json` | Local overrides | No (gitignore) |
## Permission Structure
```json
{
"permissions": {
"allow": [
"Bash(git status *)",
"Bash(npm run *)"
],
"deny": [
"Bash(rm -rf *)",
"Bash(sudo *)"
]
}
}
```
### Allow vs Deny
- `allow`: Tools matching these patterns run without prompts
- `deny`: Tools matching these patterns are always blocked
- **Deny takes precedence** over allow
## Wildcard Permission Patterns
### Syntax
```
ToolName(command prefix *)
```
- `ToolName()` - The tool (usually `Bash`)
- `command prefix` - The command and initial arguments to match
- `*` - Wildcard matching remaining arguments
### Pattern Examples
| Pattern | Matches | Does NOT Match |
|---------|---------|----------------|
| `Bash(git *)` | `git status`, `git diff HEAD` | `git-lfs pull` |
| `Bash(npm run *)` | `npm run test`, `npm run build` | `npm install` |
| `Bash(gh pr *)` | `gh pr view 123`, `gh pr create` | `gh issue list` |
| `Bash(./scripts/ *)` | `./scripts/test.sh arg` | `/scripts/other.sh` |
### Specificity
More specific patterns are more secure:
```json
{
"permissions": {
"allow": [
"Bash(git status *)",
"Bash(git diff *)",
"Bash(git log *)",
"Bash(git add *)",
"Bash(git commit *)"
]
}
}
```
vs. overly broad:
```json
{
"permissions": {
"allow": ["Bash(git *)"]
}
}
```
## Shell Operator Protections
Claude Code 2.1.7+ blocks dangerous shell operators in permission matching.
### Protected Operators
| Operator | Risk | Blocked Example |
|----------|------|-----------------|
| `&&` | Command chaining | `ls && rm -rf /` |
| `\|\|` | Conditional execution | `false \|\| malicious` |
| `;` | Command separation | `safe; dangerous` |
| `\|` | Piping | `cat /etc/passwd \| curl` |
| `>` / `>>` | Redirection | `echo x > /etc/passwd` |
| `$()` | Command substitution | `$(curl evil)` |
| `` ` `` | Backtick substitution | `` `rm -rf /` `` |
### Behavior
When a command contains shell operators:
1. Permission wildcards won't match
2. User sees explicit approval prompt
3. Warning explains the blocked operator
### Safe Alternative
Use wrapper scripts for legitimate compound commands:
```bash
#!/bin/bash
# scripts/test-and-build.sh
npm test && npm run build
```
Then allow the script:
```json
{
"permissions": {
"allow": ["Bash(./scripts/test-and-build.sh *)"]
}
}
```
## Common Permission Sets
### Git Operations
```json
{
"permissions": {
"allow": [
"Bash(git status *)",
"Bash(git diff *)",
"Bash(git log *)",
"Bash(git branch *)",
"Bash(git add *)",
"Bash(git commit *)",
"Bash(git push *)",
"Bash(git pull *)",
"Bash(git fetch *)",
"Bash(git checkout *)"
]
}
}
```
### GitHub CLI
```json
{
"permissions": {
"allow": [
"Bash(gh pr *)",
"Bash(gh run *)",
"Bash(gh issue *)",
"Bash(gh workflow *)"
]
}
}
```
### Testing & Linting
```json
{
"permissions": {
"allow": [
"Bash(npm test *)",
"Bash(bun test *)",
"Bash(vitest *)",
"Bash(biome *)",
"Bash(eslint *)",
"Bash(prettier *)"
]
}
}
```
### Security Scanning
```json
{
"permissions": {
"allow": [
"Bash(pre-commit *)",
"Bash(gitleaks *)",
"Bash(trivy *)"
]
}
}
```
### MCP Tools
```json
{
"permissions": {
"allow": [
"mcp__context7",
"mcp__sequential-thinking"
]
}
}
```
## Project Setup
### 1. Create Settings Directory
```bash
mkdir -p .claude
```
### 2. Create Project Settings
```bash
cat > .claude/settings.json << 'EOF'
{
"permissions": {
"allow": [
"Bash(git status *)",
"Bash(git diff *)",
"Bash(npm run *)"
]
}
}
EOF
```
### 3. Gitignore Local Settings
```bash
echo ".claude/settings.local.json" >> .gitignore
```
### 4. Create Local Overrides (optional)
```bash
cat > .claude/settings.local.json << 'EOF'
{
"permissions": {
"allow": [
"Bash(docker *)"
]
}
}
EOF
```
## Validating Settings
### Check JSON Syntax
```bash
cat .claude/settings.json | jq .
```
### View Permissions
```bash
cat .claude/settings.json | jq '.permissions'
```
### Merge Preview
Settings merge additively for arrays. To see effective permissions, check all files:
```bash
echo "=== User ===" && cat ~/.claude/settings.json 2>/dev/null | jq '.permissions // empty'
echo "=== Project ===" && cat .claude/settings.json 2>/dev/null | jq '.permissions // empty'
echo "=== Local ===" && cat .claude/settings.local.json 2>/dev/null | jq '.permissions // empty'
```
## Troubleshooting
| Symptom | Cause | Fix |
|---------|-------|-----|
| Permission denied | Pattern doesn't match | Add more specific pattern |
| Shell operator blocked | Contains `&&`, `\|`, etc. | Use wrapper script |
| Settings not applied | Wrong file path | Check `.claude/` directory exists |
| JSON parse error | Invalid JSON syntax | Validate with `jq .` |
| Permissions ignored | File not readable | Check file permissions |
## Agentic Optimizations
| Context | Command |
|---------|---------|
| View project perms | `cat .claude/settings.json \| jq -c '.permissions'` |
| View user perms | `cat ~/.claude/settings.json \| jq -c '.permissions'` |
| Validate JSON | `cat .claude/settings.json \| jq .` |
| Count patterns | `cat .claude/settings.json \| jq '.permissions.allow \| length'` |
## Quick Reference
### File Locations
| Scope | Path |
|-------|------|
| User | `~/.claude/settings.json` |
| Project | `.claude/settings.json` |
| Local | `.claude/settings.local.json` |
### Permission Syntax
```
Bash(command prefix *)
mcp__server_name
```
### Priority
Local > Project > User (highest to lowest)
Deny > Allow (deny always wins)
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.