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/0xnullai/dg-mcp/claude-mdgit clone --depth 1 https://github.com/0xNullAI/DG-MCPWrote 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/0xnullai/dg-mcp/claude-md)<a href="https://agentmods.dev/instructions/0xnullai/dg-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/0xnullai/dg-mcp/claude-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 5.1 | $0.02260 | $0.02260 |
| Opus 5 | $0.01130 | $0.01130 |
| Sonnet 5 | $0.00452 | $0.00452 |
| Haiku 4.5 | $0.00226 | $0.00226 |
Grade B, and why
DG-MCP CLAUDE.md scanned grade B 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 6d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo setcap cap_net_raw+eip $(eval readlink -f $(which node)) How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code working in DG-MCP — the Model Context Protocol server for DG-Lab BLE devices (Coyote 2.0 / 3.0, plus the paw-prints sensor, civet-edging sensor, and opossum vibration controller).
Project Overview
DG-MCP is a single-package Node.js CLI published to npm as dg-mcp. It speaks MCP over stdio so any MCP-compatible LLM client (Claude Desktop, Continue, etc.) can drive DG-Lab BLE devices — potentially several at once — over Bluetooth Low Energy.
The v0.1.x implementation (Python + bleak + FastMCP) is archived on the archive/0.x-py branch. The current v1.x rewrite is TypeScript on top of @dg-kit/* and @stoprocent/noble.
Repo Layout
src/
cli.ts entry; --waveforms / --waveforms-dir / --library-dir, env vars, runs stdio server
server.ts MCP server: @dg-kit/tools defs → MCP tool schema, plus device-management tools
device-manager.ts DeviceManager: Map<address, ConnectedDevice> — holds multiple concurrent BLE
connections keyed by address, one adapter per DG-Lab device family (coyote /
paw-prints / civet-edging / opossum), classifies via @dg-kit/protocol's
detectDeviceKind(), drives noble scan/connect/disconnect
noble-shim.ts @stoprocent/noble Characteristic → BluetoothRemoteGATTCharacteristicLike
waveform-library.ts fs-backed WaveformLibrary (built-ins + .pulse / .zip + JSON persist)
.github/workflows/
ci.yml typecheck + build on PR
publish.yml npm publish on git tag (`v*`)
Branch & PR Convention
- Default branch:
main - All changes go directly on
main(small project, single-user surface) - Use
archive/0.x-pyfor any Python-version maintenance only - Releases: tag a version on
mainwithgit tag v1.0.x && git push --tags→publish.ymlpushes to npm using theNPM_TOKENrepo secret
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.
- 6d ago First seen · 126 lines · 2,260 tokens per session scan B f00a25db2e19
DG-MCP CLAUDE.md is an instructions file published in the GitHub repository 0xNullAI/DG-MCP (13 stars, last pushed 25d ago), licensed MIT. It adds 2,260 tokens to every session, about $0.0113 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.