kicad-tools: Command for Claude Code

.claude/commands/repo/links.md

links is a command for Claude Code from rjwalters/kicad-tools. It costs 20 tokens per session (5,521 once invoked), scanned A, original, MIT.

A repository checker for internal references such as Markdown links, CLAUDE.md paths, and links between skills or commands.

In plain words
What is it for?
Use it to scan the whole repository or selected files, fix links that are unambiguous, and review uncertain findings.
Why use it?
It finds references that no longer work after files are moved, renamed, or deleted.

Command for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is rjwalters/kicad-tools's own configuration. It tells Claude Code 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 →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is "notes": "../notes",.

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/.claude/commands/repo/links.md
Clone the repo
git clone --depth 1 https://github.com/rjwalters/kicad-tools

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 links

README.md
[![agentmods](https://agentmods.dev/badge/commands/rjwalters/kicad-tools/links.svg)](https://agentmods.dev/commands/rjwalters/kicad-tools/links)
Your own site
<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/links"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/links.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,521 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 $0.00020 $0.05521
Opus 5 $0.00010 $0.02760
Sonnet 5 $0.00004 $0.01104
Haiku 4.5 $0.00002 $0.00552

Measured 3d ago against content hash 42d32755dc37, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

links 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 3d 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.

.claude/commands/repo/links.md · 465 lines

How it starts

The opening of the file, as written. The whole thing — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Validate that internal cross-references across the repo actually resolve. Catches broken links from reorganization, renames, and deletions.

This is the cross-reference layer of [[docs]]. Use it directly when that's all you want to check; use [[docs]] for the full documentation sweep.

Usage

/repo:links                    # Full repo — fix unambiguous links, report as you go
/repo:links CLAUDE.md          # Check one file
/repo:links .claude/           # Check skill/command files
/repo:links --ask              # Review findings and confirm before fixing

What It Checks

1. Markdown Links

Scan all .md files for [text](path) links where path is a relative file path (not a URL). Verify the target exists on disk.

Strip code before scanning. Remove fenced blocks and inline code spans from the text first — a [text](path) inside backticks is a description of a link, not a link:

text = re.sub(r"```.*?```", "", text, flags=re.S)  # fenced blocks
text = re.sub(r"`[^`]*`", "", text)  # inline spans

Without this the checker flags the sentences in this very file, and in [[audit]], that explain what it looks for. A checker that reports its own documentation as broken is not a checker anyone keeps running.

Skip:

  • External URLs (http://, https://)
  • Anchor-only links (#section)
  • Image URLs from external services

Resolve against two bases, and only report a link that fails both. A relative path can legitimately be written against either the file's own directory or the repo root, and both conventions are in active use:

  1. the directory of the file containing the link
  2. the repo root

Both bases resolve only candidates that stay inside the repo toplevel. Normalize dirname(F)/P (base 1) and P (base 2) lexically — collapse . and .. path components without touching the filesystem, never realpath/readlink -f — and check whether the normalized result still begins with ... A candidate that does is not tried as base 1 or base 2 at all, even when a file happens to exist at that escaping path on disk: it is handed to the sibling-repo base (see Sibling-repo relative links below) instead. An escaping candidate that resolves anyway is a citation into another repo silently reported as if it were in place — undisclosed proof it crossed a repo boundary, exactly the gap this restriction closes. Detection must stay lexical: resolving symlinks (realpath/readlink -f) would deport a symlinked directory that stays inside the repo to the sibling base by mistake, since a symlink target can differ from its lexical path without the link itself ever leaving the repo.

Read the full file on GitHub · 465 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. 3d ago First seen · 465 lines · 20 tokens per session scan A 42d32755dc37

Subscribe to this mod's changes

links is a command published in the GitHub repository rjwalters/kicad-tools (56 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 5,521 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 2026-09-03.