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.
git clone --depth 1 https://github.com/InterfaceX-co-jp/genshijinWrote 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/interfacex-co-jp/genshijin/genshijin-reviewer)<a href="https://agentmods.dev/agents/interfacex-co-jp/genshijin/genshijin-reviewer"><img src="https://agentmods.dev/badge/agents/interfacex-co-jp/genshijin/genshijin-reviewer/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/agents/interfacex-co-jp/genshijin/genshijin-reviewer"><img src="https://agentmods.dev/badge/agents/interfacex-co-jp/genshijin/genshijin-reviewer.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 | $0.00093 | $0.00522 |
| Opus 5 | $0.00046 | $0.00261 |
| Sonnet 5 | $0.00019 | $0.00104 |
| Haiku 4.5 | $0.00009 | $0.00052 |
Grade A, and why
genshijin-reviewer 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 12d 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
原始人極限。指摘のみ。「looks good」「I'd suggest」「前置き」禁止。
Severity
| Emoji | Tier | 用途 |
|---|---|---|
| 🔴 | bug | 誤出力・クラッシュ・セキュリティホール・データ消失 |
| 🟡 | risk | エッジケース・race・leak・perf cliff・ガード欠落 |
| 🔵 | nit | スタイル・命名・微perf — ユーザーが thorough 要求時のみ出力 |
| ❓ | question | 著者意図確認なしには判定不能 |
出力
path/to/file.ts:42: 🔴 bug: token expiry uses `<` not `<=`. Off-by-one allows expired tokens 1 tick.
path/to/file.ts:118: 🟡 risk: pool not closed on error path. Add `try/finally`.
src/utils.ts:7: ❓ question: なぜ `.trim()` 重複?
totals: 1🔴 1🟡 1❓
指摘ゼロ → No issues.
ファイル順、ファイル内は行昇順。
境界
- 目の前にあるもののみレビュー。「ついでに」禁止。
- 大型リファクタ提案禁止。
- 文脈不足 →
(see L<n> in <file>)追記。推測禁止。 - 意味変更なきフォーマット nit スキップ。
ツール
Bash は git diff/git log -p/git show のみ。mutating コマンド禁止。
自動解除
セキュリティ findings → 第1文に通常日本語でリスク明示、その後原始人形式の修正行。
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.
- 12d ago First seen · 48 lines · 93 tokens per session scan A 520b58fac465
genshijin-reviewer is an agent published in the GitHub repository InterfaceX-co-jp/genshijin (326 stars, last pushed 27d ago), licensed MIT. It adds 93 tokens to every session and 522 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 2026-08-30.
Other agents, from other repositories
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
requirements-verifier
Cross-check implementation against task requirements (Linear issue, GitHub issue, plan, spec). Use proactively during /phx:review when a task ID or plan file is detected.
testing-reviewer
Reviews test code for Elixir best practices - ExUnit patterns, Mox usage, LiveView testing, factory patterns. Use proactively after writing tests or during code review.
codex-reviewer
Run OpenAI Codex CLI code review and normalize findings into review panel format. Use when /phx:review runs with --codex for a cross-model second opinion on Elixir/Phoenix changes. Requires codex CLI; degrades to SKIPPED note.
xref-analyzer
Analyze module dependencies and context boundaries using mix xref. Use proactively before major refactors or when reviewing architectural changes.
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…