codebase-explorer

codebase-explorer is a skill for Claude Code from ankitaa186/host-terminal-mcp. It costs 36 tokens per session (1,157 once invoked), scanned A, original, Apache-2.0.

A set of guidance for exploring and understanding an existing codebase, meaning a project's files, dependencies, configuration, and source structure. It suggests starting with the directory layout and project manifest files before examining implementation details.

In plain words
What is it for?
Use it to identify a project's language and build system, locate entry points and configuration, inspect dependencies, understand architecture, and find relevant files.
Why use it?
It provides a repeatable way to find the important parts of an unfamiliar project without reading every file at random.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the host-terminal plugin — 2 skills, 5 commands, 1 MCP server shipped together

Good fit Use it to identify a project's language and build system, locate entry points and configuration, inspect dependencies, understand architecture, and find relevant files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ankitaa186/host-terminal-mcp/codebase-explorer
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.

Any agent
npx skills add ankitaa186/host-terminal-mcp --skill codebase-explorer
Clone the repo
git clone --depth 1 https://github.com/ankitaa186/host-terminal-mcp

Made for: Claude Code.

Or install host-terminal, the plugin that ships this one along with the rest of its 2 skills, 5 commands, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codebase-explorer

README.md
[![agentmods](https://agentmods.dev/badge/skills/ankitaa186/host-terminal-mcp/codebase-explorer/github.svg)](https://agentmods.dev/skills/ankitaa186/host-terminal-mcp/codebase-explorer)
Your own site
<a href="https://agentmods.dev/skills/ankitaa186/host-terminal-mcp/codebase-explorer"><img src="https://agentmods.dev/badge/skills/ankitaa186/host-terminal-mcp/codebase-explorer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codebase-explorer

Your own site · 80×15
<a href="https://agentmods.dev/skills/ankitaa186/host-terminal-mcp/codebase-explorer"><img src="https://agentmods.dev/badge/skills/ankitaa186/host-terminal-mcp/codebase-explorer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,157 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.01157
Opus 5.5 $0.00014 $0.00463
Sonnet 5.5 $0.00007 $0.00231
Haiku 4.5 $0.00004 $0.00116

Measured 2mo ago against content hash ae86d7bd9194, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codebase-explorer 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 2mo ago.

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/codebase-explorer/SKILL.md · 178 lines

How it starts

The opening of the file, as written. The whole thing — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codebase Explorer

Expert guidance for exploring and understanding codebases.

Exploration Strategy

Phase 1: High-Level Structure

# Get directory tree (limit depth)
tree -L 2 -d

# List top-level contents
ls -la

# Check for documentation
ls README* CONTRIBUTING* docs/ doc/

Phase 2: Project Detection

# Identify project type by manifest files
ls package.json pyproject.toml Cargo.toml go.mod pom.xml build.gradle Gemfile

Phase 3: Deep Dive

# Entry points
cat main.py src/index.js cmd/main.go

# Configuration
cat config/*.yaml .env.example

# Dependencies
cat package.json requirements.txt Cargo.toml

Project Type Detection

File Project Type Next Steps
package.json Node.js Check scripts, dependencies
pyproject.toml Python (modern) Check [project], [tool.*]
requirements.txt Python (legacy) Check dependencies
Cargo.toml Rust Check [package], [dependencies]
go.mod Go Check module path, dependencies
pom.xml Java (Maven) Check <dependencies>
build.gradle Java (Gradle) Check dependencies block
Gemfile Ruby Check gems
composer.json PHP Check require
Makefile C/C++/Generic Check targets

Finding Key Components

Entry Points

# Common entry point names
find . -name "main.*" -o -name "index.*" -o -name "app.*" | head -20

# Scripts directory
ls bin/ scripts/ cmd/

Configuration

# Config files
find . -name "*.config.*" -o -name "*.yaml" -o -name "*.toml" | grep -v node_modules

Tests

# Test directories and files
find . -type d -name "test*" -o -type d -name "__tests__"
find . -name "*test*.py" -o -name "*.test.js" -o -name "*_test.go"

API/Routes

# Common API patterns
grep -r "app\.\(get\|post\|put\|delete\)" --include="*.js" --include="*.ts"
grep -r "@app\.route\|@router" --include="*.py"
grep -r "func.*Handler\|http\.Handle" --include="*.go"

Read the full file on GitHub · 178 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. 2mo ago First seen · 178 lines · 36 tokens per session scan A ae86d7bd9194

Subscribe to this mod's changes

codebase-explorer is a skill published in the GitHub repository ankitaa186/host-terminal-mcp (0 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,157 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-01.

Related

codebase-explorer compared with skills from other repositories

codebase-explorer next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
codebase-explorerankitaa186/host-terminal-mcpSkill08mo agoApache-2.0A36Claude Code
systematic-debuggingopen-metadata/OpenMetadataSkill16ktodayApache-2.0A37Claude Code
log-error-digestzebbern/claude-code-guideSkill4.7k2d agoMITA71Claude Code, Codex
cwv-optimizeradobe/skillsSkill329todayApache-2.0A112Claude Code
ci-fixersipyourdrink-ltd/bernsteinSkill1.2ktodayApache-2.0A15Claude Code, Codex
self-healhristo2612/jinnSkill3293d agoMITA19Claude Code, Codex
diagnosing-missing-recordingsPostHog/posthogSkill41ktodaynoneA76Claude Code, Codex