Instability CLAUDE.md

Repository instructions for Instability, a Python chatbot and security-testing toolkit. They describe how to run its chatbot, diagnostics, tools, tests, and v3 environment checks.

In plain words
What is it for?
Use them when developing or reviewing Instability, running its chatbot or diagnostic tools, checking the v3 environment, or running tests.
Why use it?
They give a coding agent the project’s expected commands, structure, and simple function-based style, reducing the chance of changes that conflict with the repository.

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/tcpiplab/instability/claude-md
Clone the repo
git clone --depth 1 https://github.com/tcpiplab/Instability
Per session 1,883 This file is loaded in full into every session.
When invoked 1,883 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 $0.01883 $0.01883
Opus 5 $0.00941 $0.00941
Sonnet 5 $0.00377 $0.00377
Haiku 4.5 $0.00188 $0.00188

Measured 2d ago against content hash f488b53f9f87, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Instability 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 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.

CLAUDE.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 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

  • Run the chatbot: python instability.py chatbot
  • Run the chatbot with specific model: python instability.py chatbot --model MODEL_NAME
  • Run comprehensive diagnostics: python instability.py manual all
  • Run specific tool: python instability.py manual [tool_name]
  • List available tools: python instability.py manual
  • Run v3 environment test: python instability.py test
  • Run test suite: python instability.py run-tests

Code Style Guidelines & Design Philosophy

  • Simplicity First: Avoid framework complexity and OOP abstraction - keep code easy to understand, maintain, and customize
  • Function-Based: Use simple functions rather than complex class hierarchies
  • No Heavy Frameworks: Avoid LangChain, complex ORMs, or other heavyweight abstractions
  • Direct Implementation: Prefer direct library usage over abstraction layers
  • No Emojis: Never use decorative emojis in code, terminal output, or documentation. This is a professional pentesting tool that needs clean, scannable output during critical network diagnostics.
  • Functional Symbols: Use plain Unicode symbols for functional indicators:
    • ☐ for unchecked/incomplete items
    • ☑︎ for checked/complete items
    • ⚠ for warnings (plain symbol only)
    • Use text like [OK], [FAIL], [PASS], [ERROR] for status indicators
  • Imports: Standard library imports first, then third-party, then local modules
  • Typing: Use Python type hints (from typing import List, Dict, Optional, etc.)
  • Naming:
    • snake_case for functions/variables
    • CamelCase for classes (use sparingly)
    • UPPERCASE for constants
  • Error Handling: Use try/except blocks with specific exceptions
  • Logging: Print statements should use colorama (Fore.COLOR)
  • Comments: Minimal comments, focusing on why not what
  • Functions: Include verbose, thorough docstrings for functions, especially for tools that can be called by the chatbot

Read the full file on GitHub · 180 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 · 180 lines · 1,883 tokens per session scan A f488b53f9f87

Subscribe to this mod's changes

Instability CLAUDE.md is an instructions file published in the GitHub repository tcpiplab/Instability (5 stars, last pushed 2d ago), licensed MIT. It adds 1,883 tokens to every session, about $0.0094 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 2026-08-31.