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.
npx skills add amadeus-dlc/amadeus --skill amadeus-electiongit clone --depth 1 https://github.com/amadeus-dlc/amadeusWrote 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/skills/amadeus-dlc/amadeus/amadeus-election)<a href="https://agentmods.dev/skills/amadeus-dlc/amadeus/amadeus-election"><img src="https://agentmods.dev/badge/skills/amadeus-dlc/amadeus/amadeus-election/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/skills/amadeus-dlc/amadeus/amadeus-election"><img src="https://agentmods.dev/badge/skills/amadeus-dlc/amadeus/amadeus-election.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 | $0.00101 | $0.02177 |
| Opus 5 | $0.00051 | $0.01089 |
| Sonnet 5 | $0.00020 | $0.00435 |
| Haiku 4.5 | $0.00010 | $0.00218 |
Grade A, and why
amadeus-election 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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
amadeus-election — 指令転送ループ
起動
選挙定義 JSON を受け取る。定義は常に schemaVersion: 2・electionId・kind・questions[]・voters を持つ。単問は questions[] が1要素、複数問は複数要素で、各要素は questionId・text・choices を持つ。choices[] は internalNo・label に加えて任意の description(その選択肢の本文)を持てる。
questions[].text と description は投票者ごとの blind view にそのまま搬送されるため、選択肢に説明を要する選挙では description を付ける:
bun {{HARNESS_DIR}}/tools/amadeus-election.ts open --file <definition.json>
exit 0 以外なら出力の error をそのまま人間へ提示して停止する。
票の形: 票も常に schemaVersion: 2 で、回答は responses[](各要素は questionId・choiceInternalNo・goa・reservation・rationale)に入れる。単問の選挙でも要素1個の responses[] を使う。
ソロモード(subagent 投票者): voters は subagent-1 と subagent-2 を指定する。conductor(main agent)は選挙管理委員として指令ループを駆動し、自らは投票しない。
ソロ選挙の発動: 発動条件は設定項目ではなく Intent Autonomy Mode から導出する。semi / full は auto、none は manual を導出し(旧 solo-election.trigger.mode は廃止済み — 残置された旧キーは無視されず config 解決が loud fail する)、auto の場合に限り (a) 設計逸脱 (b) ブロッカー (c) §13 学習選定 の3類型を自動発動する。自動発動では open に --trigger auto を必ず付け、{"opened":null,"reason":"solo-election-manual-trigger-required"} が返ったら選挙を作成せずユーザー裁定へ切り替える。manual を導出する場合、および上記以外の類型では、ユーザーが「選挙にかけて」と明示したときだけ通常の open で発動する。仕様変更およびエスカレーション正準リスト事項は mode によらず選挙対象外(ユーザー専権)とする。
spawn 不能時: Agent tool(spawn)が使えない環境では、選挙を開かず次の1行を stderr または会話へ出力してユーザー裁定へ切り替える: spawn 不能のためユーザー裁定へ降格
転送
以下のループを繰り返す。このスキルは次の一手を自分で決めない — next の指令が名指しした verb と report を字義どおり実行するだけである。targetQuestionIds・held・preservedResultDigest を自分で選んだり作り直したりしない:
bun {{HARNESS_DIR}}/tools/amadeus-election.ts next --election <id>
- 出力(stdout の JSON 1行)を読む。
kindがdoneならループを終了する(→ 終了節)。kindがholdなら、まず人間委譲節へ移る(再投票ラウンドを回すかどうかは人間が決める)。kindがcollect-waitなら、pendingに列挙された投票者からの票を待つ。票が届いたらvote --election <id> --file <ballot.json>で受理し、ループ先頭へ戻る。受理が exit 1 なら error を投票者へそのまま返す。再実行中はtargetQuestionIdsに列挙された question だけをresponses[]に含める。- それ以外は、stdout の指令 JSON をファイルへ保存し、指令の
verbフィールドが名指しするサブコマンドと続くreportの両方を--election <id> --file <そのファイル>付きで実行する(指令を再構築しない)。いずれかが exit 0 以外なら停止して人間へ提示する。
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.
- 6d ago First seen · 74 lines · 101 tokens per session scan A d52d047ed7d4
amadeus-election is a skill published in the GitHub repository amadeus-dlc/amadeus (8 stars, last pushed 20d ago), licensed Apache-2.0. It adds 101 tokens to every session and 2,177 once invoked, about $0.0005 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
athena-codex
Use the ATHENA framework in Codex for PRD-driven, traceable delivery. Trigger when the user wants iterative execution with auditable CR/Decision/Spec/Task artifacts and disciplined one-task-at-a-time implementation.
Research Ticketing Protocol
Ticket attachment decision trees, enforcement protocols, communication templates, and worked examples for research outputs.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
remove
Remove a deployed framework or addon from the current workspace.