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.
git clone --depth 1 https://github.com/BeckhamLabsLLC/kicad-jlcpcbWrote 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/beckhamlabsllc/kicad-jlcpcb/pcb-new)<a href="https://agentmods.dev/commands/beckhamlabsllc/kicad-jlcpcb/pcb-new"><img src="https://agentmods.dev/badge/commands/beckhamlabsllc/kicad-jlcpcb/pcb-new/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.
<a href="https://agentmods.dev/commands/beckhamlabsllc/kicad-jlcpcb/pcb-new"><img src="https://agentmods.dev/badge/commands/beckhamlabsllc/kicad-jlcpcb/pcb-new.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.02790 |
| Opus 5.5 | $0.00016 | $0.01116 |
| Sonnet 5.5 | $0.00008 | $0.00558 |
| Haiku 4.5 | $0.00004 | $0.00279 |
Grade A, and why
pcb-new 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 1mo 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 — 176 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pcb-new
Take a text description of a PCB and deliver a ready-to-import KiCad board file the user drags into EasyEDA for routing and ordering.
Instructions
pcb_generateoverwrites the project's.kicad_pcb. It rebuilds the board from scratch and saves over the existing file — no merge, no backup. If the project already has a board the user may have opened in KiCad, say so and confirm before re-running.
1. Detect KiCad
Call detect_kicad. If meets_min is false, stop and pass the install_hint to the user. KiCad's pcbnew Python module is required by pcb_generate.
2. Check for a resumable session, then create or load the project
Ask the user where the project should live (default: current working directory) and what to name it.
If a <parent_dir>/<name>/ directory already exists:
- Call
load_projecton it. - If the response has
resume_available: true, show the user the session summary (stage, completed checkpoints, next step) and ask whether to resume or start a fresh project in a different directory. - If resuming, skip any step the session has already checkpointed (e.g. skip part sourcing if
parts_sourcedis already complete — just reuse the persistedbomand go to the BOM checkpoint).
Otherwise, call create_project with parent_dir and name. Each subsequent tool call automatically updates the session file, so mid-flow restarts are safe.
3. Decompose the description into a parts list
Read the user's description carefully. List the components the board will need: microcontroller, regulator, decoupling caps, connectors, indicator LEDs, etc. For each, write a one-line generic spec like "3.3V LDO, SOT-23-5, 500mA, basic-tier preferred".
4. Source parts
Dispatch one part-sourcer agent per generic spec, in parallel — a single message with one Task call per spec. Each agent applies the basic-first ladder and returns a structured pick. For parts the user already has LCSC C-numbers for, skip to step 5.
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.
- 1mo ago Changed · +25 lines 0a380efdd4e2
- 1mo ago Changed · +27 lines 0e962aaf242d
- 1mo ago First seen · 124 lines · 40 tokens per session scan A cc0c3c50d5d4
pcb-new is a command published in the GitHub repository BeckhamLabsLLC/kicad-jlcpcb (26 stars, last pushed 26d ago), licensed MIT. It adds 40 tokens to every session and 2,790 once invoked, about $0.0002 per session on Opus 5.5. 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
jensen-skills
Invoke Jensen Huang — Hardware & AI Infrastructure. Use for AI infrastructure planning, GPU and data center strategy, compute TCO analysis, and build-vs-buy decisions.
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
ccc-orchestrate
Run a sequential multi-agent workflow (feature, bugfix, refactor, security or custom chain) with structured handoffs, plus optional tmux and worktree workers for long-running sessions. Use when a task needs planner, implementer and reviewer stages in order.
environment-switching-local-cloud-ssh
The environment selector at the bottom of Claude Code switches where work executes: local for fast interactive iteration, cloud (Anthropic servers) for routines that must run with your machine off, SSH for driving a remote box like a VPS.
complete
Signal that a skill's work is complete. Triggers downstream subscriptions with "when": "complete" timing. Automatically invoked — do not run manually.
setup
A setup command for configuring claude-mini-hud as Claude Code's terminal status line. It lets the user choose Chinese, English, minimal, or ultra-minimal display text and writes the setting to Claude Code's configuration.