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 test-assertion-effectivenessgit 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/test-assertion-effectiveness)<a href="https://agentmods.dev/skills/s977043/river-review/test-assertion-effectiveness"><img src="https://agentmods.dev/badge/skills/s977043/river-review/test-assertion-effectiveness/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/test-assertion-effectiveness"><img src="https://agentmods.dev/badge/skills/s977043/river-review/test-assertion-effectiveness.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 | $0.00367 | $0.06278 |
| Opus 5.5 | $0.00147 | $0.02511 |
| Sonnet 5.5 | $0.00073 | $0.01256 |
| Haiku 4.5 | $0.00037 | $0.00628 |
Grade A, and why
Test Assertion Effectiveness 常に PASS するテストの検出 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 1mo 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Naming / 命名
skills/README.md の Naming Q0–Q5 に従って決定した。Q0 では外部プロジェクトの成果物を取り込んでいないため「概念の再実装」に分類され、リネーム（新規命名）が既定となる。Q1 は衝突なし（assertion を含む skill id は既存に無い）、Q2・Q3 は参照元の原語が存在しないため適用外、Q4 で既存の test-* 命名ファミリ（test-existence / test-naming / test-plan-review）に整合することを確認し、Q5 で「価値（アサーションが有効であること）を名指す」名として test-assertion-effectiveness を採用した。機構名（tautology 検出・grep 照合）ではなく価値を名指す点が Q5 の要件である。
Pattern declaration
Primary pattern: Reviewer Secondary patterns: Inversion Why: アサーションの形はパターンとして拾えるが、「そのアサーションが SUT の挙動に依存しているか」の判定は意味的であり、期待値の照合先（テンプレート・コンポーネント）が discover できない差分では実行を止めるゲートが必要である。
Goal / 目的
テストの「有無」や「粒度」は既存 skill が見るが、書かれたアサーションが実際に失敗しうるかは誰も見ていない。アサーションが無効なテストは行を通過するためカバレッジ指標にも現れず、CI が緑であることも有効性の証明にならない（レビュー時点の CI が古い sha で緑だった実例が #1684 に記録されている）。この盲点を diff-time の静的観点として埋める。
次の 6 Check のいずれかに該当し、そのテストが実装の退行を検知できないと読み取れる場合に指摘する。report-only（ADR-005）であり、finding / question のみを出力して自動修正はしない。
Non-goals / 扱わないこと（委譲表）
| 隣接領域 | 委譲先 | 分界 |
|---|---|---|
| テストが存在しない | test-existence |
委譲先は「変更コードに対応するテストが差分に無い」。本 skill は逆にテストがある差分にだけ働く（委譲先はテスト差分があると黙る前提のため） |
| 未テスト経路・分岐・境界の量 | coverage-gap |
委譲先は「その経路のテストが存在しない」。本 skill は「テストは存在するがアサーションが落ちない」 |
| 実行ごとに結果が変わる不安定さ | flaky-test |
委譲先は非決定性。本 skill は決定論的に必ず PASS する構造 |
describe / it の命名・構造 |
test-naming |
命名の明瞭さは対象外。名前が適切でもアサーションが無効なら本 skill が扱う |
JS / TS の un-awaited expect(...).resolves / .rejects |
vitest-mock-isolation |
委譲先が「常に pass する空 assertion」として既に所有する。async-correctness も本番コード側からここへ委譲済みであり、三重管理にしない |
tdd-ledger artifact による RED / GREEN 証跡の検証 |
plangate-tdd-evidence |
委譲先は artifact 駆動（artifact 非供給の adopter では常に NO_REVIEW）。本 skill はartifact に依存しない diff-time 観点 |
| 影響・失敗系・外部依存を調査した証拠の有無 | impact-evidence-coverage |
委譲先は同一 diff のテストを「証拠あり」として充足扱いにする。本 skill はそのテスト自体が有効かを見る（矛盾ではなく補完関係） |
| 本番経路の例外握り潰し・配線切れ | e2e-wiring / logging-observability |
委譲先は src/** 等の本番経路。本 skill が見る握り潰しはテスト本体の中で判定を無効化するものに限る |
.only / .skip / xit / @ts-ignore / 空の catch {} |
src/lib/heuristic-review.mjs の決定論検出器 |
決定論で判定済みのため重複指摘しない（.claude/rules/review-core.md §「カスタム静的解析の False-positive 責務分界（#1070）」） |
What ships with it
6 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.
- fixtures/01-nonexistent-expected-literal-should-detect.md 3.0 KB
- fixtures/02-stale-expected-value-should-detect.md 3.6 KB
- fixtures/03-unscoped-expectation-should-detect.md 3.0 KB
- fixtures/04-vacuous-and-swallowed-should-detect.md 3.7 KB
- fixtures/05-helper-parameterized-deletion-pinning-canary.md 4.0 KB
- fixtures/06-scoped-snapshot-delegated-territory-canary.md 4.6 KB
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.
- 1mo ago First seen · 226 lines · 367 tokens per session scan A e561e02e03de
Test Assertion Effectiveness 常に PASS するテストの検出 is a skill published in the GitHub repository s977043/river-review (7 stars, last pushed today), licensed MIT. It adds 367 tokens to every session and 6,278 once invoked, about $0.0015 per session on Opus 5.5. 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
run-iteration-eval
Run the Logic-Lens content-eval pipeline for one iteration and produce a scored summary.json — use to measure a skill change. Wraps scripts/run-content-evals.sh (runner, costs tokens) and scripts/grade-iteration.py (grader, free, re-runnable). ALWAYS sync the plugin cache first. Use when the user wants to "run the…
iterate-skill
Run the Logic-Lens skill-improvement loop end to end — baseline → diagnose failures → edit → sync cache → re-eval → verify net gain → iterate until clean. Use whenever the goal is to RAISE a skill's eval score or fix a failing eval mode: "improve logic-review", "the format compliance is failing, fix it", "iterate on…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
vibe-gap-analysis
Assesses production readiness or audits a codebase against its specs. Supports quick static mode, deep 17-dimension audit, or single-dimension focus. Use before a production launch, after a major refactor, when inheriting a codebase, or when someone asks how done the project is.
spike-consumer-adversarial
OI-3 spike harness — heavy consumer, ADVERSARIAL arm. Worst-case early-exit test: the mid-workflow Skill call has no continuation guardrail and the guidance skill ends with a final-sounding anchor. Use only when explicitly invoked by the spike harness with a TRIALID and data path.
shipyard-verification
Requires fresh verification evidence before any claim that work is complete, fixed, or passing. Use before committing, creating PRs, or moving to the next task. Also use when a status report contains words like "should", "probably", or "seems to", or expresses satisfaction ("Great!", "Done!") before verification…