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 skills add raisoninme/boardless-pcb --skill step3-schematicgit clone --depth 1 https://github.com/raisoninme/boardless-pcbWrote 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/skills/raisoninme/boardless-pcb/step3-schematic)<a href="https://agentmods.dev/skills/raisoninme/boardless-pcb/step3-schematic"><img src="https://agentmods.dev/badge/skills/raisoninme/boardless-pcb/step3-schematic.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 | $0.00020 | $0.00954 |
| Opus 5 | $0.00010 | $0.00477 |
| Sonnet 5 | $0.00004 | $0.00191 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
step3-schematic 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 7d 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 3 · Schematic design (incl. component selection)
Session & state check (before touching anything)
- One step per session: if this session already did substantive work for another step, stop and ask for a fresh session.
- Read
docs/flow-state.md(canonical header line; foreign file → stop and ask). Missing → step1 first. Confirm step 2 isdone; read the pin-map carrier (path in flow-state),docs/pinmap.md,docs/dev-plan.md. Not satisfied → stop and report. - This step already
donewith no issue targeting it → re-run: ask intent first. Alreadyin-progress→ aborted or concurrent session: ask before proceeding. Markedrework→ redo what the rework note requires, then wrap up. - Issues-table entries with target step = 3 → fix mode.
- Set step 3
in-progress. Rebuild context from disk only.
Execute
Adopt-and-audit path: if flow-state/requirements record an inherited BOM, selection preference, or schematic (inherited: <path>), ingest it instead of re-selecting — then audit it per this step's own disciplines: budget-line contributions for every part, ★special-part flags, do-not-substitute identification; verified-rely-on parts get spot checks, new and changed parts get the full discipline. ERC and the netlist diff run regardless. The bar doesn't move; only the labor does.
Selection discipline
- Cheap-first + mainstream mass-production parts; prefer parts your assembly service stocks free of loading/setup fees (e.g. JLC's "basic library"); recompute operating points whenever changing values or library tiers
- With no physical verification available, RF goes on a pre-certified module, never a bare chip with self-routed RF
- Before rejecting a part, verify the rejection's factual claims ("out of stock", "no SPICE model" often collapse under an online check)
- Parameters that cannot be simulated (optics, aging, wear…) ship the vendor's conservative default
- ★Special-part flags, each with a reason: pricey / thin stock / single compatible vendor / critical-path do-not-substitute / self-sourced
- Parts whose datasheet worst-case values underpin the budget/review tables: no cheap substitution (swapping the part swaps out the evidence)
- Check every part's contribution to each hard budget line in the plan (current, cost, height, …) line by line; any line over its cap → selection rollback (a part whose contribution cannot be closed at design time gets cut — e.g. an always-powered part with no credible quiescent-current figure)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 42 lines · 20 tokens per session scan A fb400b08bc90
step3-schematic is a skill published in the GitHub repository raisoninme/boardless-pcb (2 stars, last pushed 24d ago), licensed MIT. It adds 20 tokens to every session and 954 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
kicad-jlcpcb-workflow
Use this skill when the user asks to "design a PCB", "make a board", "build a PCB project", "order from JLCPCB", "create a schematic", "source LCSC parts", "wire up a board", "generate a PCB from a BOM", or any KiCad + JLCPCB workflow. Also use when working with .kicadpro or .kicadpcb files. Phase 1.6 handles project…
spark-environment-setup
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
kicad
Analyze KiCad projects and PDF schematics: schematics, PCB layouts, Gerbers, footprints, symbols, netlists, and design rules. Reviews designs for bugs, traces nets, cross-references schematic to PCB, extracts BOM data, checks DRC/ERC, DFM, power trees, and regulator circuits. Every finding carries a confidence label…
lcsc
Search LCSC Electronics for electronic components — find parts by LCSC number (Cxxxxx) or MPN, check stock/pricing, download datasheets, analyze specifications. Sister company to JLCPCB, same parts library. Sync and maintain a local datasheets directory for a KiCad project, or use batch MPN-list seeding (--mpn-list)…
telephony-and-conferencing
Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…