explore-codebase

A workflow for understanding an unfamiliar codebase by mapping its structure and examining important files progressively. It gathers focused context instead of reading the whole project at once.

In plain words
What is it for?
Use it when joining a new project, investigating how a codebase works, locating important files, tracing dependencies, or preparing to make changes safely.
Why use it?
It helps developers get oriented quickly while using less context and avoiding unnecessary code reading. The process highlights entry points, active areas, symbols, dependencies, and exports.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/edimuj/tokenlean/explore-codebase
Any agent
npx skills add edimuj/tokenlean --skill explore-codebase
Clone the repo
git clone --depth 1 https://github.com/edimuj/tokenlean

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 636 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00060 $0.00636
Opus 5 $0.00030 $0.00318
Sonnet 5 $0.00012 $0.00127
Haiku 4.5 $0.00006 $0.00064

Measured yesterday against content hash 09ae61a6efec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore-codebase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/claude/explore-codebase/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explore Codebase

Understand a project in minutes by reading as little raw code as possible.

Workflow

Structure → Key areas → Drill down → Report

1. Get the map

tl structure

This shows directories, file counts, and token estimates. Identify:

  • Where the bulk of the code lives
  • Entry points (usually obvious from directory names)
  • Test coverage presence

2. Find entry points and hot files

tl parallel "tl entry" "tl hotspots"

Entry points tell you where execution starts. Hotspots tell you where development is active.

3. Understand key files

For each important file identified above:

File size → Decision
  ├─ <150 lines → Just read it
  ├─ 150-400 lines → tl symbols first, tl snippet for specifics
  └─ 400+ lines → tl symbols only, then tl snippet as needed
# Per file, gather context in one call:
tl parallel "symbols=tl symbols <file>" "deps=tl deps <file>" "exports=tl exports <file>"

# Or for entire directories:
tl symbols src/           # All files in a directory (compact one-liner per file)
tl symbols a.ts b.ts      # Multiple specific files (compact)

4. Trace the dependency graph

Pick the most central file (usually has the most importers):

tl parallel "impact=tl impact <file>" "flow=tl flow <function> <file>"

This reveals the architecture: which modules are core infrastructure vs. leaf nodes.

5. Check conventions

tl style              # Coding conventions (naming, formatting, patterns)

Run once at the start of a session to match the project's style.

6. Report

Summarize your understanding:

## Project overview
What it does, in one sentence.

## Architecture
Key directories and their roles. How data/control flows.

## Key files
The 5-10 most important files with one-line descriptions.

## Patterns
Conventions, frameworks, notable architectural decisions.

## Entry points
Where execution starts, how to run/test.

Tips

  • Use tl parallel to gather context on multiple files simultaneously
  • tl context <dir> shows token cost of a directory — skip reading dirs over 50k tokens directly
  • For React/frontend projects, also run tl component on main UI files
  • For API projects, tl api and tl routes reveal endpoint structure

Read the full file on GitHub · 101 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 101 lines · 60 tokens per session scan A 09ae61a6efec

Subscribe to this mod's changes

explore-codebase is a skill published in the GitHub repository edimuj/tokenlean (11 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 636 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

zerodust

Sweep 100% of native gas tokens (ETH, BNB, MATIC, etc.) from EVM chains via ZeroDust, leaving exactly zero balance. Use when: user wants to exit a chain completely, consolidate dust balances, clean up wallets, or bridge remaining native tokens cross-chain. Supports 25 mainnet chains including Ethereum, Base, Arbitrum…

andresdefi/zerodust · 93 tokens

ctx2img

Cut context tokens by rendering it as images. ctx2img paint turns any text-shaped input (a repo, a directory, a file, markdown, stdin) into dense images that carry the full text at 60-75% fewer tokens, with stable handles and a verbatim factsheet; ctx2img read recovers guaranteed-exact text. Use before ingesting any…

Koukyosyumei/h5i-ctx2img · 103 tokens

r3f-animation

React Three Fiber animation - useFrame, useAnimations, spring physics, keyframes. Use when animating objects, playing GLTF animations, creating procedural motion, or implementing physics-based movement.

zebbern/claude-code-guide · 43 tokens

r3f-best-practices

React Three Fiber (R3F) and Poimandres ecosystem best practices. Use when writing, reviewing, or optimizing R3F code. Triggers on tasks involving @react-three/fiber, @react-three/drei, zustand, @react-three/postprocessing, @react-three/rapier, or leva.

zebbern/claude-code-guide · 74 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

vs-search

Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-config issues.

volcengine/SearchCLI · 27 tokens