cryptex-oss CLAUDE.md

cryptex-oss CLAUDE.md is an instructions file for coding agents from m4xx101/cryptex-oss. It costs 3,329 tokens per session, scanned A, original, MIT.

A contributor guide for Cryptex OSS, a browser application and command-line tool for exploring techniques used to test language-model security. It explains the SvelteKit app, the Python CLI, and their shared code.

In plain words
What is it for?
Working on browser tools, red-team labs, text transformations, the Python command-line interface, shared transformer code, and tests.
Why use it?
It gives coding agents the architecture and quality rules needed to change both interfaces without creating inconsistent behavior.

Instructions file

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 instructions/m4xx101/cryptex-oss/claude-md
Clone the repo
git clone --depth 1 https://github.com/m4xx101/cryptex-oss

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 cryptex-oss CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/m4xx101/cryptex-oss/claude-md.svg)](https://agentmods.dev/instructions/m4xx101/cryptex-oss/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/m4xx101/cryptex-oss/claude-md"><img src="https://agentmods.dev/badge/instructions/m4xx101/cryptex-oss/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 3,329 This file is loaded in full into every session.
When invoked 3,329 The same file — it is already loaded in full.
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 $0.03329 $0.03329
Opus 5 $0.01665 $0.01665
Sonnet 5 $0.00666 $0.00666
Haiku 4.5 $0.00333 $0.00333

Measured 5d ago against content hash 1966ad9773bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cryptex-oss 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 5d 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 · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Contributor + AI-Assistant Guide

This file is read by AI coding assistants (Claude, Copilot, Cursor, etc.) so they follow the project's conventions. Humans contributing PRs should skim it once too.

What this repo is

Cryptex OSS is a SvelteKit 2 + Svelte 5 + shadcn-svelte static-site app for LLM red-teaming techniques. The deliverable is a single-page browser app, served as static files. There is no backend, no database, and no auth; every piece of state lives in localStorage. The app exposes 25 tool routes (10 technique workbenches under /transforms, /decode, etc., plus 15 red-team labs under /redteam/*).

A Python CLI (cryptex-cli, managed with uv) shells out to Node to execute the canonical transformers in src/transformers/, so there is one source of truth for transforms: both the SvelteKit app and the CLI import the same 159 transformer files.

The v2.0 milestone hardened every tool surface with a unified ToolShell template, typed CryptexError taxonomy, Web Worker offloading for inputs at or above 50 KB, a per-tool Vault drawer (309 bundled OSS-licensed seed items + custom-add), and a persistent searchable session history via the v2 store. See the v2.0 conventions section below before adding new surfaces.

Commands

Primary (SvelteKit app)

cd app && npm install              # install deps
cd app && npm run dev              # Vite dev server, http://localhost:5173
cd app && npm run check            # svelte-kit sync + svelte-check (type-check)
cd app && npx vitest run           # run all unit tests
cd app && npx vitest run path/to/file.test.ts   # run a single test
cd app && npm run build            # static build → app/build/

Python CLI (cryptex-cli)

uv run cryptex-cli list
uv run cryptex-cli inspect caesar --json
uv run cryptex-cli encode --transform base64 --text "Hello"
uv run cryptex-cli /base64 --decode SGVsbG8=          # slash-command form
uv run cryptex-cli auto-decode --text "SGVsbG8="
pytest                                                 # python_tests/

Read the full file on GitHub · 211 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. 5d ago First seen · 211 lines · 3,329 tokens per session scan A 1966ad9773bd

Subscribe to this mod's changes

cryptex-oss CLAUDE.md is an instructions file published in the GitHub repository m4xx101/cryptex-oss (338 stars, last pushed 2mo ago), licensed MIT. It adds 3,329 tokens to every session, about $0.0166 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 instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens