shannot CLAUDE.md

Claude Code instructions for corv89/shannot, covering guidelines for ai agents (claude & others), project overview, cli commands, core workflow and setup (interactive menu or subcommands).

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/corv89/shannot/claude-md
Clone the repo
git clone --depth 1 https://github.com/corv89/shannot
Per session 950 This file is loaded in full into every session.
When invoked 950 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 $0.00950 $0.00950
Opus 5 $0.00475 $0.00475
Sonnet 5 $0.00190 $0.00190
Haiku 4.5 $0.00095 $0.00095

Measured today against content hash 04d0401aa157, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shannot 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 today.

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 · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Guidelines for AI Agents (Claude & Others)

Quick reference for AI agents working with the Shannot codebase. For detailed architecture and contribution guidelines, see CONTRIBUTING.md.

Project Overview

Shannot is a sandboxed system administration tool for LLM agents using PyPy sandbox architecture with syscall-level virtualization.

Key Facts:

  • Python 3.11+ host code, Python 3.6 sandboxed code
  • Zero runtime dependencies (stdlib only)
  • Test directory is test/ (not tests/)

CLI Commands

# Core workflow
shannot run SCRIPT              # Execute Python script in sandbox
shannot approve [SESSION]       # Interactive approval TUI
shannot status                  # Check runtime and pending sessions

# Setup (interactive menu or subcommands)
shannot setup                   # Interactive setup menu
shannot setup runtime           # Install PyPy 3.6 stdlib
shannot setup remote add NAME   # Add SSH remote target
shannot setup remote list       # List configured remotes
shannot setup remote test NAME  # Test SSH connection
shannot setup mcp install       # Install MCP integration

Key Options: --target NAME, --dry-run, --color/--no-color

Development Commands

# Environment
make install                # Install runtime dependencies
make install-dev            # Install with dev dependencies + hooks

# Testing
make test                   # Run all tests
make test-unit              # Skip integration tests
make test-integration       # Integration tests only (requires PyPy)
make test-coverage          # Run with coverage

# Code Quality
make lint                   # Lint with Ruff
make format                 # Format with Ruff
make type-check             # Type check with Basedpyright

# Documentation
make docs                   # Build MkDocs (output to site/)
make docs-serve             # Serve at http://127.0.0.1:8000

# Building
make clean                  # Clean build artifacts
make build                  # Build wheel + sdist
make build-binary           # Build Nuitka binary (Linux)

Read the full file on GitHub · 121 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. today First seen · 121 lines · 950 tokens per session scan A 04d0401aa157

Subscribe to this mod's changes

shannot CLAUDE.md is an instructions file published in the GitHub repository corv89/shannot (25 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 950 tokens to every session, about $0.0047 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 2026-09-01.