agentmods.dev

ki-stack-orient

ki-stack-orient is a skill for Claude Code from Milind220/Ki-Stack. It costs 64 tokens per session (1,419 once invoked), scanned A, original, MIT.

A starting guide for KiCad, a tool for designing circuit boards, that locates project files and checks which KiCad automation options are available. It helps choose between live editor control, command-line tools, and structured file edits.

In plain words
What is it for?
Use it at the beginning of KiCad work to orient yourself, find the project, check the installed tools, and select a suitable workflow for editing, rendering, verification, or parts search.
Why use it?
It prevents choosing the wrong way to handle a KiCad task, especially when the task depends on the current board selection, rendering, or file structure.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions OpenCode.

not rated 23repo 4mo ago A scan 64 tokens original MIT

Good fit Use it at the beginning of KiCad work to orient yourself, find the project, check the installed tools, and select a suitable workflow for editing, rendering, verification, or parts search.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/milind220/ki-stack/ki-stack-orient
View source ↗ Milind220/Ki-Stack
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 Milind220/Ki-Stack --skill ki-stack-orient
Clone the repo
git clone --depth 1 https://github.com/Milind220/Ki-Stack

Made for: Claude Code.

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 ki-stack-orient

README.md
[![agentmods](https://agentmods.dev/badge/skills/milind220/ki-stack/ki-stack-orient/github.svg)](https://agentmods.dev/skills/milind220/ki-stack/ki-stack-orient)
Your own site
<a href="https://agentmods.dev/skills/milind220/ki-stack/ki-stack-orient"><img src="https://agentmods.dev/badge/skills/milind220/ki-stack/ki-stack-orient/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 ki-stack-orient

Your own site · 80×15
<a href="https://agentmods.dev/skills/milind220/ki-stack/ki-stack-orient"><img src="https://agentmods.dev/badge/skills/milind220/ki-stack/ki-stack-orient.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,419 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 $0.00064 $0.01419
Opus 5.5 $0.00026 $0.00568
Sonnet 5.5 $0.00013 $0.00284
Haiku 4.5 $0.00006 $0.00142

Measured 1mo ago against content hash e5dc839f2fa6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ki-stack-orient 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.

skills/ki-stack/ki-stack-orient/SKILL.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ki-stack-orient

Preamble (run first)

Run this before choosing a KiCad workflow:

KI_STACK_DIR="${KI_STACK_DIR:-skills/ki-stack}"
"$KI_STACK_DIR/bin/ki-stack-update-check" 2>/dev/null || true
"$KI_STACK_DIR/bin/kicad-project-find" . 2>/dev/null | sed -n '1,80p' || true
"$KI_STACK_DIR/bin/kicad-version" 2>/dev/null || true
"$KI_STACK_DIR/bin/kicad-python-smoke" 2>/dev/null || true

Read these when the task touches the area:

  • skills/ki-stack/ETHOS.md
  • skills/ki-stack/references/version-matrix.md
  • skills/ki-stack/references/render-recipes.md
  • skills/ki-stack/references/ipc-recipes.md
  • skills/ki-stack/references/ipc-board-workflows.md
  • skills/ki-stack/references/file-editing-recipes.md

Stack Rules

  • PCB editor interaction or current selection: use kicad-python IPC.
  • Render, import/export, DRC, ERC, fabrication, 3D outputs: use kicad-cli.
  • Schematic/library/project file edits: use kicad-skip, kiutils-rs, or another structured parser. Do not hand-roll S-expression edits when a parser fits.
  • Parts search and KiCad-ready vendor artifacts: check https://pcbparts.dev/ early.
  • File format truth: use KiCad developer file-format docs at https://dev-docs.kicad.org/en/file-formats/.
  • No success claim without evidence: artifact path, DRC/ERC output, changed file list, or script output.

Completion Status

  • DONE: completed and verified.
  • DONE_WITH_CONCERNS: completed but proof is partial, version-limited, or blocked by pre-existing issues.
  • BLOCKED: prerequisite unavailable or command failed after a concrete attempt.
  • NEEDS_CONTEXT: target file, object, board session, or intended result is unclear.

Purpose

This is the first skill for KiCad work. It makes the agent stop guessing and quickly answer:

  1. What KiCad files are present?
  2. What KiCad version and CLI are available?
  3. Are Python IPC bindings installed?
  4. Is a live KiCad board reachable?
  5. Which substrate should do the work?

Read the full file on GitHub · 137 lines

Files

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.

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. 1mo ago First seen · 137 lines · 64 tokens per session scan A e5dc839f2fa6

Subscribe to this mod's changes

ki-stack-orient is a skill published in the GitHub repository Milind220/Ki-Stack (23 stars, last pushed 4mo ago), licensed MIT. It adds 64 tokens to every session and 1,419 once invoked, about $0.0003 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 2026-08-31.

Hardware and IoTagent-skillsai-agentselectronics-automationkicadpcb-design
Related

Other skills, from other repositories

altium-designer

Automate Altium Designer PCB workflows with DXP scripts, design-rule checks, OutJob fabrication outputs, and routing configuration.

alivirgo/Major-AI-Skills · 30 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-copilot-mcp

Use when KiCad Copilot MCP tools are available. Entry point for KiCad schematic and PCB workflows.

biosshot/kicad-copilot · 30 tokens

kicad-schematic-design

Create, edit, inspect, and validate KiCad schematics for digital, analog, power, interface, and mixed-signal circuits. Use for requests to open KiCad, create or draw schematics, place library symbols, assign footprints, define external interfaces, wire nets, review screenshots, or diagnose ERC and netlist issues.

Seahan1/kicad-agent · 73 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-review

Design review and validation workflow for KiCAD projects via MCP tools. Triggers on: "review my design", "check for errors", "audit", "DRC", "ERC", "find problems", "design review", "is this ready", "validate", "check my schematic", "check my PCB", "what's wrong", "run checks", "pre-fab review".

nevenfo/kicad-agentic-mcp · 83 tokens