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 skills add seob717/nunchi --skill readme-translategit clone --depth 1 https://github.com/seob717/nunchiWrote 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/seob717/nunchi/readme-translate)<a href="https://agentmods.dev/skills/seob717/nunchi/readme-translate"><img src="https://agentmods.dev/badge/skills/seob717/nunchi/readme-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.
<a href="https://agentmods.dev/skills/seob717/nunchi/readme-translate"><img src="https://agentmods.dev/badge/skills/seob717/nunchi/readme-translate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.01029 |
| Opus 5 | $0.00028 | $0.00515 |
| Sonnet 5 | $0.00011 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
readme-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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
readme-translate
Translate the canonical README.md into README.<lang>.md as a release-time snapshot. The English README is always canonical; translations never lead.
Procedure
- Pin the base. Record the current release tag and main commit (
git log -1 --format=%h origin/main,gh release view --json tagName). These go in the snapshot header. - Read
README.mdin full. Never translate from an older translation — always from the current English canonical. - Write the header block at the top of the translation:
- Language switcher linking every existing README language, e.g.
[English](README.md) | **한국어**. Add the new language to the switcher of all other READMEs too. - Snapshot note (blockquote): this is a translation of the English README, base release + commit, English wins on any mismatch, synced at release time only.
- Language switcher linking every existing README language, e.g.
- Translate section by section following the style rules and glossary below.
- Run the gate check (mandatory, before any commit):
Fix every hard failure; review every reported soft item line by line.python3 .claude/skills/readme-translate/scripts/check.py README.md README.ko.md --banned 배달 재무장 강도 캐비앗 - PR per
.claude/rules/pr-rules.md(docs:title; body states base commit and gate results).
Style rules
Write target-language technical prose, not translated English:
- Break the source syntax. Split multi-clause English sentences; reorder to the target language's natural word order. If a sentence reads like it was translated, rewrite it.
- Translate meaning, never idioms word-for-word. "upfront freight", "credit where due", "scope map, not a scoreboard" → render the point in a natural target-language phrasing.
- No transliterated loanwords when a common native word exists (ko: "캐비앗" → 한계/단서).
- Product terms use commonly understood words — English original in parentheses at first mention, target language only afterwards.
- Tone: plain declarative documentation register (ko: 합니다체, consistent throughout).
What ships with it
1 file 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.
- 10d ago First seen · 65 lines · 56 tokens per session scan A 131d33e4fedb
readme-translate is a skill published in the GitHub repository seob717/nunchi (8 stars, last pushed 6d ago), licensed MIT. It adds 56 tokens to every session and 1,029 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 2026-08-31.
Other skills, from other repositories
hreflang-international
International / multilingual SEO audit focused on hreflang correctness. Detects and diagnoses the most common (and ranking-damaging) hreflang mistakes: missing or broken return tags, wrong language/region codes, missing x-default, self-referencing errors, conflicts between hreflang and canonical, and inconsistent…
checkpoint
Maintain a thirty-second return point (CHECKPOINT.md) and a single-use handoff (HANDOFF.md) so any session can resume mid-goal without archaeology. Use when a large unit of work finishes, a session enters its closing stretch, when leaving instructions for the next session, or when resuming and the user asks where…
verify-gate
Treat research results and model knowledge as drafts until verified. Use when researching, quoting numbers or sources, recording knowledge as fact, or before declaring a task successful.
goal
Run a large or unfamiliar goal through the full ballast pipeline — mobilize what you already hold, terrain scan, full skeleton, atomic foundation learning with verification, then build from bedrock to a verified done. Use when the user hands over a big goal, enters a new field, or asks to learn X in order to achieve Y.
fec-nuxt-project-standard
A guide for building Nuxt 3 applications with Vue 3 and TypeScript. Nuxt is a framework for Vue that can render pages on the server, generate static pages, or run as a browser-only app, using file-based routes and built-in data-fetching patterns.
proof-standard
Never make an external-facing claim about a product without evidence from a truth file. Use when writing marketing copy, announcements, docs, landing pages, investor material, or answering "can our product do X".