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/lburny/cadpilot/agents-mdgit clone --depth 1 https://github.com/LBurny/cadpilotWrote 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.
[](https://agentmods.dev/instructions/lburny/cadpilot/agents-md)<a href="https://agentmods.dev/instructions/lburny/cadpilot/agents-md"><img src="https://agentmods.dev/badge/instructions/lburny/cadpilot/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.04472 | $0.04472 |
| Opus 5 | $0.02236 | $0.02236 |
| Sonnet 5 | $0.00894 | $0.00894 |
| Haiku 4.5 | $0.00447 | $0.00447 |
Grade A, and why
cadpilot AGENTS.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 4d 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CADPilot — Workspace Guide
Purpose
MCP (Model Context Protocol) server that lets AI clients (Claude Desktop, LangChain, etc.) control FreeCAD remotely. Two main components communicate over XML-RPC:
- MCP server (
src/cadpilot/) — Python package run viauvx cadpilotoruv run cadpilot. Speaks MCP to the AI client and XML-RPC to FreeCAD. - FreeCAD addon (
addon/CADPilot/) — Installed into FreeCAD'sMod/directory. Hosts the XML-RPC server inside the FreeCAD process and dispatches all document/GUI work onto the main thread.
Directory Layout
src/cadpilot/ # MCP server package (published to PyPI)
server.py # FastMCP tool definitions & CLI entry point (main())
freecad_client.py # XML-RPC client proxy to FreeCAD addon
operations/core.py # Tool operation implementations (one function per tool)
operations/__init__.py # Re-exports all operations
responses.py # ToolResponse type alias, text/json/screenshot helpers
server_state.py # ServerState dataclass (connection, host, screenshot flags)
session_state.py # ModelingSession/Step dataclasses, JSON persistence, current-session registry
assembly_state.py # AssemblySession/AssemblyStep dataclasses, JSON persistence (~/.cadpilot/assembly/), precomputed-undo rollback
operations/assembly.py # assembly_session tool: spec validation → RPC assembly_op → session recording
pattern_store.py # Pattern memory (reusable workflows), keyword retrieval
guidance.py # Lightweight next-step suggestions & risk heuristics (incl. primitive_without_sketch / absolute_placement / assembly-mode steer)
prompt_text.py # ASSET_CREATION_STRATEGY prompt template
tool_docs.py # Long per-operation reference docs served by the operation_help tool
addon/CADPilot/ # FreeCAD workbench addon (copied to FreeCAD's Mod/ dir)
InitGui.py # Workbench registration, toolbar/menu, auto-start
Init.py # Path setup
rpc_server/
rpc_server.py # FreeCADRPC class — XML-RPC handler, server start/stop
gui_dispatch.py # dispatch_to_gui() — queues work onto the GUI thread
commands.py # FreeCAD Command classes for toolbar buttons
object_factory.py # create_object_gui() — object creation logic
property_mapper.py # set_object_property() — recursive property assignment
serialize.py # serialize_object() — object → dict for RPC responses
view_manager.py # save_active_screenshot() — camera/view screenshot logic
geometry_query.py # Read-only Shape queries — measure/topology/interference
assembly_ops.py # Anchor-based assembly — anchors (auto/explicit), assemble (mates), verify_assembly
joint_ops.py # Persistent-joint assembly — FreeCAD 1.1 Assembly WB lifecycle (Link wrap, joints, preSolve+solve, rollback, verify+gap profile)
trim_ops.py # Declarative priority trimming — non-destructive baked cut in loser-link frame
feature_ops.py # Parametric feature creation (boolean/fillet/sketch/pad/...) + selectors
sketcher_ops.py # Constrained-sketch builder (geometry/constraints/solver diagnostics)
ip_filter.py # FilteredXMLRPCServer — IP/CIDR allowlist
settings.py # JSON settings persistence (auto-start, remote, allowed IPs)
examples/ # Usage examples (adk/agent.py, langchain/react.py)
tests/ # pytest suite for the MCP server side (fake XML-RPC connection)
assets/ # Demo GIFs and images for README
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.
- 4d ago First seen · 193 lines · 4,472 tokens per session scan A bebec94d6c06
cadpilot AGENTS.md is an instructions file published in the GitHub repository LBurny/cadpilot (7 stars, last pushed 21d ago), licensed MIT. It adds 4,472 tokens to every session, about $0.0224 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
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
GhidrAssistMCP CLAUDE.md
Claude Code instructions for symgraph/GhidrAssistMCP, covering claude.md, build and development commands, building the extension, set ghidrainstalldir environment variable first and build the extension.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.
pbi-context CLAUDE.md
Instructions for Osc2405/pbi-context, covering estado actual (actualizado 2026-07-15), actualización 2026-08-03 — rename pbi-docs → pbi-context, 0. contexto del proyecto (no re-investigar, ya validado), 1. feature obligatoria: soporte .pbip / tmdl and por qué es obligatoria (contexto de mercado, no opinable).
pfsense-mcp-server AGENTS.md
AGENTS.md instructions for night4me/pfsense-mcp-server, covering pfsense mcp server, architecture and security, development workflow, long-running validation and test parallelism.