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 agentmods add skills/fredchu/claude-dotfiles/forensic-transcript-translatornpx skills add fredchu/claude-dotfiles --skill forensic-transcript-translatorgit clone --depth 1 https://github.com/fredchu/claude-dotfilesWrote 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/fredchu/claude-dotfiles/forensic-transcript-translator)<a href="https://agentmods.dev/skills/fredchu/claude-dotfiles/forensic-transcript-translator"><img src="https://agentmods.dev/badge/skills/fredchu/claude-dotfiles/forensic-transcript-translator.svg" alt="Measured on agentmods" 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 | $0.00234 | $0.02621 |
| Opus 5 | $0.00117 | $0.01311 |
| Sonnet 5 | $0.00047 | $0.00524 |
| Haiku 4.5 | $0.00023 | $0.00262 |
Grade A, and why
forensic-transcript-translator 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.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
法證級逐字稿翻譯器 (Forensic Transcript Translator)
五階段流程，將英文 earnings call 逐字稿翻譯為台灣繁體中文，並以獨立審計確保零遺漏。
Phase 0: 結構指紋 → Phase 1: 術語鎖定 → Phase 2: 分段翻譯 → Phase 3: 法證審計 → Phase 4: 組裝輸出
模型路由策略
主對話（Opus 4.6）擔任指揮官，負責流程控制、術語決策、品質判斷。重型工作分派給 subagent：
| Phase | 執行者 | 模型 | 原因 |
|---|---|---|---|
| 0 結構指紋 | Task subagent (Bash) | haiku | 純腳本執行 |
| 1 術語建立 | 主對話自行處理 | opus（當前） | 需要判斷力 |
| 2 分段翻譯 | Task subagent (general-purpose) | sonnet | 翻譯重活，Sonnet 品質足夠且快 |
| 3a 腳本審計 | Task subagent (Bash) | haiku | 純腳本執行 |
| 3b 語意審計 | Task subagent (Explore) | haiku | 比對閱讀，不需生成能力 |
| 3c 問題修復 | 主對話自行處理 | opus（當前） | 需要精準重翻判斷 |
| 4 組裝輸出 | 主對話自行處理 | opus（當前） | 需要統整所有結果 |
Phase 2 的 Task 呼叫範例：
Task(
subagent_type="general-purpose",
model="sonnet",
prompt="你是法證級翻譯員。以下是術語表和翻譯規則...[完整規則]...請翻譯以下段落：[段落內容]"
)
Phase 3b 的 Task 呼叫範例：
Task(
subagent_type="Explore",
model="haiku",
prompt="你是獨立審計員。請比對以下兩份檔案...[EN_PATH]...[TW_PATH]..."
)
Phase 0: 結構指紋提取
- 使用 Read 工具讀取使用者提供的英文逐字稿檔案。
- 將原文存為工作目錄下的暫存檔：
[TICKER]_[QUARTER]_Transcript_EN.tmp。 - 執行結構指紋腳本：
python3 [SKILL_PATH]/scripts/structural_fingerprint.py [EN_TMP_PATH] --json - 記錄指紋結果（段落數、發言者序列、所有數字、字數），後續 Phase 3 比對用。
- 向使用者回報指紋摘要（段落數、發言者人數、數字總量），然後自動進入 Phase 1。
Phase 1: 動態術語表建立
- 載入基底術語表：讀取
references/glossary-base.md。 - 掃描原文，找出基底表中未涵蓋的公司專屬術語（產品名、業務指標、人名職稱）。
- 建立本次翻譯的完整術語表，格式：
## 本次專屬術語
| English | 中文 | 備註 |
|---------|------|------|
| Toast Capital | Toast Capital | 不翻譯 |
| Aman Narang | Aman Narang | CEO |
- 術語表自動生效，不暫停等待使用者確認。
- 自動進入 Phase 2。
Phase 2: 分段翻譯
翻譯原則（不可違反）
- 原子級鏡像：嚴禁摘要、刪減、優化語法。
- 口語贅詞保留："um" → 嗯, "you know" → 你知道的, "uh" → 呃, "well" → 這個, "I mean" → 我的意思是, "sort of" → 算是, "kind of" → 有點, "right?" → 對吧？
- 未完成句子：如實保留，用 ⋯⋯ 表示中斷。
- 自我糾正：如實保留（例："revenue was — sorry, operating income was"）。
- 數字格式：$479.1 million → 4.791億美元, 25% → 25%, 130,000 locations → 13萬個餐廳據點。所有數字加粗。
- 雙語標記：核心術語採「中文 (English)」格式，依術語表執行。
- 台灣在地化：使用台灣金管會與財經媒體慣用語。禁用簡體或港式詞彙。
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.
- 4d ago First seen · 191 lines · 234 tokens per session scan A abbd285b2751
forensic-transcript-translator is a skill published in the GitHub repository fredchu/claude-dotfiles (2 stars, last pushed 21d ago), licensed MIT. It adds 234 tokens to every session and 2,621 once invoked, about $0.0012 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
localized-pricing
Guide for implementing localized pricing, adaptive currency, and purchasing power parity with Dodo Payments.
rewrite-rustdoc
Rewrite Rust documentation comments to ensure all documentation and comments are in English, following rustdoc guidelines. Use when the user wants to clean up Rust documentation, translate Chinese comments to English, fix missing documentation, or ensure rustdoc compliance in a Rust codebase.
codexkit-strategy-scorecard-builder
Translate strategy into a balanced scorecard, strategy map, OKR bridge, and executive initiative portfolio with clear measures, targets, and owners. Use when leadership needs strategic alignment, portfolio prioritization, or a management dashboard tied to outcomes. Do not use for ad-hoc brainstorming with no strategic…
chinese-traditional-conversion
Convert simplified Chinese to Traditional Chinese (zh-TW), covering characters, Taiwan vocabulary, and phrasing. Use when the user asks to convert 簡體 to 正體/繁體, localise mainland Chinese text for Taiwan, fix simplified characters left in a document or repository, check whether content is written in proper zh-TW, or…
estimate-analysis
Deep-dive into analyst estimates and revision trends for any stock using Yahoo Finance data. Use when the user wants to understand analyst estimate direction, how EPS or revenue forecasts changed over time, compare estimate distributions, or analyze growth projections across periods. Triggers: "estimate analysis for…
earnings-recap
Generate a post-earnings analysis for any stock using Yahoo Finance data. Use when the user wants to review what happened after earnings, understand beat/miss results, see stock reaction, or get an earnings recap. Triggers: "AAPL earnings recap", "how did TSLA earnings go", "MSFT earnings results", "did NVDA beat…