agent-monitor
Real-time monitoring of Claude Code sub-agent activity in a tabbed terminal interface. Auto-spawns as soon as any sub-agent starts running.
What this skill does
# Agent Monitor Canvas
Displays real-time sub-agent activity with:
- Tabbed interface (one tab per agent)
- Scrollable output streams
- Tool call display with results
- Git diff visualization
## Auto-Spawn Behavior
The monitor automatically spawns as soon as Claude Code dispatches any sub-agent using the Task tool. It uses Claude Code hooks to detect agent lifecycle events:
- **PreToolUse hook**: Detects when Task tool is invoked
- **SubagentStop hook**: Tracks when agents complete
## Manual Usage
```bash
# Show agent monitor in current terminal
bun run src/cli.ts show agent-monitor --scenario monitor
# Spawn agent monitor in a new WezTerm/tmux pane
bun run src/cli.ts spawn agent-monitor --scenario monitor
# With initial configuration
bun run src/cli.ts spawn agent-monitor --scenario monitor --config '{
"parentSessionId": "session-123",
"agents": {}
}'
```
## Keyboard Controls
| Key | Action |
|-----|--------|
| Tab | Switch to next agent tab |
| 1-9 | Jump to agent by number |
| ↑/↓ | Scroll content up/down |
| PgUp/PgDn | Fast scroll (10 lines) |
| g | Jump to top |
| G | Jump to bottom |
| q/Esc | Close monitor |
## Status Indicators
Each tab shows a status indicator:
- 🟡 Yellow: Agent is running
- 🟢 Green: Agent completed successfully
- 🔴 Red: Agent encountered an error
## Content Display
For each agent, the monitor displays:
1. **Output Stream**: Text output from the agent's thinking and responses
2. **Tool Calls**: Each tool invocation with:
- Tool name (highlighted in cyan)
- Input parameters (truncated preview)
- Status icon (✓ success, ✗ error, ⋯ pending)
- Result (if available)
3. **Git Diffs**: File changes with syntax highlighting:
- Green for additions (+)
- Red for deletions (-)
- Cyan for hunk headers (@@)
## Configuration
```typescript
interface AgentMonitorConfig {
parentSessionId: string;
agents: Record<string, AgentState>;
}
interface AgentState {
id: string; // Unique agent identifier
description: string; // Task description
status: "running" | "completed" | "error";
startTime: number; // Unix timestamp
endTime: number | null;
toolCalls: ToolCallRecord[];
gitDiffs: DiffRecord[];
output: string[];
}
```
## Hook Configuration
The plugin uses the following hooks (defined in `hooks/hooks.json`):
```json
{
"hooks": {
"PreToolUse": [
{
"matcher": "Task",
"hooks": [
{
"type": "command",
"command": "bun \"${CLAUDE_PLUGIN_ROOT}/src/hooks/pre-tool-use.ts\""
}
]
}
],
"SubagentStop": [
{
"hooks": [
{
"type": "command",
"command": "bun \"${CLAUDE_PLUGIN_ROOT}/src/hooks/subagent-stop.ts\""
}
]
}
]
}
}
```
## Tracking File
Agent state is stored in `/tmp/claude-agents-{session}.json` and includes:
- Parent session ID
- Canvas pane ID (when spawned)
- Socket path for IPC
- All tracked agents with their current state
## Example Prompts
- "Run these three tasks in parallel and show me the monitor"
- "I want to see what the sub-agents are doing"
- "Open the agent activity viewer"
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.