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 source-reviewgit 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/source-review)<a href="https://agentmods.dev/skills/ozzy-labs/suasor/source-review"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/source-review/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/ozzy-labs/suasor/source-review"><img src="https://agentmods.dev/badge/skills/ozzy-labs/suasor/source-review.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 | $0.00145 | $0.01239 |
| Opus 5 | $0.00072 | $0.00620 |
| Sonnet 5 | $0.00029 | $0.00248 |
| Haiku 4.5 | $0.00015 | $0.00124 |
Grade A, and why
source-review 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 8d 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
source-review
取り込み済み素材（document / PR / 版の差分）をレビューする単一入口（ADR-0046）。
名前について:
reviewではなくsource-reviewなのは、@ozzylabs/skillsの dev skillreview（コードレビュー）と名前空間を分けるため（ADR-0008・#520）。同じ host dir に install されるので、名前が衝突すると一方が他方を上書きして壊す。target で振る舞いを決める。read-only。
以前は doc-review / doc-diff / pr-review の 3 本に分かれていたが、ユーザーの「レビューして」からはどれが発火すべきか判別できなかった。違いは何を見るかだけである。
いつ発火するか
| 言いかた | target |
|---|---|
| 「この設計書レビューして」「仕様のレビュー」「この提案どう思う」「抜け漏れ確認」 | document |
| 「この PR レビューして」「#123 確認して」「PR どう思う」 | pr |
| 「この資料は前回から何が変わった」「この資料の差分」「どこが更新された」 | diff |
対象が曖昧なら聞き返す（PR 番号があれば pr、source id / 資料名があれば document、「変わった」「差分」の語があれば diff）。
対象（source id / 資料名 / PR 番号）を指定しない「前回から何が変わった」は特定資料の差分ではなく状況サマリの質問なので、brief（period=前回確認時刻から）が受ける。
何をするか（MCP tool flow）
すべて read tool（ADR-0004）。外部への投稿は行わない（PR コメント投稿は egress なので本 skill の範囲外。ユーザーが手で貼る）。
target=document
source.get（externalId）で本文を読む。provenance も要るならinclude: ["links"]searchで関連する先行仕様・過去の議論を引くgraph.related/decision.listで関連する決定を辿る- 整合性 / 抜け漏れ / 前提 / リスクの観点で所見を組み立てる
target=pr
searchで関連 source / 過去の review / 関連決定を引く- 必要に応じて
gh pr diffの出力（ホスト側で取得）と突き合わせる - レビュー観点を提示する。PR への comment 投稿はしない
target=diff
source.history（externalId）で event log から本文の版を引く（ADR-0002 — 全版が残る）- 直近 2 版、または期間指定の前後版を突き合わせる
- 変更点を要約する（何が追加 / 削除 / 変更されたか）
制約
- read-only。persist しない・外部に投稿しない
- 判断（良し悪し）はホスト LLM 側。本 skill は手順書のみで実処理を持たない
source.historyは本文の版のみを再構成する。メタデータの変遷は対象外
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.
- 8d ago First seen · 71 lines · 145 tokens per session scan A b90ab6f78bd3
source-review is a skill published in the GitHub repository ozzy-labs/suasor (0 stars, last pushed 29d ago), licensed MIT. It adds 145 tokens to every session and 1,239 once invoked, about $0.0007 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
agent-review
Critically review a Stencila agent and suggest improvements. Use when asked to review, audit, critique, evaluate, or improve an agent directory or AGENT.md file. Covers frontmatter validation, system instruction quality, configuration correctness, and adherence to the Agent schema.
review-work
Quality gate: verify each acceptance criterion of a completed task/work unit, run quality checks, and create follow-up tasks for gaps. Use before merging or to audit delivered work. Invoked as /agiflow:review-work . Uses getworkunit, gettask, updatetask, createtask, createtaskcomment.
review-export
Export CocoReview reports as markdown, html, or pdf-ready status artifacts. Usage: $review export markdown|html|pdf [report-path].
quality-gate
Orchestrates the QUALITY pipeline stage for egregore work items, running code review, unbloat, and test updates. Use when running quality checks before a PR.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
developer_review
Code-review workflow for Developer Studio repositories.