What is language-experiments CLAUDE.md?

Repository instructions for a project that explores programming languages through small, runnable experiments and recorded findings.

Use them when creating a new experiment: inspect existing work and insights, choose an uncovered topic, run the script, and record the result.

They prevent repeated experiments and keep each investigation focused, self-contained, and based on observed output.

How amitshekhariitbhu/language-experiments configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to amitshekhariitbhu/language-experiments. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/amitshekhariitbhu/language-experiments/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/amitshekhariitbhu/language-experiments

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/amitshekhariitbhu/language-experiments/claude-md/github.svg)](https://agentmods.dev/instructions/amitshekhariitbhu/language-experiments/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/amitshekhariitbhu/language-experiments/claude-md"><img src="https://agentmods.dev/badge/instructions/amitshekhariitbhu/language-experiments/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/amitshekhariitbhu/language-experiments/claude-md"><img src="https://agentmods.dev/badge/instructions/amitshekhariitbhu/language-experiments/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 633 This file is loaded in full into every session.

When invoked 633 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00633	$0.00633
Opus 5.5	$0.00253	$0.00253
Sonnet 5.5	$0.00127	$0.00127
Haiku 4.5	$0.00063	$0.00063

Measured 2mo ago against content hash 70ee8c9bd594, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

language-experiments CLAUDE.md 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.

CLAUDE.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Purpose

This is a language experimentation project. The goal is to explore programming languages through hands-on experiments that reveal non-obvious, unique, or surprising behaviors — things you don't learn from textbooks.

How It Works

When the user asks to do a new experiment (e.g., "do a new experiment in Python" or "new experiment in Kotlin on coroutines"):

Read all existing experiment files and INSIGHTS.md in the <language>/ folder to understand what's already covered.
If the user specified a topic, create an experiment on that topic (but still avoid repeating existing insights).
If no topic specified, pick a topic that is NOT already covered by existing experiments.
Create the experiment as a standalone, runnable script in <language>/.
Run the experiment and capture actual output.
Append the new insight to <language>/INSIGHTS.md.

If the language folder doesn't exist yet, create it.

Rules for Experiments

No web apps, no frameworks — pure language experiments only.
Each experiment file should be self-contained and runnable independently.
Name experiments descriptively: floating_point_trap.py, mutable_default_gotcha.py, etc.
Every experiment must include comments explaining what's happening and why it's surprising.
Focus on behaviors that differ from other languages or defy common assumptions.
Run the experiments and capture actual output in INSIGHTS.md.
Never repeat an experiment or insight that already exists in the language folder.

Running Experiments

C: gcc -std=c17 -o /tmp/c_exp c/<file>.c && /tmp/c_exp
C++: g++ -std=c++17 -o /tmp/cpp_exp cpp/<file>.cpp && /tmp/cpp_exp
Go: go run go/<file>.go
Java: javac java/<file>.java -d /tmp/java_exp && java -cp /tmp/java_exp <ClassName>
JavaScript: node javascript/<file>.js
Kotlin: kotlinc kotlin/<file>.kt -include-runtime -d /tmp/kt_exp.jar && java -jar /tmp/kt_exp.jar
Python: python3 python/<file>.py
Ruby: ruby ruby/<file>.rb
Rust: rustc rust/<file>.rs -o /tmp/rust_exp && /tmp/rust_exp
Swift: swiftc swift/<file>.swift -o /tmp/swift_exp && /tmp/swift_exp
Other languages: use standard toolchain for that language.

Read the full file on GitHub · 53 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.

2mo ago First seen · 53 lines · 633 tokens per session scan A 70ee8c9bd594

Subscribe to this mod's changes

language-experiments CLAUDE.md is an instructions file published in the GitHub repository amitshekhariitbhu/language-experiments (11 stars, last pushed 8mo ago), licensed MIT. It adds 633 tokens to every session, about $0.0025 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 2026-08-31.

Languages agent ai-agent ai-agents experiments language learn

language-experiments CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
language-experiments CLAUDE.mdamitshekhariitbhu/language-experiments	Instructions file	11	8mo ago	MIT	A	633	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

language-experiments: Instructions file for Claude Code