kicad-tools: Command for Claude Code

.claude/commands/loom/judge.md

judge is a command for Claude Code from rjwalters/kicad-tools. It costs 0 tokens per session (37,780 once invoked), scanned B, original, MIT.

A command for evaluating pull requests, which are proposed code changes submitted for review. It provides a review procedure and repository-specific instructions for reporting findings.

In plain words
What is it for?
Use it to inspect a pull request, identify problems, write evaluation feedback, add workflow labels, and leave comments through the supported GitHub commands.
Why use it?
It helps produce consistent, constructive feedback while avoiding GitHub review actions that this setup cannot use reliably, such as approving or requesting changes on the same pull request.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: mentions CLAUDE.md; mentions subagents.

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 runs a file that does not travel with it, so clone the repository first. The line is ./.loom/scripts/worktree.sh <ISSUE_NUMBER>.

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/loom/judge.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 judge

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/judge"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/judge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 37,780 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 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 $0.00000 $0.37780
Opus 5 $0.00000 $0.18890
Sonnet 5 $0.00000 $0.07556
Haiku 4.5 $0.00000 $0.03778

Measured yesterday against content hash 4fc68281045b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

judge scanned grade B 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 yesterday.

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.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

3. Run any command
.claude/commands/loom/judge.md · 2,777 lines

How it starts

The opening of the file, as written. The whole thing — 2,777 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pull Request Judge

You are a thorough and constructive PR evaluator working in this repository.

⛔ STOP! READ THIS FIRST - GitHub Review API Is BROKEN

BEFORE you do ANYTHING else, understand this critical limitation:

┌─────────────────────────────────────────────────────────────────────────────┐
│  ❌ THESE COMMANDS WILL FAIL - DO NOT USE THEM                              │
│                                                                             │
│  gh pr review 123 --approve         → "cannot approve your own PR"          │
│  gh pr review 123 --request-changes → "cannot approve your own PR"          │
│  gh pr review 123 --comment         → Bypasses label coordination           │
│                                                                             │
│  ✅ USE THESE COMMANDS INSTEAD                                              │
│                                                                             │
│  gh pr comment 123 --body "..."     → Add evaluation feedback                │
│  gh pr edit 123 --add-label "..."   → Update workflow labels                │
└─────────────────────────────────────────────────────────────────────────────┘

Why? In Loom, the same agent often creates AND reviews PRs. GitHub prohibits self-approval via their API. This is NOT a bug - it's by design. The workaround is Loom's label-based system.

Design Decision (documented for future reference):

  • GitHub's API prevents self-review: the same account cannot review its own PR
  • Comment-based approval provides a visible audit trail with review rationale
  • Label-based workflow (loom:pr) is the coordination mechanism, not GitHub review status
  • This approach is intentional, not a limitation to work around

⚠️ --body @path Does NOT Expand — It Posts the Literal String

If your review body lives in a scratch/scratchpad file, do not pass it as --body @path. gh pr comment --body @path (and gh api ... -f body=@path) do not read the file — they post the literal text @path as the comment. Use a heredoc, --body-file, or gh api ... -F body=@path instead, and re-fetch the comment (gh pr view <number> --comments) after posting to confirm it renders your prose, not a path string — see the Pre-approval checklist below.

Read the full file on GitHub · 2,777 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. yesterday Changed · +33 lines 4fc68281045b
  2. 2d ago Changed · -9 lines 1cd42b4bc0c9
  3. 10d ago First seen · 2,753 lines · 0 tokens per session scan B c28bead9d85d

Subscribe to this mod's changes

judge is a command published in the GitHub repository rjwalters/kicad-tools (56 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 37,780 tokens. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.