kicad-tools: Command for Claude Code

.claude/commands/loom/champion-common.md

champion-common is a command for Claude Code from rjwalters/kicad-tools. It costs 0 tokens per session (7,795 once invoked), scanned A, original, MIT.

Shared instructions and utilities for Champion workflows, including completion reports and tracking pull requests and issues that were merged, promoted, rejected, or held.

In plain words
What is it for?
Use them after reviewing work to record outcomes, list merged pull requests and promoted issues, and report the current merge-risk hold count.
Why use it?
They make decisions and unresolved merge risks visible across evaluation passes instead of leaving important work hidden in one report.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

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 →

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/champion-common.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 champion-common

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/champion-common"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/champion-common.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 7,795 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 $0.00000 $0.07795
Opus 5 $0.00000 $0.03897
Sonnet 5 $0.00000 $0.01559
Haiku 4.5 $0.00000 $0.00779

Measured yesterday against content hash b6207b85fe26, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

champion-common 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 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.

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/loom/champion-common.md · 552 lines

How it starts

The opening of the file, as written. The whole thing — 552 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Champion: Common Utilities

This file contains shared utilities, protocols, and information used across all Champion workflows.


Completion Report

After evaluating both queues:

  1. Report PRs evaluated and merged
  2. Report issues evaluated and promoted
  3. Report capped-PR recovery decisions (granted / kept parked / close recommended)
  4. Report rejections with reasons
  5. List merged PR numbers and promoted issue numbers with links
  6. Report the merge-risk hold census — always, including when it is zero (#6720)
  7. Persist the per-PR merge-risk hold digest — durably, across passes, not just in this transcript (#6851)

Merge-risk hold census (mandatory line, #6720). A held PR does not merge and does not report itself; without a standing count, a pile grows unseen. On rjwalters/loom it reached 21 held PRs, 20 of them conflicting, and was found only because an operator inspected PR labels by hand. Run the single gh pr list query in champion-pr-merge.md → "Held-PR Census" in this pass (never restate numbers from a previous one) and emit one line:

Merge-risk holds: <N> open PR(s) — <C> conflicting, <D> out at Doctor, oldest <A>d

Emit the line even when the set is empty (the census command already produces Merge-risk holds: 0 open PR(s) — 0 conflicting, 0 out at Doctor, oldest 0d). A line that only appears when something is wrong is a line nobody learns to read.

Per-PR digest (mandatory, #6851) — additive to the census line above, not a replacement for it. The aggregate line is a transcript-only summary: it tells the pipeline how many PRs are held, but a fresh read of it exists only for the length of this pass's own session. Run champion-pr-merge.md → "Held-PR Census" → "Per-PR Digest" in this same pass to also write PR number / hold reason / mergeable status for every currently-held PR to the pinned Champion: Merge-Risk Hold Digest tracking issue, so a human or another role (e.g. Guide) can read the current pile without a Champion transcript or a hand-run loom:operator label query. This is reporting/visibility only — it changes no Safety Criteria evaluation and no merge decision.

Read the full file on GitHub · 552 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 · +87 lines b6207b85fe26
  2. 9d ago First seen · 465 lines · 0 tokens per session scan A e2229d00504a

Subscribe to this mod's changes

champion-common is a command published in the GitHub repository rjwalters/kicad-tools (56 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,795 tokens. 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 2026-08-30.