source-command-research-codebase

Name: source-command-research-codebase
Availability: InStock
Author: redblacktree

Documents existing codebase structure and behavior through parallel sub-agent research.

1|1|Updated Feb 3, 2026

Search Tags:#architecture #code analysis #documentation #markdown #codebase research #sub-agents #thoughts directory

Ready to run

npx skills add https://github.com/redblacktree/fastflow --skill source-command-research-codebase-redblacktree

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: source-command-research-codebase
Source: https://github.com/redblacktree/fastflow/tree/main/.agents/skills/source-command-research-codebase
Command: npx skills add https://github.com/redblacktree/fastflow --skill source-command-research-codebase-redblacktree

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Answering questions about how a large codebase works requires manually tracing files, components, and historical decisions, which is slow and error-prone. This Skill automates comprehensive codebase research by spawning parallel sub-agents and compiling their findings into a structured, citable research document. ## Core Features & Use Cases - Parallel Sub-Agent Research: Spawns specialized locator, analyzer, and pattern-finder agents to map where code lives and how it works without critiquing it. - Structured Research Documents: Generates markdown reports with YAML frontmatter, code references with file paths and line numbers, and GitHub permalinks, saved to the thoughts/ directory. - Historical Context Integration: Combines live codebase findings with prior research and decisions stored in the thoughts/ directory. - Use Case: Ask how the authentication flow works, and receive a complete document mapping every relevant file, component interaction, and past design decision. ## Quick Start Ask the agent to research how a specific feature or component works in the codebase and generate a research document.

Frequently Asked Questions about source-command-research-codebase

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I research how a codebase feature works with AI agents?▼

Invoke the research command with your question, and it spawns parallel locator and analyzer sub-agents to map relevant files and explain how components work. Findings are synthesized into a structured markdown document with file paths and line numbers.

What output does the codebase research command produce?▼

It generates a markdown research document in thoughts/shared/research/ with YAML frontmatter, a summary, detailed findings, code references, architecture documentation, and historical context. GitHub permalinks are added when the commit is pushed.

Does the codebase research skill suggest improvements or refactoring?▼

No. The skill strictly documents the codebase as it exists today. It explicitly prohibits recommendations, root cause analysis, and critiques unless the user explicitly requests them.

Can the research document be updated with follow-up questions?▼

Yes. Follow-up questions append a new dated section to the same research document, and the frontmatter fields last_updated and last_updated_by are refreshed. New sub-agents are spawned as needed for additional investigation.

Why are paths in research documents missing the searchable directory?▼

The thoughts/searchable/ directory contains hard links used only for searching. The skill strips the searchable/ prefix while preserving all other subdirectories so documented paths remain valid for editing and navigation.