champion-reference

champion-reference is a command for Claude Code from rjwalters/kicad-tools. It costs 0 tokens per session (12,278 once invoked), scanned A, original, MIT.

Reference documentation for the Champion role, including unusual cases, workflow scripts, and troubleshooting notes. The Champion is the role responsible for final checks before certain pull requests are merged.

In plain words
What is it for?
Use it to handle non-standard cases in automated pull-request merging and to follow the documented GitHub command-line workflows safely.
Why use it?
It provides guidance when the normal pull-request process does not cover a situation, including cases involving missing checks or command-line errors.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is ./.loom/scripts/classify-capacity-defer.sh --issue "$ISSUE_NUMBER" \.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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-reference

README.md
[![agentmods](https://agentmods.dev/badge/commands/rjwalters/kicad-tools/champion-reference.svg)](https://agentmods.dev/commands/rjwalters/kicad-tools/champion-reference)
Your own site
<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/champion-reference"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/champion-reference.svg" alt="Measured on agentmods" 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 12,278 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.12278
Opus 5 $0.00000 $0.06139
Sonnet 5 $0.00000 $0.02456
Haiku 4.5 $0.00000 $0.01228

Measured 6d ago against content hash a4331744a0bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

champion-reference 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 6d 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/loom/champion-reference.md · 711 lines

How it starts

The opening of the file, as written. The whole thing — 711 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Champion: Reference Documentation

This file contains edge cases, complete workflow scripts, and troubleshooting information for the Champion role. Reference this file when handling non-standard situations.


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

If you post a comment via gh issue comment / gh pr comment / gh api ... comments from a scratch file, --body @path (and gh api -f body=@path) posts the literal string @path, not the file's contents. Full pitfall, incident citation, and fixes: comment-body-literal-path.md.

Edge Cases and Special Scenarios

This section documents how Champion handles non-standard situations during PR auto-merge.

Edge Case 1: PR with No CI Checks

Scenario: Repository has no CI/CD configured, or PR doesn't trigger any checks.

Handling:

#6211: empty stdout alone is NOT proof "no checks exist". An earlier version of this doc detected "no checks" via empty stdout from gh pr checks --json alone (with stderr discarded via 2>/dev/null and the exit code never inspected). That is unsafe: gh pr checks can ALSO return empty stdout during a transient forge failure (e.g. the intermittent TLS handshake error #6169 hit, observed ~1 call in 3 on one host) — a state indistinguishable from genuine "no checks configured" once stderr is thrown away. Since this read gates Champion's auto-merge, that ambiguity is a real (if rare) false-positive path: a PR with actual pending/unrun CI could get merged.

The fix distinguishes the two cases instead of collapsing them: the genuine no-checks case has a documented, stable signature — EMPTY stdout, NONZERO exit, and stderr containing "no checks reported" — and only that combination is trusted. Any other empty read is ambiguous and gets one retry before failing closed (never silently defaulting to "no checks"). Critically, the genuine no-checks case is resolved on the very first read (its stderr always matches immediately), so a repo that legitimately has zero CI checks configured (e.g. a quickstart repo) is never made to wait — only an ambiguous read pays the one retry.

Read the full file on GitHub · 711 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. 6d ago First seen · 711 lines · 0 tokens per session scan A a4331744a0bc

Subscribe to this mod's changes

champion-reference is a command published in the GitHub repository rjwalters/kicad-tools (55 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 12,278 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.