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 fireostendere/mcp_diptrace --skill diptrace-board-bringupgit clone --depth 1 https://github.com/fireostendere/mcp_diptraceWrote 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/fireostendere/mcp_diptrace/diptrace-board-bringup)<a href="https://agentmods.dev/skills/fireostendere/mcp_diptrace/diptrace-board-bringup"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/diptrace-board-bringup/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/fireostendere/mcp_diptrace/diptrace-board-bringup"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/diptrace-board-bringup.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 | $0.00087 | $0.01019 |
| Opus 5.5 | $0.00035 | $0.00408 |
| Sonnet 5.5 | $0.00017 | $0.00204 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
diptrace-board-bringup 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 1mo 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read runtime access before selecting tools or declaring a capability unavailable. MCP tools and native/headless CLI are separate interfaces.
DipTrace board bring-up and production test
RAG: engineering memory by default — shared workflow. Use indexed measurement, circuit and bring-up material to derive the test sequence, probe strategy, limits and fault-isolation plan for this exact board.
Use the exact schematic/PCB, fitted BOM, component rules, release evidence, and firmware revision. Planning produces a procedure; a physical test passes only from actual observed measurements. Do not energize or flash hardware from a planning request.
Prepare the procedure
- Resolve board revision and unit/serial identity, assembly/rework state, available instruments, supply, programming interface, and requested mode: plan or guided run. Check pinouts and testpoint nets from the actual design; do not reuse another board's connector order.
- Read
rules/and the project specification. For every measurement define the condition/load, probe points and reference, method, expected range/tolerance, source/calculation, and stop condition. - Derive supply voltage, initial current limit, rail/startup expectations, and thermal limits from this design and the instruments. Leave unknown values unresolved. Never choose a universal current limit or infer a short from a generic resistance threshold. Inspect low-resistance rails and charging capacitors in context.
- Plan access to power/GND, reset/boot, debug, and representative interfaces. If PCB changes are requested, use testpoint-planner and an ECO; existing connector access may suffice. Do not load sensitive RF, crystal, high-impedance, or fast nets with an unspecified probe or long stub.
First article sequence
- Unpowered inspection: correct parts/variant, orientation/polarity, solder bridges, connector mating, exposed pads, missing/DNP parts, and known assembly defects.
- With power removed, check ground and supply continuity/resistance and isolation required by the design. Account for capacitors and parallel semiconductor paths.
- Power from the specified current-limited source using the approved connection sequence. Observe input current, rails, sequencing, reset, and heating. Stop and remove power on a defined limit violation, unexpected heating, or abnormal behavior; record the fault before retrying.
- Use the exact target/programmer and verify device identity before flashing. Record firmware hash, boot configuration, programming/verification results, and logs. Mass erase, irreversible fuses, and security provisioning require their own scope. Use an installed flashing/serial tool only after discovering its actual capability.
- Exercise one subsystem at a time, then combined loads and interfaces. Test RF last when present. Compare measurements with the planned bounds; a missing instrument leaves that test NOT_RUN, not PASS.
- For failures, preserve logs and measurements, isolate the owning subsystem, and record any physical rework as an ECO through diptrace-revision-review.
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.
- 1mo ago First seen · 79 lines · 87 tokens per session scan A 6d57c115641c
diptrace-board-bringup is a skill published in the GitHub repository fireostendere/mcp_diptrace (24 stars, last pushed 4d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,019 once invoked, about $0.0003 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 2026-09-13.
Other skills, from other repositories
jetson-video-pipeline
Use when planning, executing, and independently validating Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or concise acceptance workflows.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
SmartHome Video Anomaly Benchmark
VLM evaluation suite for video anomaly detection in smart home camera footage.
holohub-app-lifecycle
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.
passport-build
Validate and package FoloToy AI Passport firmware, including a verified merged image and matching debugging artifacts. Use for build, test, and firmware-package requests; does not flash, commit, or publish.
ros2-robotics
Best practices for ROS 2 robotics development, covering package structure, nodes, topics/services/actions, launch files, QoS, tf2 transforms, and testing. Use when creating ROS 2 packages, writing nodes in rclpy or rclcpp, defining custom messages/services/actions, writing launch files, configuring QoS profiles…