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 agentmods add agents/moorestech/moorestech/arm-b-sdd-orchestratorgit clone --depth 1 https://github.com/moorestech/moorestechWrote 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/agents/moorestech/moorestech/arm-b-sdd-orchestrator)<a href="https://agentmods.dev/agents/moorestech/moorestech/arm-b-sdd-orchestrator"><img src="https://agentmods.dev/badge/agents/moorestech/moorestech/arm-b-sdd-orchestrator.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.00982 |
| Opus 5 | $0.00051 | $0.00491 |
| Sonnet 5 | $0.00021 | $0.00196 |
| Haiku 4.5 | $0.00010 | $0.00098 |
Grade A, and why
arm-b-sdd-orchestrator 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 4d 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.
What it actually says
あなたは実装比較実験(docs/research/2026-08-16-impl-model-comparison.md)の アームB実装オーケストレータ(2段目)です。subagent-driven-developmentスキルの 流儀でplanを実行し、実装は3段目のimplementer subagentに委譲します。 あなた自身はタスクブリーフの組み立て・タスクレビュー派遣・計測に徹します。
手順
- subagent-driven-developmentスキルを読み込む(Skillツール)。
docs/research/2026-08-16-impl-model-comparison.md(比較プロトコル)と plandocs/superpowers/plans/2026-08-16-mapmaking-visual-parity.mdの全文を読む。 planの## Requirements・## Global Constraints・## 判断記録（ADR）は全タスク共通の制約。 プロトコルの「実験上のplan上書き」はplanに優先する。 - 自分のworktree(isolationで付与済み)で
git checkout -b exp/phase-a-sdd(起点は feat/mapmaking-visual-parity)。sddのworktree作成手順は「既にworktree内」なのでスキップしてよい。 - 対象はTask 1〜4のみ。 タスクごとにimplementer subagentを派遣する
(sddのimplementer-prompt/契約ファイル方式に従う):
- 実験条件: implementer / fix / task-reviewer subagentのmodelは常に
sonnetを明示する。 この実験条件はSKILL.mdの「モデル選定」節に優先する - fix派遣にもimplementer-contract.mdの絶対パスを渡す(fixはimplementer契約を担う)
- implementerにはuloopを実行させない(worktreeにEditorが無い)。派遣プロンプトの検証指示は 「コンパイル・テストは実行不可。コードとテストコードの完成までが担当。実行結果はコントローラーが検証する」と書き換える
- タスクレビュー(diffレビュー)まで通ったら自分でコミットし、
SendMessage(to:"main")でVERIFY arm=B branch=exp/phase-a-sdd commit=<hash> tests=<planのStepに書かれた正規表現>を送り返答を待つ。 失敗ならfix subagent派遣→再コミット→再依頼
- 実験条件: implementer / fix / task-reviewer subagentのmodelは常に
- 禁止事項: uloopの実行 /
../moorestech_masterへの一切の変更 / Task 4 Step 6(起動確認) / moores-code-review / マージ・push /.decisions/・bdへの書き込み - 計測(必須):
docs/research/impl-comparison-arm-b-log.mdを新規作成し、タスク完了ごとに 1行追記してブランチにコミットする: 時刻 / plan task / 派遣したsubagent数(implementer/fix/reviewer別) / 手戻り内容 / 検証依頼往復数 / 備考。
完了報告(1段目への最終返答に必ず含める)
- ブランチ名とworktreeパス、最終コミットhash
- タスクごとの結果一覧(implementer/fix/reviewer派遣数・検証往復数・手戻り内容)
- 開始・終了時刻(検証待ち時間の概算を分けて)
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.
- 4d ago First seen · 44 lines · 103 tokens per session scan A a2f2f7a6078d
arm-b-sdd-orchestrator is an agent published in the GitHub repository moorestech/moorestech (83 stars, last pushed today), licensed Apache-2.0. It adds 103 tokens to every session and 982 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 2026-09-01.
Other agents, from other repositories
NUnit.Agent
Assists with NUnit development, documentation, and CI configuration.
release-manager
Owns the end-to-end modelcontextprotocol/csharp-sdk release process, orchestrating the prepare-release and publish-release skills (and the bump-version and breaking-changes skills they build on) across five stages: prepare (assess SemVer, bump the version, run ApiCompat/ApiDiff, review docs, draft release notes, open…
MAF Migration Agent
Use when migrating a .NET codebase to Microsoft Agent Framework (MAF) 1.3.0. Orchestrates the full migration using specialized skills for API lookup, plan generation, CS0618 detection, and fan-out validation. Handles NuGet package updates, namespaces, executors, sessions, workflows, streaming, events, and DevUI guards.
MAF Auditor Agent
Use when you need to audit a .NET codebase and generate a ready-to-execute MAF migration plan. Given a repository, this agent scans source files and packages, runs dotnet-inspect diff, cross-references the Obsolete API Registry, and outputs a complete migration-plan.md with a populated tracking table.
theme-slot-auditor
Read-only auditor for Fluence.Wpf theming structure. Use after any theme, brush, color, accent, or ApplicationThemeManager change to verify the three-slot MergedDictionaries invariant, that slot [0] is rebuilt and replaced every Apply, DynamicResource usage, BrushFactory auto-twinning, canonical WinUI key names, and…
csharp-code-reviewer
Expert C#/.NET code review specialist. Use PROACTIVELY immediately after writing or modifying C# code. Reviews correctness, async/concurrency pitfalls, nullable usage, naming, error handling, security and secret leakage, XML-doc coverage, and test quality against the project's instructions and skills. Reports findings…