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 agentmods add commands/rjwalters/kicad-tools/hv-isolation-loopgit clone --depth 1 https://github.com/rjwalters/kicad-toolsWrote 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/commands/rjwalters/kicad-tools/hv-isolation-loop)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/hv-isolation-loop"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/hv-isolation-loop.svg" alt="Measured on agentmods" 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 | $0.00086 | $0.03905 |
| Opus 5 | $0.00043 | $0.01953 |
| Sonnet 5 | $0.00017 | $0.00781 |
| Haiku 4.5 | $0.00009 | $0.00391 |
Grade A, and why
hv-isolation-loop 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 6d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HV-isolation design loop
Drive a non-isolated-mains or high-voltage-bank board from a raw floorplan to a creepage-closed, sign-off-ready layout. This skill is the orchestration layer over the shipped kct HV commands: it sequences voltage-domain capture, per-pair creepage targets, HV plane-void generation, HV-aware placement, routing, and the isolation gates into one coherent runbook, then hands the decision and fab sign-off steps off to the sibling skills.
It complements, not duplicates, /kct:ee-review (which writes the decision document) and /kct:manufacturing-readiness / /kct:tapeout (which do fab sign-off). This skill drives the layout to closure and calls those skills at the right steps.
The
kctnamespace. This skill lives in.claude/commands/kct/— the kicad-tools-native, harness-agnostic agent-tool namespace, invoked as/kct:hv-isolation-loop. Keep kicad-tools' own agent tools here, not under.claude/commands/loom/or.loom/roles/: that tree is installed into this repo from rjwalters/loom and belongs to the loom framework. Thekctnamespace is deliberately harness-agnostic — it hosts kicad-tools-native skills that live alongside installable harness frameworks (loom, rjwalters/anvil, or any future orchestrator). It runs from inside a consumer repo that depends on kicad-tools as auvdependency (kct ...is onPATHvia the venv); it does not assume the current directory is the kicad-tools repo, and it hardcodes no board path and no fab tier.
Scope (advisory / orchestration only). This skill sequences commands and states gates. It does not itself route copper, place parts, or edit the
.kicad_pcbbeyond invoking the documented mutating commands, and it never self-applies a work label. The one human-judgment input — the voltage-map sidecar (net → volts) — is authored by a qualified EE, and the human EE ratifies the result before fabrication. Derived IEC creepage/clearance values are an engineering aid, NOT a certification: the governing standard and a qualified engineer remain authoritative (same disclaimer asmanufacturing-readinessGate 4).
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.
- 6d ago First seen · 187 lines · 86 tokens per session scan A 377c8a35ed36
hv-isolation-loop is a command published in the GitHub repository rjwalters/kicad-tools (55 stars, last pushed yesterday), licensed MIT. It adds 86 tokens to every session and 3,905 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 2026-08-30.
Other commands, from other repositories
observe
部屋を能動的に観察する。3つの基本ブロックを自由に選びながらループし、受動的なスナップショットではなく発見のある観察を行う。.
model
Check if an AI model fits on your GPU before downloading.
compliance-matrix
Gestiona matriz de conformidad con estándares regulatorios (CE, FCC, UL, RoHS, ISO). Permite definir estándares, trackear estado de requisitos, vincular evidencia, identificar gaps y generar reportes de cumplimiento.
eol-report
EOL/EOS risk report — devices, OS versions, and firmware approaching or past end-of-life/end-of-support, prioritized by criticality.
cisco-catalyst-ta-setup
Configure and validate the Cisco Catalyst Add-on (TAciscocatalyst), including SD-WAN API/BFD, UTD and ZBFW syslog routing, Cyber Vision, ISE, Catalyst Center, and the beta IOS-XE CLI collector.
gum-search
BM25 search the embedded catalog (TTY table, pipe JSON).