Codebase Analysis
- 520 installs
- 894 repo stars
- Updated March 13, 2026
- solatis/claude-config
codebase-analysis is an agent skill that helps developers inspect and reason about existing codebases during AI-assisted software development and agent-building workflows.
About
codebase-analysis is a skill entry in solatis/claude-config aimed at AI and agent-building tasks that require understanding an existing repository. The catalog lists it under agent tooling with minimal public readme detail, but the name and placement signal support for mapping project structure, dependencies, and implementation patterns before making changes. Developers reach for codebase-analysis when they need an agent to orient inside an unfamiliar repo instead of guessing file layout. It fits early build work where comprehension precedes refactors, feature additions, or integration changes across backend and service code.
- codebase-analysis
- AI & Agent Building
- AI-coding skill
Codebase Analysis by the numbers
- 520 all-time installs (skills.sh)
- +7 installs in the week ending Jul 27, 2026 (Skillselion tracking)
- Ranked #1,724 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 3, 2026 (Skillselion catalog sync)
npx skills add https://github.com/solatis/claude-config --skill codebase-analysisAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 520 |
|---|---|
| repo stars | ★ 894 |
| Last updated | March 13, 2026 |
| Repository | solatis/claude-config ↗ |
How do agents analyze an unfamiliar codebase quickly?
Helps with ai & agent building tasks.
Who is it for?
Developers onboarding an AI agent to a large or unfamiliar repository before refactors or feature work.
Skip if: Projects where automated static-analysis dashboards and architecture docs already answer every structural question.
When should I use this skill?
The user asks the agent to explore, map, or analyze an existing codebase as part of AI or agent-building work.
What you get
Repository orientation notes, structural maps, and analysis context the agent uses for subsequent code changes.
Files
Codebase Analysis
Understanding-focused skill that builds foundational comprehension of codebase structure, patterns, flows, decisions, and context. Serves as foundation for downstream analysis skills (problem-analysis, refactor, etc.).
When this skill activates, IMMEDIATELY invoke the script. The script IS the workflow.
Invoke:
<invoke working-dir=".claude/skills/scripts" cmd="python3 -m skills.codebase_analysis.analyze --step 1" />
codebase-analysis/
Codebase exploration skill. IMMEDIATELY invoke the script -- do NOT explore first.
Files
| File | What | When to read |
|---|---|---|
SKILL.md | Skill invocation | Using this skill |
README.md | Architecture | Understanding design |
scripts/analyze.py | Orchestrator | Debugging behavior |
scripts/subagent.py | Subagent workflow | Debugging exploration |
Analyze
Before you plan anything non-trivial, you need to actually understand the codebase. Not impressions -- evidence. The analyze skill forces systematic investigation with structured phases and explicit evidence requirements.
| Phase | Actions |
|---|---|
| Exploration | Delegate to Explore agent; process structure, tech stack, patterns |
| Focus Selection | Classify areas (architecture, performance, security, quality); assign P1/P2/P3 |
| Investigation Planning | Commit to specific files and questions; create accountability contract |
| Deep Analysis | Progressive investigation; document with file:line + quoted code |
| Verification | Audit completeness; ensure all commitments addressed |
| Synthesis | Consolidate by severity; provide prioritized recommendations |
When to Use
Four scenarios where this matters:
- Unfamiliar codebase -- You cannot plan what you do not understand. Period.
- Security review -- Vulnerability assessment requires systematic coverage,
not "I looked around and it seems fine."
- Performance analysis -- Before optimization, know where time actually
goes, not where you assume it goes.
- Architecture evaluation -- Major refactors deserve evidence-backed
understanding, not vibes.
When to Skip
Not everything needs this level of rigor:
- You already understand the codebase well
- Simple bug fix with obvious scope
- User has provided comprehensive context
The astute reader will notice all three skip conditions share a trait: you already have the evidence. The skill exists for when you do not.
Example Usage
Use your analyze skill to understand this codebase.
Focus on security and architecture before we plan the authentication refactor.The skill outputs findings organized by severity (CRITICAL/HIGH/MEDIUM/LOW), each with file:line references and quoted code. This feeds directly into planning -- you have evidence-backed understanding before proposing changes.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What is codebase-analysis used for?
codebase-analysis is a skill in solatis/claude-config for AI and agent-building tasks that require understanding an existing repository. Developers use it so agents can orient to project structure and implementation details before proposing edits or integrations.
When should developers load codebase-analysis?
Developers should load codebase-analysis when an agent must explore or analyze an unfamiliar codebase as part of development or agent-configuration work. The skill is intended for repository comprehension tasks that precede refactors, features, or integration changes.