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/helpgit 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/help)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/help"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/help.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 | $0.00045 | $0.01683 |
| Opus 5 | $0.00023 | $0.00842 |
| Sonnet 5 | $0.00009 | $0.00337 |
| Haiku 4.5 | $0.00005 | $0.00168 |
Grade A, and why
help 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 4d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kct help
Orient a user inside a consumer PCB-design repo that has kicad-tools installed:
which /kct:* skills are present, what each one is for, the load-bearing
conventions, and where to start. This is a meta-skill — it describes the
other skills by reading the files actually vendored under
.claude/commands/kct/, so it never drifts from a version-skewed or
--skills=-filtered install.
The
kctnamespace. This skill lives in.claude/commands/kct/— the kicad-tools-native, harness-agnostic agent-tool namespace, invoked as/kct:help. It runs from inside a consumer repo and assumes nothing about the current directory being the kicad-tools source checkout.
Strictly read-only. This skill only reads
.mdfiles and (optionally).kct/install-metadata.jsonto describe what is installed. It never invokes another/kct:*skill, never opens/modifies/routes/checks/exports a.kicad_pcb, and never writes any file. It takes no board argument because it never touches a board. See the Notes section.
Model selection
suggestedModel: sonnet. Reading frontmatter and rendering an orientation
table is summarization, not frontier judgment. Model resolves through the
harness's normal precedence chain (explicit dispatch param → harness role
config → this doc's frontmatter suggestedModel → session default).
Arguments
Arguments: $ARGUMENTS
$ARGUMENTS is [<command>] — an optional skill name (e.g. ee-review).
It is not a board path: this skill takes no board argument and touches no
board.
| Token | Meaning |
|---|---|
| (none) | Overview mode. Render a one-screen orientation: every installed /kct:* skill (one line each from its frontmatter), the load-bearing conventions, and a "start here" pointer. |
<command> |
Detail mode. Summarize exactly one installed skill (<command>.md): its usage/arguments, what it does, one concrete example invocation, and whether it is read-only or writes to the board. If <command>.md does not exist, say so and fall back to the overview's skill list. |
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.
- 4d ago First seen · 135 lines · 45 tokens per session scan A 9bcae26e0677
help is a command published in the GitHub repository rjwalters/kicad-tools (53 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,683 once invoked, about $0.0002 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
git
Git operations with intelligent commit messages and workflow optimization.
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.
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.