zaptrace-design-validation

zaptrace-design-validation is a skill for Claude Code from oaslananka/zaptrace. It costs 31 tokens per session (545 once invoked), scanned A, original, MIT.

A guide for checking a local ZapTrace design against requirements and engineering constraints. It covers checks such as electrical-rule and design-rule validation.

In plain words
What is it for?
Use it to inspect designs, review requirements and assumptions, run ERC and DRC checks, compare revisions, and create engineering findings reports.
Why use it?
It helps find design problems and document risks before an export or review, without treating automated results as fabrication approval.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the zaptrace plugin — 3 skills, 1 MCP server shipped together

Good fit Use it to inspect designs, review requirements and assumptions, run ERC and DRC checks, compare revisions, and create engineering findings reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oaslananka/zaptrace/zaptrace-design-validation
Install

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.

Any agent
npx skills add oaslananka/zaptrace --skill zaptrace-design-validation
Clone the repo
git clone --depth 1 https://github.com/oaslananka/zaptrace

Made for: Claude Code.

Or install zaptrace, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote 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.

agentmods badge for zaptrace-design-validation

README.md
[![agentmods](https://agentmods.dev/badge/skills/oaslananka/zaptrace/zaptrace-design-validation/github.svg)](https://agentmods.dev/skills/oaslananka/zaptrace/zaptrace-design-validation)
Your own site
<a href="https://agentmods.dev/skills/oaslananka/zaptrace/zaptrace-design-validation"><img src="https://agentmods.dev/badge/skills/oaslananka/zaptrace/zaptrace-design-validation/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.

agentmods 80×15 button for zaptrace-design-validation

Your own site · 80×15
<a href="https://agentmods.dev/skills/oaslananka/zaptrace/zaptrace-design-validation"><img src="https://agentmods.dev/badge/skills/oaslananka/zaptrace/zaptrace-design-validation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 545 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.00545
Opus 5 $0.00015 $0.00272
Sonnet 5 $0.00006 $0.00109
Haiku 4.5 $0.00003 $0.00055

Measured 9d ago against content hash ff9d1503ffcd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

zaptrace-design-validation 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 9d 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.

skills/zaptrace-design-validation/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ZapTrace Design Validation

Use this skill to inspect and validate an existing local ZapTrace design through the public MCP contract.

When to use

Use this skill for:

  • Parsing and inspecting a local design file
  • Requirements and assumption review
  • ERC and DRC execution
  • Electrical, mechanical, security, and testability evidence
  • Comparing two design revisions
  • Producing an engineering findings report before any export decision

Do not use this skill to approve fabrication, silently waive violations, expose an MCP/REST service to an untrusted network, or treat generated evidence as a substitute for qualified human review.

Required inputs

Collect:

  • Local design file or committed project path
  • Intended operating conditions and requirements
  • Applicable board, electrical, and manufacturing constraints
  • Expected validation scope
  • Existing waivers, assumptions, and known unsupported domains

MCP workflow

  1. Parse the local design with design_parse_file.
  2. Inspect the normalized design with design_inspect and design_list_nets.
  3. Review requirements and assumptions with requirements_parse and requirements_review when requirements are available.
  4. Run erc_validate; read the retained result with erc_get_result.
  5. Run drc_run; read the retained result with drc_get_result.
  6. Add bounded domain evidence with electrical_analysis, mechanical_review, security_review, and testability_report as applicable.
  7. Use design_diff when a before/after comparison is required.
  8. Keep unsupported, skipped, warning, and human-review-required states explicit.

Quality checks

A complete response must include:

  • Source design identity and revision where available
  • Requirements and assumptions
  • ERC and DRC summaries
  • Findings grouped by severity and domain
  • Unsupported or skipped checks
  • Recommended repairs or next validation steps
  • Explicit human-review boundary

Failure modes

Stop and report clearly when:

  • The design path is missing, ambiguous, or outside the approved local project
  • Parsing fails or the normalized design cannot be identified
  • ERC/DRC results are unavailable
  • Required constraints are missing
  • A requested domain is unsupported or only heuristic
  • The user asks to suppress findings without an engineering rationale

Read the full file on GitHub · 80 lines

Changes

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.

  1. 9d ago First seen · 80 lines · 31 tokens per session scan A ff9d1503ffcd

Subscribe to this mod's changes

zaptrace-design-validation is a skill published in the GitHub repository oaslananka/zaptrace (0 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 545 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 2026-08-31.

Related

Other skills, from other repositories

kicad

Use when designing electronic circuits and PCBs — schematic capture, PCB layout, 3D viewer, SPICE simulation, Gerber export. KiCad: the leading open-source EDA/PCB design suite.

znlgis/opengis-skills · 46 tokens

multisim-verify-requirements

A review method that turns circuit design requirements into measurable tests and checks them against Multisim experiment data. It reports each requirement as passed, failed, or not yet verified.

yxy050208/multisim-mcp · 45 tokens

altium-schematic-review

Review an Altium schematic (.SchDoc) — find unconnected pins, missing footprint links and net errors, then judge each candidate against the datasheet before calling it a defect. Triggers: "review this schematic", "check my circuit", "ERC", "floating pins", "unconnected", "any missing footprints", "does this schematic…

ScottJeong/altium-claude-skills · 251 tokens

pcb-design

Design, modify, review, validate, or export a KiCad schematic or PCB from natural-language hardware requirements. Use for circuit design, component selection, schematic capture, footprint assignment, board layout, routing, ERC/DRC, BOM, Gerbers, and manufacturing handoff through the KiCad MCP tools.

Avinash1286/KiCAD-MCP-Server-THEAVI · 65 tokens

kicad-library

Library management workflow for KiCAD — creating symbols, footprints, and managing libraries via MCP tools. Triggers on: "create a symbol", "make a footprint", "custom component", "register library", "find a part", "pin numbering", "new symbol", "new footprint", "add to library", "library path", "pad layout".

nevenfo/kicad-agentic-mcp · 77 tokens

kicad-pcb

Workflow skill for KiCAD PCB layout and routing via MCP tools. Triggers on: "layout the board", "route traces", "PCB", "place footprints", "copper pour", "board outline", "differential pair", "board setup", "track width", "via", "zone", "design rules", "stackup", "silkscreen".

nevenfo/kicad-agentic-mcp · 81 tokens