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.
npx agentmods add instructions/tcpiplab/instability/claude-mdgit clone --depth 1 https://github.com/tcpiplab/InstabilityWhat 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 | $0.01883 | $0.01883 |
| Opus 5 | $0.00941 | $0.00941 |
| Sonnet 5 | $0.00377 | $0.00377 |
| Haiku 4.5 | $0.00188 | $0.00188 |
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.
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
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.
- 2d ago First seen · 180 lines · 1,883 tokens per session scan A f488b53f9f87
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.
Other instructions, from other repositories
AionUi AGENTS.md
AGENTS.md instructions for iOfficeAI/AionUi, covering aionui - project guide, code conventions, file & directory structure, naming and ui library & icons.
vscode-unify-chat-provider AGENTS.md
Instructions for smallmain/vscode-unify-chat-provider, a project described as: Integrate multiple LLM API providers into VS Code's GitHub Copilot Chat using the Language Model API. One-click use of your Claude Code, Gemini CLI, Antigravity, Github Copilot, OpenAI Codex (ChatGPT Plus/Pro), xAI Grok (SuperGrok / X…
technocore-chat AGENTS.md
Instructions for flop-labs/technocore-chat: CI runs exactly these — run them before pushing.
mcp-erpnext AGENTS.md
Instructions for Casys-AI/mcp-erpnext, covering agents.md, project overview, project structure & module organization, build, test, and development commands and run all tests (also: deno task test).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
mcp-erpnext CLAUDE.md
Instructions for Casys-AI/mcp-erpnext: See AGENTS.md for all repository guidelines, architecture, conventions, and task recipes.