Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rjwalters/kicad-toolsnpx agentmods add commands/rjwalters/kicad-tools/champion-epic-standdownWrote 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.
[](https://agentmods.dev/commands/rjwalters/kicad-tools/champion-epic-standdown)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/champion-epic-standdown"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/champion-epic-standdown/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.
<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/champion-epic-standdown"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/champion-epic-standdown.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01897 |
| Opus 5.5 | $0.00000 | $0.00759 |
| Sonnet 5.5 | $0.00000 | $0.00379 |
| Haiku 4.5 | $0.00000 | $0.00190 |
Grade A, and why
champion-epic-standdown scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Champion: Step 0.5 — Tracking-Umbrella Stand-Down (#7666)
This file is the body of champion-epic.md → "Step 0.5". Read it when that
step tells you to, after Step 0's Completion-First Check has declined to act
and before Step 1. It answers the one question the 6 structural criteria
cannot: "has this epic already been decomposed, by someone other than
Step 3?"
The 6 criteria describe an epic awaiting decomposition — they check the
phases, sizing, and success criteria Step 3 needs in order to create Phase 1
issues. An epic whose children already exist and are being worked is past that
point. Those children may come from a Curator decomposition pass, native
GitHub sub-issues, or a hand-written - [ ] #N task list, none of which carries
the <!-- loom:epic:$EPIC_NUMBER:phase:N --> marker that Step 2.75 and
"Detecting Phase Completion" search for — so neither phase creation nor phase
progression can see them, and a literal reading of Step 2.75 would report
EXISTING_COUNT=0 and create a duplicate Phase 1 set. Champion has nothing
left to do for such an epic except watch it finish, which Step 0 already does
on every pass. A passing epic is never a stuck epic: the correct handling is
one durable note and then silence — never a structural re-evaluation, never an
operator escalation.
0.5a. Detect the tracking umbrella
Reuses Step 0a's discovery — do NOT re-run discover_epic_children.
# Set by Step 0a: EPIC_CHILD_STRONG_{OPEN,CLOSED}, EPIC_CHILD_SOURCES.
# `phase-marker` in EPIC_CHILD_SOURCES means discovery source (a) contributed,
# i.e. Champion decomposed this epic itself and "Phase Progression" owns it
# from here — such an epic must fall through to Step 1 exactly as before.
case ",$EPIC_CHILD_SOURCES," in
*,phase-marker,*)
IS_TRACKING_UMBRELLA=no ;; # Champion's own decomposition
*)
if [ "$EPIC_CHILD_STRONG_OPEN" -gt 0 ]; then
IS_TRACKING_UMBRELLA=yes # decomposed elsewhere, still in flight
else
IS_TRACKING_UMBRELLA=no # undecomposed (Step 1), or complete (Step 0 owned it)
fi ;;
esac
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.
- 2d ago Changed c59dd395ae8d
- 15d ago Changed ade44849120f
- 1mo ago First seen · 118 lines · 0 tokens per session scan A f4bf698413d9
champion-epic-standdown is a command published in the GitHub repository rjwalters/kicad-tools (70 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,897 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 2026-09-17.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.