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 ozzy-labs/suasor --skill decisionsgit clone --depth 1 https://github.com/ozzy-labs/suasorWrote 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/ozzy-labs/suasor/decisions)<a href="https://agentmods.dev/skills/ozzy-labs/suasor/decisions"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/decisions.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 | $0.00107 | $0.01214 |
| Opus 5 | $0.00053 | $0.00607 |
| Sonnet 5 | $0.00021 | $0.00243 |
| Haiku 4.5 | $0.00011 | $0.00121 |
Grade A, and why
decisions 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 7d 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
decisions
意思決定を引く単一入口（ADR-0046）。mode で「一覧・変遷」と「1 件の根拠」を切り替える。read-only。
以前は decision-log（一覧）と decision-rationale（根拠）に分かれていたが、どちらも decision.list + graph.related で、違いは何件を、どこまで深くだけだった。
いつ発火するか
| 言いかた | mode |
|---|---|
| 「今月の決定」「直近の意思決定一覧」「[topic] の決定履歴」「決定の変遷を追いたい」 | log（既定） |
| 「あの決定はなぜ」「X を選んだ理由」「なんで A じゃなくて B に」「この方針の根拠は?」 | rationale |
何をするか（MCP tool flow）
すべて read tool（ADR-0004）。
mode=log（既定）
decision.list（recordedAfter/recordedBefore、トピック絞りは結果側で）で対象期間の決定を引く- 各決定について
graph.relatedで背景 source を 1 hop 辿る（decision→source のderived_fromのみ。決定どうしを直接つなぐ辺は無い — 下記「先行決定の辿りかた」） - 時系列に並べ、変遷（何が何を置き換えたか）が分かる形でまとめる
mode=rationale
decision.listで対象の決定を特定する（曖昧なら候補を提示して選んでもらう）graph.relatedで provenance を辿る — その決定の根拠になった sourcesource.getで根拠 source の本文を読むsearchで当時の議論を補強する- 決定 + 経緯 + 根拠 source（+ 辿れた場合の先行決定）を組み立てて返す。却下された選択肢が記録されていればそれも示す
先行決定の辿りかた（辺が無いことを前提にする）
reducer が張る決定まわりの辺は decision → source の derived_from だけで、決定どうしを直接つなぐ辺は存在しない。したがって「先行決定」は次のどちらかでしか辿れない:
- 共有 source 経由の 2 hop — 決定の根拠 source から
graph.relatedを逆向きに辿り、同じ source を根拠に持つ別の決定を見る。同じ議論から複数の決定が出た場合にだけ当たる - 手で張った
manual_link—link.add（write / HITL）で決定間に明示的に張られていればgraph.relatedに出る
1 hop で何も返らないことを「先行決定は無い」と言い換えてはならない（ADR-0007 の "no silent wrong answer"）。辿れなかったときは「provenance link には記録が無い」と述べ、必要なら search で当時の議論を補う。
制約
- read-only。persist しない（決定の記録は
decision.record、HITL） - 根拠は provenance link に基づく。記録が無いものを推測で補わない（「記録が無い」と言う方が有用）
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.
- 7d ago First seen · 69 lines · 107 tokens per session scan A 1725d8ae9c46
decisions is a skill published in the GitHub repository ozzy-labs/suasor (0 stars, last pushed 28d ago), licensed MIT. It adds 107 tokens to every session and 1,214 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 2026-08-31.
Other skills, from other repositories
acceptance
A personal decision framework for difficult situations, built around three choices: change the situation, accept it, or leave it.
decision-heuristics
A set of heuristics for making difficult personal decisions such as changing jobs, buying a home, moving, forming a partnership, or getting married. It is intended for major choices, not everyday decisions.
exec-briefing-memo
A one-page decision memo that condenses complex material into the problem, recommended choice, evidence, trade-offs, risks, and next actions. It is meant for a decision maker, not as meeting notes, a weekly report, or a product requirements document.
strategic-architect
A strategic planning guide for making long-term technology and business decisions. It uses systems thinking to consider goals, risks, resources, and lasting effects.
dual-steelman
Bidirectional steelman deep-thinking protocol for one pending decision, stance, or contested choice. Restates the user's real problem in its strongest form, steelmans both the user's current position and its opposition (or every candidate option), names the true crux and the decisive variables, asks exactly one key…
clarifier-une-decision
Décomposer une décision hésitante en contexte, critères, options et hypothèses, en validant à chaque étape, sans trancher à la place de la personne.