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/mzzj114/nt-mcp-server/agents-mdgit clone --depth 1 https://github.com/Mzzj114/nt-mcp-serverWrote 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/mzzj114/nt-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/mzzj114/nt-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/mzzj114/nt-mcp-server/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 | $0.00982 | $0.00982 |
| Opus 5 | $0.00491 | $0.00491 |
| Sonnet 5 | $0.00196 | $0.00196 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
nt-mcp-server 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 3d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
MCP server exposing FRC NetworkTables (NT4) to AI agents. Reads/writes/monitors a robot's network tables; primary target is a local RobotPy sim (python -m robotpy sim on 127.0.0.1:5810).
Run
uv run nt-mcp-server # stdio MCP server (equiv: python -m nt_mcp_server)
uv run nt-recorder --prefixes /SmartDashboard/ --output-dir recordings # standalone CLI, not an MCP tool
Server runs on stdio — MCP clients (opencode) launch it via opencode.jsonc (uv run nt-mcp-server). It connects to 127.0.0.1:5810 by default. Live NT is optional; offline tools work without any connection.
Architecture
Package nt_mcp_server/ (4 modules, strict layering — each lower layer knows nothing about the one above):
__init__.py— FastMCPmcpinstance + all 17 tool definitions. Imports no ntcore. Tools delegate to the module-levelmanager = NTManager(). Sync tools (nt_set,nt_disconnect, etc.) are plain functions; read tools areasync.nt_manager.py—NTManager: pure NT4 client lifecycle + reads/writes/subscribe streams. No MCP/FastMCP imports. Lazy default instance viantcore.NetworkTableInstance.getDefault().nt_recorder.py— two unrelated pieces: thent-recorderCLI (argparsemain), and the synchronous offline NDJSON reader API (list_recordings,get_history,subscribe_offline, …) used by the offline MCP tools.nt_types.py— value normalization (to_jsonable), homogeneous-list classification, summaries. Pure, no connection state.
17 tools = 13 live + 4 offline (nt_list_recordings, nt_get_recording_info, nt_get_history/nt_subscribe_offline/nt_list_topics_offline). Every live tool response carries a top-level connected flag; disconnected reads return {"connected": false, "error": ...} instead.
NT4 gotchas (cost real debugging time)
- An NT4 client only receives a topic/value once it has a matching subscription.
NTManagerkeeps a topics-only subscription on"/"so the topic store stays populated; firstlist_topics/getafter connect polls briefly for the server to announce topics. Don't assume topics exist before syncing. nt_setdispatches on Python type (bool before int). Writes to an already-typed topic warn on mismatch;strict_type_check=Truerefuses the write (ok=False). NT itself also refuses cross-type writes.- Offline tools read from
NT_RECORDINGS_DIRenv var (default./recordings). Recordings are plain NDJSON:{"time": float, "topic": str, "value": jsonable}; filenames are Windows-safe (nt-record-<YYYY-MM-DDTHHMMSSZ>.ndjson). Never call reader functions on a recording an activeRecorderis still writing.
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.
- 3d ago First seen · 45 lines · 982 tokens per session scan A 0e172ac1e5cf
nt-mcp-server AGENTS.md is an instructions file published in the GitHub repository Mzzj114/nt-mcp-server (0 stars, last pushed 2d ago), licensed MIT. It adds 982 tokens to every session, about $0.0049 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
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.