codebase-research

Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.

509 stars

Best use case

codebase-research is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.

Teams using codebase-research should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/codebase-research/SKILL.md --create-dirs "https://raw.githubusercontent.com/a5c-ai/babysitter/main/library/methodologies/rpikit/skills/codebase-research/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/codebase-research/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How codebase-research Compares

Feature / Agentcodebase-researchStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Systematic codebase exploration following the Iron Law - understand the problem before exploring code. Four phases with file-finder and web-researcher agents.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Codebase Research

## Overview

Perform systematic codebase exploration to understand how existing systems work. Follows the Iron Law: "Do NOT explore the codebase until the problem is understood."

## When to Use

- Implementation direction is clear but codebase understanding is needed
- Investigating how an existing feature works before modifying it
- Understanding dependencies and data flows before planning
- Gathering context for a known goal

## Process

1. **Understand the request** - Ask clarifying questions one at a time (purpose, specifics, scope, constraints, context). Do NOT read any files until confirmed.
2. **Explore the codebase** - Use file-finder agent, read in order, trace data flows, identify constraints.
3. **Document findings** - Write structured research document to `docs/plans/YYYY-MM-DD-<topic>-research.md`.
4. **Transition** - Ask: plan, continue research, or conclude.

## Key Rules

- Quotations from source material capped at 125 characters maximum
- Only proceed to exploration after human confirms understanding
- Use file-finder agent for initial file discovery
- Use web-researcher agent for external context needs

## Agents Used

- `agents/file-finder/` - Locates relevant files with suggested reading order
- `agents/web-researcher/` - Gathers external context when needed

## Tool Use

Invoke via babysitter process: `methodologies/rpikit/rpikit-research`

Related Skills

user-research-synthesis

509
from a5c-ai/babysitter

Specialized skill for synthesizing qualitative user research into actionable insights. Analyzes interview transcripts, extracts patterns and themes, identifies pain points, creates affinity diagrams, and generates persona attributes from research data.

specialization-researcher

509
from a5c-ai/babysitter

Research specialization domains, compile references, analyze best practices, and gather comprehensive knowledge for new specialization creation.

research-ethics-irb

509
from a5c-ai/babysitter

Navigate institutional review board processes, informed consent, confidentiality, and ethical considerations in human subjects research

ethnographic-research

509
from a5c-ai/babysitter

Conduct participant observation, fieldwork, immersion, and thick description documentation in diverse cultural settings

research-ethics-irb-navigation

509
from a5c-ai/babysitter

Prepare ethics applications, develop informed consent protocols, and navigate institutional review processes for human subjects research

curatorial-research

509
from a5c-ai/babysitter

Conduct art historical research, provenance investigation, and scholarly analysis to inform exhibitions, acquisitions, and publications using primary and secondary sources

elicit-research-assistant

509
from a5c-ai/babysitter

AI-assisted literature review for question-answering over papers and evidence synthesis

market-research-platform

509
from a5c-ai/babysitter

Integration with market research platforms and survey tools for primary and secondary research

market-research-aggregator

509
from a5c-ai/babysitter

Market intelligence aggregation skill for synthesizing market data from multiple sources

codebase-sync

509
from a5c-ai/babysitter

Convention discovery and rule generation from codebase analysis. Scans project structure, builds search indexes, identifies patterns, and generates enforceable rules.

research-first-dev

509
from a5c-ai/babysitter

Research-first development methodology that investigates existing solutions, brainstorms alternatives, and evaluates trade-offs before any implementation begins.

research-orchestration

509
from a5c-ai/babysitter

Parallel research agent orchestration dispatching 5-10 concurrent agents for comprehensive multi-source research with synthesis and validation.