Borrowing it
Nothing to install: this file belongs to yttrium400/reducethemtokens. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yttrium400/reducethemtokens/main/CLAUDE.mdgit clone --depth 1 https://github.com/yttrium400/reducethemtokensWrote 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.
[](https://agentmods.dev/instructions/yttrium400/reducethemtokens/claude-md)<a href="https://agentmods.dev/instructions/yttrium400/reducethemtokens/claude-md"><img src="https://agentmods.dev/badge/instructions/yttrium400/reducethemtokens/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.
<a href="https://agentmods.dev/instructions/yttrium400/reducethemtokens/claude-md"><img src="https://agentmods.dev/badge/instructions/yttrium400/reducethemtokens/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01140 | $0.01140 |
| Opus 5.5 | $0.00456 | $0.00456 |
| Sonnet 5.5 | $0.00228 | $0.00228 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
reducethemtokens 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.
How it starts
The opening of the file, as written. The whole thing — 86 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.
Commands
# Install for development
pip install -e ".[dev]" # core + test deps
# Run tests
pytest tests/ # all tests (~0.3s)
pytest tests/test_extractor.py # single file
pytest tests/ -k "test_python" # single test by name
# Build and publish
python -m build
twine upload dist/*
# Use the CLI from source
rtt index .
rtt install .
Architecture
The pipeline is: extractor → formatter → CLI/installer.
Data model (rtt/__init__.py)
Three dataclasses flow through everything: Symbol (name, kind, signature, children), FileIndex (path, language, imports, symbols), RepoIndex (list of FileIndex). CompareReport is only used by rtt compare.
Extraction (rtt/extractor.py)
extract_repo() is the main entry point. It walks the directory, calls _extract_file() per file, applies include/exclude/no_tests filters, then optionally trims to a token budget via _trim_to_budget().
_extract_file() parses with tree-sitter and delegates to language-specific functions (_extract_python_symbol, _extract_js_symbol, etc). Import extraction is separate from symbol extraction and only captures top-level imports - imports inside function bodies are intentionally excluded.
Language modules (rtt/languages/)
Each module (python_lang.py, javascript_lang.py, etc.) provides extract_fn_signature() and extract_class_signature() - functions that format a tree-sitter node into a readable signature string. Adding a new language means adding a module here, registering it in languages/__init__.py and languages/registry.py, and adding extraction logic in extractor.py.
JS/TS edge cases
Two patterns require special handling in _iter_toplevel_nodes():
- IIFE wrappers
(function($){...})(jQuery)- handled by_iter_js_iife_body() - Bare block statements
{ function foo(){} }- tree-sitter parses these asERRORorstatement_blocknodes; children are yielded transparently
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 · 86 lines · 1,140 tokens per session scan A de1b84824bc7
reducethemtokens CLAUDE.md is an instructions file published in the GitHub repository yttrium400/reducethemtokens (11 stars, last pushed 4mo ago), licensed MIT. It adds 1,140 tokens to every session, about $0.0046 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 2026-08-30.
reducethemtokens CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| reducethemtokens CLAUDE.mdyttrium400/reducethemtokens | Instructions file | 11 | 4mo ago | MIT | A | 1,140 | 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 |