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/layout-journalgit 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/layout-journal)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/layout-journal"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/layout-journal.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 | $0.00050 | $0.02142 |
| Opus 5 | $0.00025 | $0.01071 |
| Sonnet 5 | $0.00010 | $0.00428 |
| Haiku 4.5 | $0.00005 | $0.00214 |
Grade A, and why
layout-journal 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layout journal
Keep a LAYOUT_NOTES.md journal alongside a board while hand-routing it, so the reasoning behind manual copper is not lost when the scratch workspace is (a reboot, a new worktree, a hand-off to another agent or the owner). The committed board artifact is shipping truth; this journal is the why behind it. This skill generalizes the hand-router-session convention proven during kicad-tools' own manufacturing hand-routing work — it hardcodes no board and no fixture.
The
kctnamespace. This skill lives in.claude/commands/kct/— the kicad-tools-native, harness-agnostic agent-tool namespace, invoked as/kct:layout-journal. It runs from inside a consumer repo and assumes nothing about the current directory being the kicad-tools repo.
Why this skill exists
Hand-routing is iterative and the intermediate reasoning is fragile: which nets you ripped and why, which corridor you chose, what the referee said after each pass, what is still blocked and on whom. Scratch state (/tmp, un-committed working notes) is routinely lost on reboot. A LAYOUT_NOTES.md committed next to the board preserves that journal as durable, reviewable truth — the same reason artifact-first treats the committed board as canonical (Epic #4054 convention #3). Without it, a resumed session re-derives decisions that were already made and paid for.
Prerequisite
The native router/DRC backend must be built in the active checkout so the referee gate (below) runs at full speed:
uv run kct build-native --check # expect: "C++ backend: available"
uv run kct build-native # if "not installed"
Model selection
suggestedModel: sonnet. Maintaining a structured journal and running a referee gate is disciplined record-keeping, not frontier judgment. Model resolves through the harness's normal precedence chain.
Arguments
Arguments: $ARGUMENTS
$ARGUMENTS is <board-path> [--entry "<free text>"].
| Token | Meaning |
|---|---|
<board-path> |
Required. Path to the board being hand-routed (a *.kicad_pcb, or a board directory containing one). The journal is written to <board-dir>/LAYOUT_NOTES.md, derived from this token — never a hardcoded board directory. |
--entry "<free text>" |
Append a single dated session entry describing what you just did (the nets touched, the decision, the referee result). Optional; if omitted, the skill creates/updates the journal skeleton and prompts for the first entry. |
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 · 130 lines · 50 tokens per session scan A c68e42df102e
layout-journal is a command published in the GitHub repository rjwalters/kicad-tools (55 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 2,142 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.
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).