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 sbrunner-atx/fldigi-mcp --skill fldigi-operatinggit clone --depth 1 https://github.com/sbrunner-atx/fldigi-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/skills/sbrunner-atx/fldigi-mcp/fldigi-operating)<a href="https://agentmods.dev/skills/sbrunner-atx/fldigi-mcp/fldigi-operating"><img src="https://agentmods.dev/badge/skills/sbrunner-atx/fldigi-mcp/fldigi-operating/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/sbrunner-atx/fldigi-mcp/fldigi-operating"><img src="https://agentmods.dev/badge/skills/sbrunner-atx/fldigi-mcp/fldigi-operating.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 | $0.00100 | $0.01160 |
| Opus 5 | $0.00050 | $0.00580 |
| Sonnet 5 | $0.00020 | $0.00232 |
| Haiku 4.5 | $0.00010 | $0.00116 |
Grade A, and why
fldigi-operating 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 11d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating fldigi: TX/RX handoff and RX polling
The one rule that matters most
Never poll the TX buffer to decide when to stop transmitting. fldigi never auto-stops on an empty buffer — it holds PTT and sends idle until something explicitly returns it to receive. Detecting "buffer empty" from outside always lags, and you transmit idle carrier on top of the station answering you.
Instead, end every over with the inline return-to-receive control character
^r. The transmit → send operation does this for you.
Transmitting an over
transmit → send "<over text>\n" (return_to_rx=true, the default)
One call: clears the TX buffer, appends ^r, keys the radio. When the modem
reaches ^r — the exact sample the last real character finishes — fldigi
drops to RX instantly. No polling, no lag, no lingering carrier.
- End each message with a real newline character (
\n) so the receiving station's display advances a line. Do not use the two-character string^n— it is transmitted literally as caret-n. - If an over must be built incrementally with
text → add_tx, the lastadd_txmust end in^rbeforetransmit → tx, and nothing may be added after it.
The three ways to stop, and when to use each
| Operation | Behavior | Use for |
|---|---|---|
^r in stream (via send) |
Graceful auto-return the moment the over ends | Every normal over |
transmit → abort |
Immediate stop, discards queued text | Panic button: caller came back early, wrong message, operator says stop |
transmit → rx |
Returns to RX only after the buffer drains | Almost never — it is slow and is not the stop button |
Waiting for TX to finish
After send, poll controls → get_trx_status until it returns "rx".
A BPSK31 over of 2–4 short lines takes roughly 15–30 seconds; poll at a
relaxed interval rather than hammering the API.
Listening: RX buffer discipline
Track the RX stream by position, reading only deltas:
text → rx_length→ current end position.text → readfrom your last known position to the new length.- Save the new position.
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.
- 11d ago First seen · 107 lines · 100 tokens per session scan A 7011d6e7eff6
fldigi-operating is a skill published in the GitHub repository sbrunner-atx/fldigi-mcp (0 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 1,160 once invoked, about $0.0005 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 skills, from other repositories
contest-operating
Run a contest operating loop end-to-end: call CQ, work callers through the exchange, handle QRM/garble/no-copy situations, and log completed QSOs to N3FJP via n3fjp-mcp. Use for ARRL Field Day and similar exchange-based contests on digital modes (pairs with the fldigi-operating skill in fldigi-mcp for radio control).…
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hyperpod-version-checker
Check and compare software component versions on SageMaker HyperPod cluster nodes - NVIDIA drivers, CUDA toolkit, cuDNN, NCCL, EFA, AWS OFI NCCL, GDRCopy, MPI, Neuron SDK (Trainium/Inferentia), Python, and PyTorch. Use when checking component versions, verifying CUDA/driver compatibility, detecting version mismatches…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.