kicad-tools: Instructions file for Codex

AGENTS.md

kicad-tools AGENTS.md is an instructions file for Codex, OpenCode from rjwalters/kicad-tools. It costs 2,235 tokens per session, scanned C, original, MIT.

Project instructions for developing kicad-tools, a software project related to KiCad electronics design tools, with guidance for its AI development workflow.

In plain words
What is it for?
Preparing the C++ router before performance tests, rebuilding it when source changes, and following repository development conventions.
Why use it?
They tell coding agents how to build the native C++ component, interpret checks, and handle project-specific worktree and release rules.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is rjwalters/kicad-tools's own configuration. It tells Codex and OpenCode how to work on kicad-tools itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything kicad-tools configures →

Reuse

Borrowing it

Nothing to install: this file belongs to rjwalters/kicad-tools. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/rjwalters/kicad-tools/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/rjwalters/kicad-tools

Made for: Codex, OpenCode.

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 kicad-tools AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rjwalters/kicad-tools/agents-md/github.svg)](https://agentmods.dev/instructions/rjwalters/kicad-tools/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rjwalters/kicad-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/rjwalters/kicad-tools/agents-md/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 kicad-tools AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/rjwalters/kicad-tools/agents-md"><img src="https://agentmods.dev/badge/instructions/rjwalters/kicad-tools/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,235 This file is loaded in full into every session.
When invoked 2,235 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.02235 $0.02235
Opus 5.5 $0.00894 $0.00894
Sonnet 5.5 $0.00447 $0.00447
Haiku 4.5 $0.00224 $0.00224

Measured 9d ago against content hash 5bdc96e30fc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

kicad-tools AGENTS.md scanned grade C with 1 finding 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

anything else, `rm -rf .mypy_cache` and re-run **before** investigating. Never
AGENTS.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Routing performance: build the C++ backend first

Before benchmarking routing latency or filing "router is slow" issues, verify the C++ router extension (src/kicad_tools/router/router_cpp.*.so) is built in the active worktree:

uv run kct build-native --check
# Expected: "C++ backend: available (version 1.0.0)"

If it reports "not installed", build it once:

uv run kct build-native

uv sync does not build the native extension — fresh checkouts and new git worktrees (.loom/worktrees/issue-N/) need this step explicitly. The C++ backend gives a 10-100x speedup for the A* loop, so a missing extension is the most likely cause of multi-minute-per-net routing.

Rebuilding after editing C++ sources

kct build-native now detects staleness automatically: it compares the newest mtime of src/kicad_tools/router/cpp/** (.cpp/.hpp and CMakeLists.txt) against the installed .so and rebuilds when the source is newer, even without a BUILD_VERSION bump. When the .so is already up to date it prints SKIPPED rebuild instead of the old misleading installed successfully!.

--force always recompiles regardless of mtimes — reach for it if you suspect the auto-detection missed something (e.g. a touched build flag).

See README.md "Fresh worktree checklist" for the full setup sequence.

Native evidence: produce it on the pinned KiCad toolchain

Committed native DRC/ERC evidence (readiness-verification/**, readiness.json, native-drc*.json) must not depend on the host's KiCad config or release (issue #6962). Producers (kct readiness, scripts/boards/*.py) run kicad-cli with a scratch KICAD_CONFIG_HOME holding the pinned tables in src/kicad_tools/data/kicad-config/10.0/, and refuse (exit 2, nothing written) a kicad-cli other than CI's image release, or a DRC report with lib_footprint_issues. On a Mac with Homebrew KiCad, route through the pinned image instead of fighting the refusal:

Read the full file on GitHub · 179 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 Changed · +19 lines · +268 tokens per session 5bdc96e30fc8
  2. 20d ago Changed · +139 lines · +1,652 tokens per session scan A → C f30d90b0301d
  3. 1mo ago Changed · +18 lines · +192 tokens per session f0940941f23b
  4. 1mo ago First seen · 3 lines · 123 tokens per session scan A 395aa0971ee4

Subscribe to this mod's changes

kicad-tools AGENTS.md is an instructions file published in the GitHub repository rjwalters/kicad-tools (74 stars, last pushed yesterday), licensed MIT. It adds 2,235 tokens to every session, about $0.0089 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,786 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens