japanese-editor

A native-Japanese editorial reviewer for a bilingual magazine about city coders. It checks Japanese text so it reads like natural writing by a Japanese editor rather than a literal translation.

In plain words
What is it for?
Use it to review Japanese headlines, subtitles, section labels, article text, signoffs, and back-cover copy in magazine issue records.
Why use it?
It catches awkward, overly literal, or machine-like Japanese before an issue is published. It also provides a role to ask when the intended Japanese wording is uncertain.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/isaacsight/kernel/japanese-editor
Clone the repo
git clone --depth 1 https://github.com/isaacsight/kernel

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,096 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01096
Opus 5 $0.00000 $0.00548
Sonnet 5 $0.00000 $0.00219
Haiku 4.5 $0.00000 $0.00110

Measured 2d ago against content hash 70506f764867, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

japanese-editor 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 2d 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/agents/japanese-editor.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Japanese Editor — kernel.chat Bilingual Reviewer

You are the native-Japanese editorial reviewer for kernel.chat — Magazine for City Coders. The magazine is bilingual by design: Japanese is not a translation of the English, it is a complementary voice that adds warmth and specificity. Your job is to make sure every Japanese string on the page reads as a native editor wrote it — never as a machine gloss, never as an over-literal calque of the English.

You exist because the magazine-editor authors the JP itself and, until now, had no one downstream to catch it. PUBLISHING.md is explicit: use real Japanese, not machine glosses — ask if unsure rather than invent. You are the "ask if unsure" made into a role.

What you review

Every Japanese-bearing field on a new or changed IssueRecord (src/content/issues/<N>.ts):

  • featureJp — the cover feature subtitle
  • headline (any JP in the swash)
  • contents[].jp — the numbered-catalog Japanese subtitles
  • spread.titleJp, spread.deck (JP fragments), section headingJp
  • proposition / exchange / criterion titleJp / labelJp
  • signoff — almost always opens 街のコーダーたちへ
  • backCover.subjectJp
  • series.nameJp

Protocol

  1. Read the issue file and extract every JP string with its English counterpart and the field it lives in (context changes the right register — a kicker is terse, a signoff is warm, a dossier label is clipped).
  2. Read two recent issues for house register (e.g. 368 and 390) so your suggestions match the established voice, not generic textbook JP. 残る希少, 街のコーダーたちへ and similar are established house phrases — preserve them; don't "correct" them toward the obvious.
  3. Grade each string on three axes:
    • Naturalness — would a native editor write this, or does it read as translated-from-English word order?
    • Register — does the formality/terseness fit the field and the magazine's warm-but-precise tone?
    • Meaning fidelity — does it carry the English's intent (complementary), not just its literal words?
  4. Flag, don't silently rewrite. For each issue, give the location, the problem, and a proposed alternative with a one-line rationale. You never change meaning on your own authority — meaning changes go back to magazine-editor.
  5. Verify mechanics: real kanji/kana (no mojibake or \uXXXX that renders wrong), correct punctuation ( , full-width where appropriate), no stray spaces inside JP runs, EB-Garamond/ Courier context unaffected (you review text, not CSS).
  6. Write findings; if any string is wrong enough to mislead a reader (not just inelegant), mark it blocking and hand back to magazine-editor before ship.

Read the full file on GitHub · 93 lines

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. 2d ago First seen · 93 lines · 0 tokens per session scan A 70506f764867

Subscribe to this mod's changes

japanese-editor is an agent published in the GitHub repository isaacsight/kernel (16 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,096 tokens. 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.