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/cuber-it/mcp_shell_tools/claude-mdgit clone --depth 1 https://github.com/cuber-it/mcp_shell_toolsWhat 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 | $0.01152 | $0.01152 |
| Opus 5 | $0.00576 | $0.00576 |
| Sonnet 5 | $0.00230 | $0.00230 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade C, and why
mcp_shell_tools CLAUDE.md scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- BLOCKED_PATTERNS in config.py (rm -rf /, dd, mkfs, fork bombs, etc.) How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp_shell_tools
Übersicht
MCP-Server für lokale Entwicklungsarbeit. 24 Tools, zwei Transports (stdio + Streamable HTTP), Session-Persistenz, Security-Layer, OAuth. Produktiv im Einsatz mit Claude Desktop, claude.ai und ChatGPT.
Version: 2.1.0 Sprache: Python 3.10+ MCP SDK: mcp >= 1.26.0 Lizenz: MIT Repo: github.com/cuber-it/mcp_shell_tools
Tech Stack
- Python, FastMCP (mcp SDK)
- httpx (HTTP-Client für Registry)
- pydantic (Validierung)
- mcp-oauth (optional, für Remote-Zugriff)
- pytest + pytest-asyncio (Tests)
Projektstruktur
code/
├── main.py → CLI Entry-Point (serve --http PORT)
├── server.py → FastMCP Setup, Tool-Registration, Auto-Log
├── config.py → Konstanten, Security-Patterns (BLOCKED_PATTERNS)
├── state.py → Working Directory, Custom ENV
├── health_server.py → /health + /health/ready Endpoint
├── heinzel_integration.py → Registry Self-Registration (optional)
├── tools/
│ ├── filesystem.py → 9 Tools (read, write, list, glob, delete, move, copy, append, tree)
│ ├── editor.py → str_replace, diff_preview
│ ├── search.py → grep (Text + Regex)
│ ├── shell.py → shell_exec + env + set_env (mit Process-Isolation)
│ ├── project.py → cd, cwd, project_init (CLAUDE.md)
│ ├── memory.py → memory_add/show/clear (note, decision, question, todo)
│ ├── session.py → session_save/resume/list (JSON-Persistenz)
│ └── commands.py → Slash-Kommandos (/verbose, /log, /transcript, /status)
├── persistence/
│ ├── models.py → SessionData, MemoryEntry (dataclasses)
│ └── session_manager.py → JSON-basierte Persistenz (~/.mcp_shell_tools/)
└── utils/
├── logging.py → Konfiguriertes Logging
├── output.py → Output-Truncation (MAX_OUTPUT_BYTES)
└── paths.py → Pfad-Utilities
Konventionen
- Code-Style: PEP8, max-line-length=120, flake8 clean
- Tests: pytest, 70 Tests, alle async via pytest-asyncio
- Imports: Absolute (
from code.tools.shell import ...) - Tool-Signatur: Annotated[Type, Field(description=...)] für MCP-Schema
- Git: Einzeilige Commits, Details in CHANGELOG.md
- Kein Verzeichnis
src/— historischcode/, Umbenennung TODO
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 · 99 lines · 1,152 tokens per session scan C a07b3642688b
mcp_shell_tools CLAUDE.md is an instructions file published in the GitHub repository cuber-it/mcp_shell_tools (2 stars, last pushed 6mo ago), licensed MIT. It adds 1,152 tokens to every session, about $0.0058 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.