dotfiles: Skill for Claude Code

.claude/skills/po-translate/SKILL.md

po-translate is a skill for Claude Code from natsukium/dotfiles. It costs 30 tokens per session (1,406 once invoked), scanned A, original, CC0-1.0.

A workflow for translating the repository's English text in a PO file into Japanese. PO files are translation files that pair source text with translated text.

In plain words
What is it for?
Use it to classify entries in po/ja.po, translate eligible text, and repeat review until the Japanese translation is clean.
Why use it?
It separates entries that should stay unchanged from those that need translation, then coordinates translation and review.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions subagents.

This is natsukium/dotfiles's own configuration. It tells Claude Code how to work on dotfiles itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dotfiles configures →

Reuse

Borrowing it

Nothing to install: this file belongs to natsukium/dotfiles. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/natsukium/dotfiles/main/.claude/skills/po-translate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/natsukium/dotfiles

Made for: Claude Code.

Wrote 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.

agentmods badge for po-translate

README.md
[![agentmods](https://agentmods.dev/badge/skills/natsukium/dotfiles/po-translate/github.svg)](https://agentmods.dev/skills/natsukium/dotfiles/po-translate)
Your own site
<a href="https://agentmods.dev/skills/natsukium/dotfiles/po-translate"><img src="https://agentmods.dev/badge/skills/natsukium/dotfiles/po-translate/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.

agentmods 80×15 button for po-translate

Your own site · 80×15
<a href="https://agentmods.dev/skills/natsukium/dotfiles/po-translate"><img src="https://agentmods.dev/badge/skills/natsukium/dotfiles/po-translate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,406 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.01406
Opus 5 $0.00015 $0.00703
Sonnet 5 $0.00006 $0.00281
Haiku 4.5 $0.00003 $0.00141

Measured 10d ago against content hash 9a4595c51419, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

po-translate 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.

.claude/skills/po-translate/SKILL.md · 153 lines

How it starts

The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PO Translation Orchestrator

Translate po/ja.po from English to Japanese for this literate Nix configuration repository. This skill orchestrates the process: you classify entries yourself, then delegate translation and review to subagents, iterating until the review passes.

Phase 1: Classify (do this yourself)

Scan po/ja.po and classify every entry into three buckets.

Skip (leave msgstr empty)

PO type comment (#. type:) Reason
paragraph in src Code block content
keyword NAME / keyword name Source block identifiers
keyword SETUPFILE Org directive
keyword PROPERTY Property drawer value
keyword OPTIONS Export option string
keyword STARTUP Startup keyword
keyword INCLUDE po4a handles path swap
property (*) Property values

Also skip: bare URLs as msgid, table cells with hardware models/hostnames/platforms.

Already Translated

Non-empty msgstr — leave unchanged unless review flags them.

Translate

Everything else: paragraph, heading ******, plain list, paragraph in QUOTE/quote/example, cell column N with prose, keyword title.

Grouping

Group translatable entries by primary source file into sequential batches:

  1. configuration.org
  2. applications/emacs/init.org
  3. overlays/configuration.org + applications/emacs/early-init.org + .github/README.org
  4. modules/configuration.org

Output a batch summary (entry counts, line ranges) before proceeding to Phase 2.

Phase 2: Translate (delegate to subagents)

Spawn one Agent per batch, sequentially (wait for each to finish before starting the next — they all edit the same file).

Subagent prompt template

Include ALL of the following in each subagent's prompt:

  1. The batch assignment: line range, list of msgid start lines to translate
  2. The full content of these reference files (read them yourself first, then paste the content into the prompt — subagents cannot read skill reference files by path):
    • .claude/skills/po-translate/references/glossary.md
    • .claude/skills/po-translate/references/style-guide.md
    • .claude/skills/po-translate/references/po-format.md
  3. These rules:

Read the full file on GitHub · 153 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 153 lines · 30 tokens per session scan A 9a4595c51419

Subscribe to this mod's changes

po-translate is a skill published in the GitHub repository natsukium/dotfiles (103 stars, last pushed today), licensed CC0-1.0. It adds 30 tokens to every session and 1,406 once invoked, about $0.0002 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.