ard

aigon-research-do

Run this command followed by the Research ID.

aigon research-do {{args}}

Argument Resolution

If no ID is provided, or the ID doesn't match an existing topic in progress:

1. List all files in ./docs/specs/research-topics/03-in-progress/ matching research-*.md
2. If a partial ID or name was given, filter to matches
3. Present the matching topics and ask the user to choose one

This command is the research equivalent of feature-do: it is the main work step after research-start.

Step 0: Verify your workspace (MANDATORY)

Before doing ANYTHING else, verify your environment:

pwd
git branch --show-current

Research agents work in the main repository on the current branch. This is normal — research does not require branch isolation because you are only writing findings files, not modifying code.

CRITICAL RULES for research:

• You MUST NOT modify any source code files (.js, .ts, .py, .json, etc.)
• You MUST NOT modify other agents' findings files
• You MUST ONLY write to YOUR findings file: docs/specs/research-topics/logs/research-{ID}-cc-findings.md
• You MUST NOT run git checkout, git branch, or create new branches — stay where you are

Required Lifecycle Step

Before starting active research, run:

aigon agent-status implementing

This updates your agent state in the main repo so the dashboard and coordinator know you're actively working.

Your Task

1. Find the research topic in docs/specs/research-topics/03-in-progress/research-{ID}-*.md

2. Check for worktree/Fleet mode: Look for your findings file at: docs/specs/research-topics/logs/research-{ID}-cc-findings.md

3. Conduct deep research to answer each question in the research doc. Go broad before going deep:

   How to research thoroughly:

   • Search the web for documentation, blog posts, comparisons, and real-world usage. Don't rely only on what's in the codebase.
   • Read primary sources — official docs, GitHub repos, RFCs — not just summaries.
   • Explore multiple approaches before settling on one. For each question, consider at least 2-3 alternatives.
   • Look at the codebase to understand current patterns, constraints, and what's already been tried.
   • Compare trade-offs with evidence, not just intuition. Include concrete pros/cons.
   • Cite your sources — every claim should link back to where you found it.