Borrowing it
Nothing to install: this file belongs to fireostendere/mcp_diptrace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fireostendere/mcp_diptrace/main/.agents/skills/diptrace-pcb-testpoints/SKILL.mdgit 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-pcb-testpoints)<a href="https://agentmods.dev/skills/fireostendere/mcp_diptrace/diptrace-pcb-testpoints"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/diptrace-pcb-testpoints/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-pcb-testpoints"><img src="https://agentmods.dev/badge/skills/fireostendere/mcp_diptrace/diptrace-pcb-testpoints.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 | $0.00091 | $0.00835 |
| Opus 5.5 | $0.00036 | $0.00334 |
| Sonnet 5.5 | $0.00018 | $0.00167 |
| Haiku 4.5 | $0.00009 | $0.00084 |
Grade A, and why
diptrace-pcb-testpoints 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 19d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DipTrace PCB Test Points
Headless PCB-only workflow over the DipTrace MCP server. For schematic-wired
test points use the separate diptrace-testpoints skill. Datasheets, DRC, and
manufacturability override anything here.
Parse the request
nets=explicit net list. Without it, build a proposal fromreview_testpoint_coverageplus design knowledge and confirm before writing.side=Top|Bottom— default Top.pad=<mm>probe pad diameter, default 1.0 mm;hole=<mm>default 0 (surface pad). Through-hole only when requested.grid=<mm>candidate grid, default 2.54 mm.mode=review|plan|apply. Direct "add testpoints" means apply, but show the placement table before committing.
Hard rules
- Always call
add_testpointswithdry_run=truefirst; commit only with the preview'sexpected_sha256. - Never place a TP on an RF antenna feed, crystal, switching node, reset, or high-impedance analog net unless the user explicitly names that net.
- One TP per net. Skip nets already covered by
list_testpoints. - Candidate generation avoids component/testpoint/keepout bounding boxes but NOT traces, vias, or pads. Sanity-check every chosen coordinate against routed geometry before committing, and run DRC after.
- The TP pad joins its net logically; copper still needs a pour (typical for GND) or a short stub trace to the nearest same-net pad. Escape beyond the pad copper edge plus applicable clearance before any via; via-in-pad stays disabled.
- Keep TPs off the board-edge margin (≥0.5 mm, more for pogo fixtures) and out of connector and tall-component shadows; enclosure shadowing is not modeled by the tools.
- Auto RefDes is
TP<n>; passrefdesonly to keep a fixture map stable.
Workflow
diptrace_status, thensummarize_designon the PCB path.- Baseline:
list_testpointsandreview_testpoint_coverage. - Choose target nets: functional signals worth probing; power/GND only when the user wants supply probing. List intentionally skipped nets with reasons.
find_testpoint_candidates(target_nets, side, probe_diameter, grid)— take rank 1–2 per net; prefer a spot near the driver/receiver pad so the stub stays short.- Show the table before editing:
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.
- 19d ago Changed 2400bed3772f
- 1mo ago First seen · 66 lines · 91 tokens per session scan A 961160e2b417
diptrace-pcb-testpoints is a skill published in the GitHub repository fireostendere/mcp_diptrace (25 stars, last pushed 15d ago), licensed Apache-2.0. It adds 91 tokens to every session and 835 once invoked, about $0.0004 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.
passport-device-test
Guide authorized flashing and on-device acceptance of FoloToy AI Passport firmware, including device discovery and bounded serial observation. Use for explicit device-test or flash requests, not merely because a build succeeded.