KiCadRoutingTools: Skill for Claude Code

.claude/skills/stress-test-router/SKILL.md

stress-test-router is a skill for Claude Code from drandyhaas/KiCadRoutingTools. It costs 69 tokens per session (3,215 once invoked), scanned A, original, MIT.

A large-scale test process for a KiCad circuit-board router using real open-source boards. It removes existing routes, routes the boards again, measures completion and DRC errors, and can prepare new GitHub issues for approval.

In plain words
What is it for?
Use it to download and prepare board examples, run routing regression tests, validate board files, collect routing and design-rule results, and identify new router or parser problems.
Why use it?
It shows whether router changes work across many realistic boards instead of only on small test examples, while keeping downloaded test boards outside the code repository.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents.

This is drandyhaas/KiCadRoutingTools's own configuration. It tells Claude Code how to work on KiCadRoutingTools itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything KiCadRoutingTools configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash tests/stress/run_queue.sh [max_concurrency=8] [model=sonnet].

Reuse

Borrowing it

Nothing to install: this file belongs to drandyhaas/KiCadRoutingTools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/drandyhaas/KiCadRoutingTools/main/.claude/skills/stress-test-router/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/drandyhaas/KiCadRoutingTools

Made for: Claude Code.

Wrote 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.

agentmods badge for stress-test-router

README.md
[![agentmods](https://agentmods.dev/badge/skills/drandyhaas/kicadroutingtools/stress-test-router/github.svg)](https://agentmods.dev/skills/drandyhaas/kicadroutingtools/stress-test-router)
Your own site
<a href="https://agentmods.dev/skills/drandyhaas/kicadroutingtools/stress-test-router"><img src="https://agentmods.dev/badge/skills/drandyhaas/kicadroutingtools/stress-test-router/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.

agentmods 80×15 button for stress-test-router

Your own site · 80×15
<a href="https://agentmods.dev/skills/drandyhaas/kicadroutingtools/stress-test-router"><img src="https://agentmods.dev/badge/skills/drandyhaas/kicadroutingtools/stress-test-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,215 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 59
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.03215
Opus 5 $0.00034 $0.01607
Sonnet 5 $0.00014 $0.00643
Haiku 4.5 $0.00007 $0.00321

Measured 9d ago against content hash 8ba9a08af68e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

stress-test-router 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 9d 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.

.claude/skills/stress-test-router/SKILL.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stress-Test Router on Real-World Boards

Run the tests/stress/ harness end-to-end: prepare the board corpus, route every board following the plan-pcb-routing skill workflow, aggregate completion/DRC statistics, and turn novel findings into GitHub issues.

All corpus artifacts live OUTSIDE the repo in $STRESS_DIR (default ~/Documents/kicad_stress_test). Never commit boards to the repo.

Step 1: Prepare the corpus (skip parts that already exist)

Check $STRESS_DIR/boards_unrouted/*.kicad_pcb first — if the corpus exists and parses (run tests/stress/validate_boards.py), skip to Step 2.

cd tests/stress
python3 fetch_boards.py            # downloads from GitHub (needs `gh` auth)

KIPY=/Applications/KiCad/KiCad.app/Contents/Frameworks/Python.framework/Versions/Current/bin/python3
$KIPY normalize_boards.py          # pcbnew round-trip -> current format
for f in "$STRESS_DIR"/boards/*.kicad_pcb; do   # ONE board per process
  $KIPY strip_routing.py "$(basename "${f%.kicad_pcb}")"
done
python3 validate_boards.py         # all boards must parse with sane stats

Platform note: on Linux/Windows find the KiCad-bundled python equivalent, or any python with a working pcbnew module of KiCad 9+.

To extend the corpus, add (owner/repo, note) entries to REPOS in fetch_boards.py and a fragment->name mapping in normalize_boards.py. Only KiCad 6+ sources survive; older ones are rescued by the pcbnew round-trip.

Step 2: Run boards (queue manager)

Drive the whole corpus with the queue manager — it keeps headless claude -p board workers in flight until every board has a results JSON, deriving all state from disk (safe to stop and restart):

bash tests/stress/run_queue.sh [max_concurrency=8] [model=sonnet]
bash tests/stress/stress_status.sh        # monitor: DONE/RUNNING/TODO + free slots

run_queue.sh auto-launches tests/stress/queue_watchdog.sh, which caps per-board attempts (default 3, QUEUE_MAX_LAUNCH) and stubs a FAILED results JSON for any board whose worker keeps dying without writing one — otherwise the queue relaunches it forever and never terminates. The watchdog also runs standalone next to a manually-driven queue.

Read the full file on GitHub · 218 lines

Changes

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.

  1. 9d ago First seen · 218 lines · 69 tokens per session scan A 8ba9a08af68e

Subscribe to this mod's changes

stress-test-router is a skill published in the GitHub repository drandyhaas/KiCadRoutingTools (400 stars, last pushed yesterday), licensed MIT. It adds 69 tokens to every session and 3,215 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

boardrepo

Read and review real PCB projects on BoardRepo. Search published hardware designs, open a board's schematic connectivity, bill of materials and files, run KiCad's DRC and ERC, and check a design against a fabrication house's limits. Use whenever the user names a BoardRepo board or URL, asks to find a published board…

flintt-dev/boardrepo-plugin · 156 tokens

jetson-video-pipeline

Use when executing and verifying Jetson Video Codec SDK or PyNvVideoCodec encode/decode, transcode, segmentation, container decode, AV1, or acceptance workflows with exact artifact handoffs.

NVIDIA/skills · 45 tokens

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.

NVIDIA/skills · 50 tokens

holohub-app-lifecycle

Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.

NVIDIA/skills · 40 tokens

code-plan

Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).

initializ/forge · 29 tokens

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…

Mindrally/skills · 87 tokens