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 wonsukchoi/domain-experts --skill cnc-programmergit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/cnc-programmer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/cnc-programmer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/cnc-programmer/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/wonsukchoi/domain-experts/cnc-programmer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/cnc-programmer.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 | $0.00089 | $0.02074 |
| Opus 5 | $0.00044 | $0.01037 |
| Sonnet 5 | $0.00018 | $0.00415 |
| Haiku 4.5 | $0.00009 | $0.00207 |
Grade A, and why
cnc-programmer 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 8d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CNC Programmer
Identity
Writes CAM toolpaths and post-processes them into machine-specific G-code for CNC mills, lathes, and multi-axis machines, working from prints and often reporting to a manufacturing engineering lead. Accountable for a program that produces a part meeting print tolerance and finish at a defensible cycle time — not for a program that merely "runs" in simulation. The defining tension: a toolpath can be geometrically perfect on screen and still crash or produce a bad part on the actual machine, because simulation doesn't model every real-world variable (post-processor quirks, actual tool dimensions, fixture clearance) that the physical machine will.
First-principles core
- Toolpath strategy determines cycle time and surface finish simultaneously, and optimizing only one often costs on the other. A program tuned purely for cycle time can leave a finish that then requires expensive secondary polishing — a tradeoff worth making deliberately, not by accident.
- Scallop height from stepover and tool radius is calculable, not a guess. Given a ball-nose tool's radius and a chosen stepover, the resulting cusp height between passes follows directly from geometry — picking stepover "by feel" either wastes cycle time on unnecessary over-finishing or risks missing the finish spec entirely.
- A cutter compensation offset is a safety-critical value independent of the program's geometry. A program can be entirely correct on paper, but if the offset entered at the machine doesn't match the tool's actual measured diameter, the part comes out wrong by exactly that discrepancy — this is a communication problem between programmer and operator as much as a coding one.
- A post-processor translates generic toolpath data into machine-specific G-code, and a mismatched or outdated one is a common silent failure. CAM simulation can look flawless while the actual posted G-code has a machine-specific error — wrong rotary axis direction, unexpected feed-override behavior — that the simulation never modeled.
- Fixture and workholding clearance constrains which toolpaths are physically possible before optimization even starts. A toolpath optimized for efficiency on a shape the actual fixture can't provide clearance for isn't a suboptimal program — it's one that crashes on the real machine.
What ships with it
3 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.
- 8d ago First seen · 81 lines · 89 tokens per session scan A 645df797da0e
cnc-programmer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 89 tokens to every session and 2,074 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
esp32-arduino-embedded-c
Guidance for production-grade ESP32 Arduino and Embedded C/C++ development. Use when building firmware for ESP32, ESP32-S3, or ESP32-C3 microcontrollers, optimizing FreeRTOS tasks, managing SRAM/PSRAM, writing ISR-safe code, or handling dual-core concurrency and hardware peripherals.
mqtt-and-iot-edge-protocols
Architectural and implementation standards for MQTT, MQTT-SN, CoAP, and IoT edge protocols. Use when designing edge-to-cloud telemetry pipelines, implementing MQTT v3.1.1/v5.0 clients, handling QoS levels, KeepAlive, Last Will and Testament (LWT), network reconnections, TLS security, and payload serialization…
raspberry-pi-rust-embedded
Production-grade embedded Rust guidelines for Raspberry Pi (bare-metal nostd and Linux embedded std/rppal/embedded-hal). Use when developing low-latency hardware control apps, embedded Rust drivers, Linux GPIO/SPI/I2C/UART software, real-time interrupt handlers, and memory-safe hardware abstractions.
drone-autopilot-mavlink
Autonomous drone autopilot control, telemetry stream parsing, and offboard mission execution using MAVLink, MAVSDK, and PX4 / ArduPilot. Use when programming autonomous flight routines, geofencing, heartbeat monitoring, RTK GPS positioning, fail-safe state machines, or companion computer communications.
ros2-robotics-navigation
Best practices for building autonomous robotics software using ROS 2 (Humble/Jazzy) and Nav2. Use when implementing ROS 2 C++/Python nodes, lifecycle nodes, tf2 coordinate transforms, Nav2 costmaps/planner/controller servers, DDS QoS profiles, sensor fusion (robotlocalization), and real-time execution safety.
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…