Skill: Inquiry Output Collector

You are a specialized agent for collecting and consolidating research outputs from Phase 1 inquiry agents. Your goal is to gather independent research findings and prepare them for the synthesis phase.

Capabilities

1. Completion Detection

   • Monitor ccmux sessions tagged with inquiry ID for completion
   • Watch inquiry research/ directory for file-based completion
   • Handle timeouts and partial completions gracefully

2. Output Extraction

   • Parse agent outputs from ccmux pane buffers or files
   • Extract structured sections (problem analysis, approaches, evidence, findings)
   • Normalize various output formats to standard structure

3. Report Generation

   • Create standardized research/agent-N.md files
   • Generate SUMMARY.md with cross-agent analysis
   • Update inquiry_report.json with completion status

Usage

# Collect from ccmux sessions (recommended for managed agents)
/inquiry-collect INQ-001 --mode ccmux

# Collect from files (for external agents or testing)
/inquiry-collect INQ-001 --mode file

# With custom timeout (seconds)
/inquiry-collect INQ-001 --mode ccmux --timeout 600

# Dry run - show what would be collected without writing
/inquiry-collect INQ-001 --mode file --dry-run

Arguments

Argument	Required	Description
inquiry_id	Yes	The inquiry ID (e.g., INQ-001)
--mode	No	Collection mode: ccmux (default) or file
--timeout	No	Timeout in seconds (default: 300)
--dry-run	No	Preview without writing files
--force	No	Overwrite existing research files

Workflow

1. Initialization

Read inquiry_report.json to get:

• research_agents: Number of expected agents
• phase: Verify inquiry is in research phase
• inquiry_id: Confirm ID match

2. Collection (Mode-Dependent)

ccmux Mode:

# Find sessions tagged with inquiry
sessions = ccmux_list_sessions()
inquiry_sessions = [s for s in sessions if f"INQ-{id}" in s.tags]

# Monitor each session
for session in inquiry_sessions:
    status = ccmux_get_status(session.pane_id)
    if status in ['complete', 'idle']:
        output = ccmux_read_pane(session.pane_id, lines=2000)
        # Extract and save

File Mode:

# Watch research/ directory
research_dir = inquiry_path / "research"
for i in range(1, research_agents + 1):
    file = research_dir / f"agent-{i}.md"
    if file.exists() and is_complete(file):
        # Extract and validate

3. Extraction

For each agent output, extract:

• Problem analysis
• Approaches explored
• Evidence gathered
• Key findings
• Recommendations

4. Summary Generation

Analyze all reports to create SUMMARY.md:

• Identify common themes across agents
• Note points of agreement and divergence
• Generate questions for synthesis phase
• Create comparison table of key findings

5. Status Update

Update inquiry_report.json:

{
  "phase": "synthesis",
  "status": "synthesis",
  "phase_history": [
    {
      "phase": "research",
      "entered_date": "2026-01-20",
      "notes": "Completed with 3/3 agents"
    },
    {
      "phase": "synthesis",
      "entered_date": "2026-01-20",
      "notes": "Research collection complete"
    }
  ]
}

Completion Detection

ccmux Mode Markers

An agent session is considered complete when:

• Session status is complete or idle
• OR pane output contains ## Conclusion or ## Summary
• OR agent explicitly reports completion via ccmux_report_status

File Mode Markers

A research file is considered complete when:

• File contains ## Conclusion section
• OR file ends with ---END--- marker
• OR file hasn't been modified for 60 seconds and has minimum content

Output Format

research/agent-N.md

# Agent N Research Report

**Inquiry**: INQ-XXX
**Agent**: [identifier]
**Completed**: YYYY-MM-DD HH:MM:SS

## Problem Analysis

[Extracted content about the agent's understanding of the problem]

## Approaches Explored

[Methods and strategies the agent investigated]

## Evidence Gathered

[Data, examples, or references found]

## Key Findings

[Main conclusions from the research]

## Recommendations

[Agent's suggestions for how to proceed]

---
*Generated by inquiry-collector*

SUMMARY.md

# Research Phase Summary

**Inquiry**: INQ-XXX
**Title**: [inquiry title]
**Completed**: YYYY-MM-DD HH:MM:SS
**Agents**: N/N completed

## Overview

[Brief synthesis of what was researched]

## Common Themes

- Theme 1: [description with supporting agents]
- Theme 2: [description with supporting agents]

## Points of Agreement

| Topic | Consensus | Agents |
|-------|-----------|--------|
| ... | ... | 1, 2, 3 |

## Points of Divergence

| Topic | Position A | Position B | Agents |
|-------|------------|------------|--------|
| ... | ... | ... | 1 vs 2, 3 |

## Key Questions for Synthesis

1. [Question arising from divergent findings]
2. [Question requiring deeper analysis]

## Agent Summary

| Agent | Focus Area | Key Insight | Unique Contribution |
|-------|------------|-------------|---------------------|
| 1 | ... | ... | ... |
| 2 | ... | ... | ... |

## Next Steps

The inquiry is ready for Phase 2: Synthesis. Key areas to address:
1. [Priority item]
2. [Priority item]

---
*Generated by inquiry-collector at YYYY-MM-DD HH:MM:SS*

Error Handling

Error	Behavior
Inquiry not found	Exit with clear error message
Wrong phase	Warning, offer --force option
Timeout	Mark incomplete agents, generate partial summary
Extraction failure	Save raw output, flag for manual review
Missing sessions/files	Report which agents are missing

Tools

The skill uses scripts in scripts/:

• collect.py - Main orchestrator
• ccmux_monitor.py - ccmux session monitoring
• file_monitor.py - File-based monitoring
• extract.py - Content extraction
• summarize.py - Summary generation

Requirements

• Python 3.9+
• ccmux MCP tools (for ccmux mode)
• jq (for JSON manipulation)

Examples

Complete Collection Workflow

# 1. Start inquiry with research agents
# (agents are spawned in ccmux with INQ-001 tag)

# 2. Wait for completion and collect
/inquiry-collect INQ-001 --mode ccmux --timeout 600

# Output:
# Collecting research outputs for INQ-001...
# Found 3 sessions tagged INQ-001
# Agent 1: Complete (output: 2847 chars)
# Agent 2: Complete (output: 3102 chars)
# Agent 3: Complete (output: 2956 chars)
#
# Generated files:
#   research/agent-1.md
#   research/agent-2.md
#   research/agent-3.md
#   SUMMARY.md
#
# Updated inquiry_report.json:
#   phase: research -> synthesis
#   status: research -> synthesis
#
# INQ-001 ready for synthesis phase.

Partial Collection

/inquiry-collect INQ-001 --mode ccmux --timeout 60

# Output:
# Collecting research outputs for INQ-001...
# Found 3 sessions tagged INQ-001
# Agent 1: Complete (output: 2847 chars)
# Agent 2: Timeout after 60s
# Agent 3: Complete (output: 2956 chars)
#
# WARNING: 1 of 3 agents did not complete
#
# Generated files:
#   research/agent-1.md
#   research/agent-3.md
#   SUMMARY.md (partial)
#
# Inquiry remains in 'research' phase.
# Re-run with longer timeout or --force to proceed.