source-command-ff-research-codebase

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

1|1|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/redblacktree/fastflow --skill source-command-ff-research-codebase-redblacktree
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: source-command-ff-research-codebase
Source: https://github.com/redblacktree/fastflow/tree/main/.agents/skills/source-command-ff-research-codebase
Command: npx skills add https://github.com/redblacktree/fastflow --skill source-command-ff-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, dated research document. ## Core Features & Use Cases - Parallel Sub-Agent Research: Spawns specialized locator, analyzer, and pattern-finder agents to investigate different aspects of the codebase concurrently. - Structured Research Documents: Generates markdown reports with YAML frontmatter, code references with file paths and line numbers, architecture documentation, and historical context from the thoughts/ directory. - GitHub Permalinks & Sync: Adds permanent GitHub links for code references and syncs results via the thoughts directory. - Use Case: Ask "How does the authentication flow work?" and receive a complete research document mapping every relevant file, component interaction, and prior design decision without suggesting changes. ## 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-ff-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?▼

Invoke the research command and provide your question about the feature. The skill spawns parallel locator and analyzer sub-agents to map relevant files and document how components work, then compiles findings into a structured research document.

What agents are used for codebase research?▼

The skill uses codebase-locator to find where files live, codebase-analyzer to document how code works, and codebase-pattern-finder to surface existing patterns. Thoughts-locator and thoughts-analyzer agents add historical context from the thoughts directory.

Does the research skill suggest code improvements?▼

No. The skill strictly documents the codebase as it exists today. It does not critique implementations, propose refactoring, or recommend changes unless the user explicitly asks for them.

Where are research documents saved?▼

Research documents are saved to thoughts/shared/research/ with filenames formatted as YYYY-MM-DD-ENG-XXXX-description.md. Each document includes YAML frontmatter with date, researcher, git commit, branch, and tags.

Can I ask follow-up questions after research completes?▼

Yes. Follow-up questions append new sections to the same research document with updated frontmatter fields like last_updated and last_updated_by. New sub-agents are spawned as needed for additional investigation.