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/readmegit 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/readme)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/readme"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/readme.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 | $0.00000 | $0.00787 |
| Opus 5 | $0.00000 | $0.00394 |
| Sonnet 5 | $0.00000 | $0.00157 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
README 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kct slash-command namespace
This directory holds kicad-tools-native agent skills, invoked as /kct:<name>.
Why a separate namespace?
The .claude/commands/loom/ tree (and .loom/roles/) is installed into this repo
from rjwalters/loom and belongs to the loom
orchestration framework — kicad-tools should not add its own skills there. The kct
namespace is deliberately harness-agnostic: it hosts kicad-tools' own agent tools
so they live alongside any installable harness framework (loom,
rjwalters/anvil, or a future orchestrator)
without colliding with vendored content.
Convention: kicad-tools-native agent tools go under .claude/commands/kct/ and are
invoked as /kct:<name>. Do not place them under .claude/commands/loom/ or .loom/roles/.
Available skills
| Command | Purpose | Model |
|---|---|---|
/kct:help [<command>] |
Explain the installed /kct:* skills — what each does, how to invoke it, and the load-bearing conventions — by reading the files actually vendored in this repo. Introspective and strictly read-only; no board argument. |
sonnet |
/kct:ee-review <issue-or-board> |
Produce an EE decision document (escalating intervention ladder + binding constraints, cited and confidence-graded) for an analog/placement-blocked board. Advisory only — decisions, not copper. | opus |
/kct:manufacturing-readiness <board-path> |
Sign off a routed board for fabrication: kct check + the mandatory kicad-cli pcb drc --refill-zones cross-gate + a kct export bundle at the board's fab tier. Refuses sign-off if any gate is skipped. |
sonnet |
/kct:hv-isolation-loop <board-path> |
Drive the HV-isolation / creepage design loop on a mains/high-voltage board: voltage-domain capture → per-pair creepage targets → HV plane-voids (zones hv-keepout) → HV-aware placement (optimize-placement --voltage-map) → route/reinforce → creepage + Kelvin + --refill-zones gates → EE-review + sign-off handoff. Orchestration only; the human EE authors the voltage map and ratifies before fab. |
sonnet |
/kct:board-recipe-scaffold <board-path> |
Scaffold a new consumer board recipe (generate_design.py) following the artifact-first convention: project → schematic+ERC → PCB → route+pour → check → LVS hard gate → export, with circuit-specific parts left as fill-in points. |
sonnet |
/kct:layout-journal <board-path> |
Keep a LAYOUT_NOTES.md journal for a hand-routing session so the reasoning behind manual copper (decisions, rip-ups, referee results, blockers) survives reboots and hand-offs. |
sonnet |
/kct:tapeout <board-path> [--assembly|--pcb-only] |
Produce a complete, fab-ready export bundle — or refuse loudly. Superset of /kct:manufacturing-readiness: the three sign-off pre-gates plus a BOM part-number-resolution gate, schematic + assembly-view PDFs, a human README, and a manifest checksumming the entire bundle. "tapeout returned 0" means "upload this directory as-is." |
sonnet |
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 · 29 lines · 0 tokens per session scan A 24f5959817b2
README is a command published in the GitHub repository rjwalters/kicad-tools (55 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 787 tokens. 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.