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 skills add Mzzj114/nt-mcp-server --skill nt-mcp-workflowgit 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/skills/mzzj114/nt-mcp-server/nt-mcp-workflow)<a href="https://agentmods.dev/skills/mzzj114/nt-mcp-server/nt-mcp-workflow"><img src="https://agentmods.dev/badge/skills/mzzj114/nt-mcp-server/nt-mcp-workflow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mzzj114/nt-mcp-server/nt-mcp-workflow"><img src="https://agentmods.dev/badge/skills/mzzj114/nt-mcp-server/nt-mcp-workflow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00025 | $0.00677 |
| Opus 5.5 | $0.00010 | $0.00271 |
| Sonnet 5.5 | $0.00005 | $0.00135 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
nt-mcp-workflow 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 15d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
nt-mcp-workflow
Investigate an FRC robot issue using the nt (NetworkTables) MCP server. The server speaks NT4 and works both live (connected to a running RobotPy sim or real robot) and offline (replaying a saved .ndjson recording).
When to use this skill
- You need to read, write, or monitor NetworkTables values to diagnose robot behavior.
- You have a saved NT recording and need to inspect what happened after the fact.
- The user asks you to tune, debug, or analyze a robot subsystem through telemetry.
- The user asks you to start listening and implies that later you will analyze results with the user.
Choose the investigation mode
| Mode | Best for | See |
|---|---|---|
| Live online | A focused, interactive issue (wrong value, single subsystem, real-time inputs). | references/automated-workflow.md |
| Offline recording | A broad or transient issue (whole-match forensics, post-event analysis, unreproducible glitch). | references/replay-recording.md |
| Capture telemetry | You need a recording of what happened — to feed offline analysis or to keep a capture window out of your context. | references/recording.md |
If neither mode is a perfect fit, use whichever tools best answer the user's question.
Capture telemetry
Offline analysis needs a recording. Two ways to produce one, both writing the same NDJSON format:
nt-recorderCLI — a standalone process that records until stopped; best for long captures, background recording, or capturing before the agent connects. Seereferences/recording.mdfor flags, detached startup on Windows, and shutdown.nt_start_recording/nt_stop_recording— start immediately, perform the test, then stop to close the file and receive a compact receipt (recording_id,path, timing,rows,topic_count, ...) with no sample values. Discover topics withnt_get_recording_infoand query values withnt_query_recordingafter stopping. Also covered inreferences/recording.md.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 15d ago Changed · +6 lines bc392d1afc2a
- 1mo ago Changed · +10 lines 67295f92208f
- 1mo ago Changed · +2 lines 2bb17d695c03
- 1mo ago First seen · 29 lines · 25 tokens per session scan A ad7f9d6dd565
nt-mcp-workflow is a skill published in the GitHub repository Mzzj114/nt-mcp-server (1 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 677 once invoked, about $0.0001 per session on Opus 5.5. 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 skills, from other repositories
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…
doca-flow
DOCA Flow packet steering on NVIDIA NICs/DPUs, linked into a C application: match/action pipes, ports, representors, forwarding, hairpin, counters. Trigger on packet steering, classifier, rule-matching, representor, hairpin or 5-tuple-to-queue questions even when "DOCA Flow" is not named. Also covers pipe validation…
competition-firmware-layout
Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect bootloader or init…
diagnose-driver-install
Diagnose NVIDIA driver installation failures on DeepOps-managed nodes — nvidia-smi errors, "No devices were found", DKMS build failures, or GPU pods crash-looping. Use before reinstalling anything.
catc-troubleshoot
Catalyst Center troubleshooting workflows - device unreachable investigation, client connectivity issues, interface down analysis, site-wide outage triage, wireless roaming problems, integration with pyATS for CLI-level diagnostics. Use when the device is managed by Catalyst Center and you want its…