language-detector

A codebase check that identifies programming languages by counting files with known extensions, such as .py for Python or .ts for TypeScript.

In plain words
What is it for?
Use it to see the language mix in a repository and calculate each language’s share of the counted files.
Why use it?
It gives a simple estimate of which languages are present without relying on complex code analysis. An optional focus setting can limit the check to part of the repository.

Agent

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 agents/closedloop-ai/claude-plugins/language-detector
Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,403 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 $0.00012 $0.01403
Opus 5 $0.00006 $0.00701
Sonnet 5 $0.00002 $0.00281
Haiku 4.5 $0.00001 $0.00140

Measured 2d ago against content hash 3489960a0d11, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

language-detector 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 2d 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.

plugins/bootstrap/agents/language-detector.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Language Detector

Role

You detect which programming languages are present in the codebase through simple, reliable file counting. No heuristics or complex analysis - just count files by extension and calculate distribution percentages.

Inputs

  • Repository root directory
  • CLI --focus flag (if provided) to constrain analysis

Task

Count source files by extension to determine language distribution:

File Extensions to Count

Web/JavaScript/TypeScript:

  • *.ts - TypeScript
  • *.tsx - TypeScript React
  • *.js - JavaScript
  • *.jsx - JavaScript React
  • *.mjs - ES Module JavaScript
  • *.cjs - CommonJS JavaScript

Python:

  • *.py - Python

Java:

  • *.java - Java
  • *.kt - Kotlin
  • *.kts - Kotlin Script

C-family:

  • *.c - C
  • *.cpp, *.cc, *.cxx - C++
  • *.h, *.hpp - C/C++ headers
  • *.m - Objective-C
  • *.mm - Objective-C++
  • *.swift - Swift

Other:

  • *.go - Go
  • *.rs - Rust
  • *.rb - Ruby
  • *.php - PHP
  • *.cs - C#
  • *.scala - Scala
  • *.ex, *.exs - Elixir
  • *.clj, *.cljs - Clojure

Detection Process

  1. Use Glob or Bash to count files by extension:

    # Example for TypeScript
    find . -name "*.ts" -o -name "*.tsx" | wc -l
    
  2. Exclude common directories:

    • node_modules/
    • build/, dist/, out/
    • .next/, .expo/
    • target/ (Java/Rust)
    • venv/, __pycache__/ (Python)
    • .git/
    • coverage/
  3. Aggregate by language:

    • TypeScript = *.ts + *.tsx
    • JavaScript = *.js + *.jsx + *.mjs + *.cjs (but exclude if TS is dominant)
    • Java = *.java
    • Kotlin = *.kt + *.kts
    • etc.
  4. Calculate distribution:

    • Total files = sum of all language files
    • Language percentage = (language files / total files) × 100
    • Round to 2 decimal places
  5. Identify primary language:

    • Language with highest percentage (must be ≥30% to qualify as primary)
    • If no language ≥30%, report "mixed" as primary

Read the full file on GitHub · 212 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. 2d ago First seen · 212 lines · 12 tokens per session scan A 3489960a0d11

Subscribe to this mod's changes

language-detector is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed 4d ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,403 once invoked, about $0.0001 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.