Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/rjwalters/kicad-toolsWrote 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-merge-risk-shadow)<a href="https://agentmods.dev/commands/rjwalters/kicad-tools/champion-merge-risk-shadow"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/champion-merge-risk-shadow/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-merge-risk-shadow"><img src="https://agentmods.dev/badge/commands/rjwalters/kicad-tools/champion-merge-risk-shadow.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 | $0.01108 |
| Opus 5.5 | $0.00000 | $0.00443 |
| Sonnet 5.5 | $0.00000 | $0.00222 |
| Haiku 4.5 | $0.00000 | $0.00111 |
Grade A, and why
champion-merge-risk-shadow 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 24d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shadow-Mode Merge-Risk Pre-Score (#8545) — telemetry, never a verdict
Load-gated: champion-pr-merge.md criterion #2 points here, and only when
TYPESAFE_API_KEY is set. With the key unset this file is never read, no
call is made, no log line is written, and Champion's pass is byte-identical to
one from before #8545.
Why this exists
Criterion #2 is the one safety criterion that is a fresh LLM judgment every tick, and it is the criterion behind the recurring merge-risk-hold gridlock (digest #6877): the same unchanged PR can read green one pass and red the next. Jev (TypeSafe) answers the same four axes as calibrated probabilities, deterministically and cheaply. Logging both verdicts side by side is how we find out how often a hold is later released with no new commits — i.e. how many holds were noise. Nothing can be learned from the comparison if the score is allowed to change the verdict it is being compared against, which is why every rule below is about keeping the two apart.
What to run, after your own verdict is final
# ONLY after criterion #2's four-axis judgment is decided. Never before.
SHADOW=$(loom-daemon jev-merge-risk "$PR_NUMBER" 2>/dev/null) || SHADOW=""
jev-merge-risk prints one JSON line — pr, head_sha, truncated, model,
confidence_basis, usage, and an axes object with a probability (that
the axis is RED) plus a derived confidence for each of
diff_composition_red, blast_radius_red, review_depth_red,
revertability_red. It reads TYPESAFE_API_KEY from the environment, never
from a file or a config key, and it never comments on, labels, merges, or
holds anything.
If $SHADOW is empty (any failure: no key, forge read failed, Jev unreachable,
malformed answer), stop here — log nothing and carry on with the pass
exactly as if this file did not exist. Do not retry, do not wait, do not hold.
A merge must never come to depend on a vendor being reachable.
Where it goes
Append one JSONL record to .loom/logs/champion-merge-risk-shadow.jsonl (a
gitignored local log), pairing your own verdict with Jev's:
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.
- 24d ago First seen · 89 lines · 0 tokens per session scan A 95209c52ff44
champion-merge-risk-shadow 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 1,108 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 2026-09-23.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.