afk
AFK (Away From Keyboard) mode - enable tiered modes, check status, review sessions. Use /afk [operation] where operation is full|plan|research|monitor|off|status|review
Best use case
afk is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
AFK (Away From Keyboard) mode - enable tiered modes, check status, review sessions. Use /afk [operation] where operation is full|plan|research|monitor|off|status|review
Teams using afk should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/afk/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How afk Compares
| Feature / Agent | afk | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
AFK (Away From Keyboard) mode - enable tiered modes, check status, review sessions. Use /afk [operation] where operation is full|plan|research|monitor|off|status|review
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# AFK Mode Skill
Manage AFK (Away From Keyboard) mode with tiered tool access and session tracking.
## Operations
- [Enable AFK mode](enable.md) - Activate AFK with tiered tool access (full/plan/research/monitor)
- [Disable AFK mode](off.md) - Turn off AFK and resume normal operation
- [Check status](status.md) - View current AFK status and statistics
- [Review session](review.md) - Review planning documents and blocked actions
## Routing
Parse `$ARGUMENTS` to determine the operation:
| First Word | Operation | Description |
|------------|-----------|-------------|
| `full` | [enable.md](enable.md) | No tools allowed |
| `plan` | [enable.md](enable.md) | Read-only tools (Read, Glob, Grep) |
| `research` | [enable.md](enable.md) | Read + web (WebFetch, WebSearch) |
| `monitor` | [enable.md](enable.md) | Read + Bash |
| `off` | [off.md](off.md) | Disable AFK mode |
| `status` | [status.md](status.md) | Show current status |
| `review` | [review.md](review.md) | Review planning session |
| *(empty/other)* | [enable.md](enable.md) | Default to full mode |
## Usage Examples
```
/afk → full mode, default message
/afk full "In a meeting" → full mode, custom message
/afk plan "Explore codebase" → plan mode (read-only)
/afk research → research mode (read + web)
/afk off → disable
/afk status → check status
/afk review → review current/last session
/afk review 20240115_103000 → review specific session
```
## State Management
All state operations use the script at `scripts/state.sh`:
```bash
"${CLAUDE_PLUGIN_ROOT}/skills/afk/scripts/state.sh" <command> [args]
```
Commands: `enable`, `disable`, `is-enabled`, `get-state`, `get-mode`, `get-message`, `get-allowed`, `is-allowed`, `get-plan-path`, `get-log-path`Related Skills
specification-writing
Core reference for EARS requirement patterns, Given/When/Then acceptance criteria, RFC 2119 language, requirement ID conventions, and specification quality checklists. Background knowledge for the spec-writer agent. Preloaded by spec-writer via the skills frontmatter field; not user-invocable.
refine
Unified specification refinement plugin. Single entry point for all spec operations: greenfield architecture pipelines (principles → design → stack → spec → plan), feature spec creation in existing systems, iterative convergence loops, quality reviews, drift detection, finalization, ticket decomposition, traceable updates, and lifecycle archival. Detects pipeline state from existing artifact frontmatter and routes intelligently. Use whenever you need to create, refine, validate, or evolve a technical specification.
validation-orchestrator
Intelligent validation orchestrator with auto-detection and progressive validation workflows
security-scan
Comprehensive security scanning for secrets, vulnerabilities, and unsafe practices
schema-validation
Validate JSON schemas, required fields, and format compliance for marketplaces and plugins
quality-analysis
Deep quality analysis with scoring, recommendations, and actionable reports
documentation-validation
Validate documentation completeness, format, and quality for plugins and marketplaces
best-practices
Enforce OpenPlugins and Claude Code best practices for naming, versioning, and standards compliance
message-generation
Generate conventional commit messages following best practices
history-analysis
Analyze git history to learn project's commit style and conventions
commit-error-handling
Handle git errors and edge cases gracefully
commit-best-practices
Enforce git commit best practices and workflow guidance