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 s977043/river-review --skill unknown-coverage-reviewgit clone --depth 1 https://github.com/s977043/river-reviewWrote 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/s977043/river-review/unknown-coverage-review)<a href="https://agentmods.dev/skills/s977043/river-review/unknown-coverage-review"><img src="https://agentmods.dev/badge/skills/s977043/river-review/unknown-coverage-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/s977043/river-review/unknown-coverage-review"><img src="https://agentmods.dev/badge/skills/s977043/river-review/unknown-coverage-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 | $0.00190 | $0.03532 |
| Opus 5 | $0.00095 | $0.01766 |
| Sonnet 5 | $0.00038 | $0.00706 |
| Haiku 4.5 | $0.00019 | $0.00353 |
Grade A, and why
unknown-coverage-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 10d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unknown Coverage Review(残存 Unknown のメタ観点)
由来 / Inspired by: Thariq「A Field Guide to Finding Your Unknowns」(The map is not the territory: Plan やプロンプトは現実のコードベースを圧縮した地図であり、地図と土地の差分に Unknown が潜む)と Matt Pocock「
/grill-me」(実装前に質問を重ね共有理解を作る)から着想した概念の再実装。原著者を名指しする nominative fair use に留め、endorsement は主張しない。
通常のレビューは「壊れている箇所(defect)」を指す。 本観点は 「そのリスク種別を調査した証拠が残っているか(evidence-sufficiency)」 を、完成した差分を横断して合成する。問いが直交するため、defect 検出とは混載しない。
背景 / Background
AI coding agent の実行能力が上がるほど、見逃しは単純なコード品質から 要件・暗黙知・影響範囲・運用条件・移行条件などの「未確認の未知(Unknown)」 へ移る。 チェックリストを満たしても、レビュー対象外の前提や未確認領域が残れば誤ったマージ判断につながる。 本観点は大量の質問を生成しない。差分・PR 本文・Plan・テスト・設定・履歴を調査し、以下を構造化して出力する。
- 何が未確認か
- なぜ危険か
- どの証拠が不足しているか
- 何を確認すれば解消できるか
- マージを止めるべきか(既存 verdict 語彙への写像で表現)
Pre-execution Gate / 発火条件
最初に判定する。満たさない場合は以降の観点を実行せず NO_REVIEW を返す。
- finding verification 後の 合成ステップとして呼ばれている(orchestrator の Execution Flow から。keyword routing では呼ばない)。
- 入力に少なくとも
diffがあり、差分が リポジトリ内で実行されるコード・migration・schema・公開 API・設定のいずれかに触れる。docs・コメントのみの差分は対象外とする。 - ビルド成果物・生成物(
dist/**・*.map・lockfile・自動生成 manifest)は Gate 判定からもレビュー対象からも除外する。 - PlanGate 非依存:
plan/review-selfなどの artifact が欠損しても動作する。欠損した観点は finding を出さずskippedSkillsに記録してデグレードする(artifact-input-contract の既定挙動)。plan/test-casesartifact は schema のinputContextenum・実行側availableContextsに供給元が存在しない optional evidence のため、frontmatterinputContextには宣言せず本 Gate の記述で扱う(宣言すると deterministic 経路で常に skipped になる)。 - 観点6 の plan 代替 evidence: 観点6(Plan / Assumption)は
planartifact 欠損時、PR 本文へ前提・open question が inline 列挙されていれば列挙分のみ部分評価する(外部 issue は取得・推測しない)。計画 issue の bare 参照(#NNNN)のみなら skip しskippedSkillsに記録する。この分岐は registry skillassumption-resolution-traceと同一ルールに揃える。 - PlanGate #810 ledger: PlanGate #810 が assumption/unknown ledger を出力する場合も、専用 artifact を新設しない。
planartifact 経由で受け取る同一の artifact-driven パターンに従う(artifact-input-contract.md)。欠損時は上記と同じデグレード(skippedSkills)を適用する。PlanGate への依存は必須にしない。
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 128 lines · 190 tokens per session scan A 551e27404ee2
unknown-coverage-review is a skill published in the GitHub repository s977043/river-review (3 stars, last pushed today), licensed MIT. It adds 190 tokens to every session and 3,532 once invoked, about $0.0010 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
review-all
Multi-agent code review for diffs (project-agnostic). Covers standards, bugs, security, DRY, smells, perf, tests, API contracts, a11y/i18n. Verifies each finding to eliminate false positives. Use for /review-all, pre-PR/pre-commit review, or auditing uncommitted/staged changes.
logic-health
Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic patterns. Trigger when the user requests a health view — "audit the whole codebase", "health check", "health overview", "logic health overview", "audit src/", "audit auth and payments modules", "where…
logic-diff
Compare two code versions for semantic equivalence via semi-formal tracing of both versions side-by-side. Trigger when the user shares a refactor, rewrite, migration, or A/B implementation and wants to confirm behavior is unchanged — "did I break anything", "is this equivalent", "are these equivalent", "semantically…
omnicheck-gitlab
Use when checking if MR review findings have been applied — verifies both OmniForge-generated and human reviewer comments against the current diff, posts nudge replies on unaddressed threads.
omnicheck-github
Use when checking if PR review findings have been applied — verifies both OmniForge-generated and human reviewer comments against the current diff, posts nudge replies on unaddressed threads.
omnicreate-gitlab
Use when creating a GitLab merge request (OmniForge). Auto-populates title and description from commits, supports draft MRs, labels, assignees, reviewers, and issue linking.