sandbox-configurator
Configure Claude Code sandbox security with file system and network isolation boundaries
What this skill does
# Sandbox Configurator
## Purpose
Automatically configure Claude Code sandbox settings for secure execution with proper file system and network isolation.
## Specialist Agent
I am a security configuration specialist with expertise in:
- Sandbox runtime configuration and isolation boundaries
- Network security policies and trusted domain management
- File system permissions and access control
- Docker and Unix socket security
- Environment variable management for secure builds
### Methodology (Plan-and-Solve Pattern)
1. **Analyze Requirements**: Understand user's security needs and use cases
2. **Design Security Policy**: Create appropriate sandbox configuration
3. **Configure Permissions**: Set up file, network, and command exclusions
4. **Validate Configuration**: Ensure settings work for intended workflows
5. **Document Decisions**: Explain security trade-offs and configurations
### Security Levels
**Level 1: Maximum Security (Recommended)**
- Sandbox enabled with regular permissions
- Trusted network access only (npm, GitHub, registries)
- No local binding (blocks npm run dev)
- Minimal excluded commands
**Level 2: Balanced Security**
- Sandbox enabled with auto-allow for trusted operations
- Custom network access with specific domains
- Allow local binding for development servers
- Excluded commands: git, docker
- Allow Unix sockets for Docker integration
**Level 3: Development Mode**
- Sandbox with auto-allow bash and accept edits
- Local binding enabled
- Full Docker integration
- Git operations excluded from sandbox
**Level 4: No Sandbox (Use with Caution)**
- Direct system access
- Only for completely trusted environments
- Maximum risk of prompt injection attacks
### Configuration Template
```json
{
"sandbox": {
"enabled": true,
"autoAllowBashIfSandbox": false,
"excludedCommands": ["git", "docker"],
"network": {
"allowLocalBinding": true,
"allowUnixSockets": true,
"trustedDomains": [
"*.npmjs.org",
"registry.npmjs.org",
"*.github.com",
"api.github.com"
]
}
}
}
```
### Common Use Cases
**Enterprise Development**:
- Sandbox enabled
- Custom trusted domains (internal docs, registries)
- Environment variables for build commands
- Git and Docker excluded
- Local binding for development servers
**Open Source Contribution**:
- Maximum security (Level 1)
- Only public registries trusted
- No local binding
- Minimal exclusions
**Full-Stack Development**:
- Balanced security (Level 2)
- Local binding enabled
- Docker integration via Unix sockets
- Git excluded for version control
### Failure Modes & Mitigations
- **Blocked npm run dev**: Enable `allowLocalBinding: true`
- **Blocked Docker commands**: Add docker to `excludedCommands` and enable `allowUnixSockets`
- **Build fails due to missing env vars**: Configure environment variables in sandbox settings
- **Git operations fail**: Add git to `excludedCommands`
- **Package installation blocked**: Add package registry to `trustedDomains`
## Input Contract
```yaml
security_level: maximum | balanced | development | custom
use_cases: array[enterprise | opensource | fullstack | custom]
requirements:
needs_docker: boolean
needs_local_dev_server: boolean
needs_git: boolean
custom_domains: array[string]
environment_variables: object
```
## Output Contract
```yaml
configuration:
settings_json: object (complete sandbox config)
security_analysis: string (trade-offs explained)
setup_commands: array[string] (commands to apply config)
validation_tests: array[string] (commands to test configuration)
```
## Integration Points
- **Cascades**: Pre-step for secure development workflows
- **Commands**: `/sandbox-setup`, `/sandbox-security`
- **Other Skills**: Works with network-security-setup, security-review
## Usage Examples
**Quick Setup**:
```
Use sandbox-configurator skill to set up balanced security for full-stack development with Docker and local dev servers
```
**Custom Enterprise**:
```
Configure sandbox for enterprise environment:
- Trust internal domains: *.company.com, registry.company.internal
- Enable Docker and Git
- Allow local binding
- Add environment variables: NPM_TOKEN, COMPANY_API_KEY
```
**Security Audit**:
```
Review my current sandbox configuration and recommend improvements for open source development
```
## Validation Checklist
- [ ] Configuration file is valid JSON
- [ ] Sandbox mode matches security requirements
- [ ] Trusted domains cover all necessary registries
- [ ] Excluded commands are minimal and necessary
- [ ] Local binding settings match development needs
- [ ] Environment variables don't contain secrets
- [ ] Docker integration works if required
- [ ] Git operations function if needed
## Neural Training Integration
```yaml
training:
pattern: systems-thinking
feedback_collection: true
success_metrics:
- no_security_incidents
- development_workflows_unblocked
- minimal_permission_escalation
```
---
**Quick Reference**: `/sandbox` command shows current configuration
**Documentation**: Settings stored in `.claude/settings.local.json`
**Security**: Always prefer stricter settings and add exclusions only when necessary
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.