Borrowing it
Nothing to install: this file belongs to gurezo/mdn-translation-ja-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gurezo/mdn-translation-ja-mcp/main/.agents/skills/harvest-review-findings/SKILL.mdgit clone --depth 1 https://github.com/gurezo/mdn-translation-ja-mcpWrote 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/gurezo/mdn-translation-ja-mcp/harvest-review-findings)<a href="https://agentmods.dev/skills/gurezo/mdn-translation-ja-mcp/harvest-review-findings"><img src="https://agentmods.dev/badge/skills/gurezo/mdn-translation-ja-mcp/harvest-review-findings/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/gurezo/mdn-translation-ja-mcp/harvest-review-findings"><img src="https://agentmods.dev/badge/skills/gurezo/mdn-translation-ja-mcp/harvest-review-findings.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 | $0.00070 | $0.00708 |
| Opus 5 | $0.00035 | $0.00354 |
| Sonnet 5 | $0.00014 | $0.00142 |
| Haiku 4.5 | $0.00007 | $0.00071 |
Grade A, and why
harvest-review-findings 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 4d 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
Harvest Review Findings
閉じた翻訳 Issue と JA PR の人手レビュー指摘を集め、.agents/skills のチェックリストと references に反映する。
When to use
- mozilla-japan/translation の閉じた Issue を解析するとき
- mdn/translated-content の閉じた
l10n-jaPR レビュー指摘を収集するとき - レビュー慣行を
.agents/skillsに取り込むとき
Utility scripts
実行する（読むだけではない）:
node .agents/skills/harvest-review-findings/scripts/harvest.mjs \
--pr-limit=40 --issue-limit=30 \
--out=/tmp/mdn-review-harvest.json
gh がログイン済みであること。自動 PR（automated pr）、bot、プレビュー URL、Issue テンプレ、作者の feat: 作業ログ、短い承認・クローズ文は除外する。
Workflow
- 上記スクリプトを実行し、
/tmp/mdn-review-harvest.jsonと.mdを読む clustersをスキルごとに読み、references/review-conventions.md と照合する- 繰り返す指摘だけを対象スキルへ反映する（1件だけの文脈依存指摘は入れない）
- 反映先:
- 表記 →
editorial-guideline - 意訳・メタデータ・マクロ →
l10n-guideline - 文体・かな漢字 →
japanese-style - 訳語 →
mozilla-l10n-glossary
- 表記 →
- SKILL.md の Quick checklist と
references/の両方を更新する。機械検査できるパターンはsrc/shared/data/review-rules.jsonも検討する - 出典は PR/Issue URL を
sourceRefまたは conventions 表に残す - 生の harvest JSON はコミットしない
Do not
- Issue 本文の翻訳作業チケットをガイドラインにコピーしない
- 承認だけ（「OKです」）を指摘として扱わない
- ユーザーが依頼するまで対象
index.mdを編集しない
Additional resources
What ships with it
3 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.
- 4d ago First seen · 53 lines · 70 tokens per session scan A f14605fbafd6
harvest-review-findings is a skill published in the GitHub repository gurezo/mdn-translation-ja-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 708 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
tongwen
Use when translating engineering CAD drawings between languages — DWG text extraction, translation workspace with terminology management, quality-checked write-back. TongWen (同文): local-first CAD/BIM lossless translation suite for AutoCAD 2019-2026.
internationalization-i18n
Audits and implements internationalization (i18n) and localization (l10n) for a frontend application. Covers message format selection, locale file organisation, pluralization, RTL layout, and CI extraction workflows. Invoked when the user asks to add i18n support, set up translations, or make the UI multilingual.
i18n
A guide to adding multiple languages and regional formats to Flutter apps. It covers translation files, right-to-left layouts, plural and gender-aware messages, and changing the language while the app runs.
localization-testing
Internationalization (i18n) and localization (l10n) testing for global products including translations, locale formats, RTL languages, and cultural appropriateness. Use when launching in new markets or building multi-language products.
i18n-manager
An internationalization tool for managing text in software for different languages and regions. It extracts strings, finds missing translations, creates locale files, and reports coverage.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.