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 hon454/grimoire --skill magical-translationgit clone --depth 1 https://github.com/hon454/grimoireWrote 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/hon454/grimoire/magical-translation)<a href="https://agentmods.dev/skills/hon454/grimoire/magical-translation"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/magical-translation/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/hon454/grimoire/magical-translation"><img src="https://agentmods.dev/badge/skills/hon454/grimoire/magical-translation.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 | $0.00029 | $0.00382 |
| Opus 5 | $0.00015 | $0.00191 |
| Sonnet 5 | $0.00006 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
magical-translation 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 9d 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
Magical Translation
Translate or interpret text using the Grimoire session translation locale. Use this when a user asks for translation, localized explanation, or when another skill needs user-facing text in the configured Grimoire locale.
Locale
Before translating, resolve the target locale with the bundled script:
python3 <skill-dir>/scripts/resolve_translation_locale.py --format json
Use the returned locale as the translation target. Do not infer the target
language from conversation prose, source text, repository language, or host
locale when the script cannot read the session cache. If the script fails, tell
the user the Grimoire session config cache is unavailable or invalid and ask for
an explicit target language before translating.
Translation Rules
- Preserve code, commands, file paths, branch names, issue or PR numbers, commit SHAs, API names, config keys, error strings, and quoted identifiers unless the user explicitly asks to translate them.
- Translate meaning, not just words. Explain implied intent, risk, and nuance when the task asks for interpretation.
- Keep source excerpts short. Summarize long source text instead of copying it.
- Redact secrets, credentials, tokens, private emails, customer data, signed URL query strings, and other sensitive values before echoing source details.
- Match the user's requested output shape when provided. Otherwise prefer concise prose or a compact table for multi-item interpretation.
Use From Other Skills
When another skill delegates translation here, first run the locale script, then apply these translation rules inside that skill's workflow. Return control to the calling skill after translation or interpretation is complete.
What ships with it
2 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.
- 9d ago First seen · 44 lines · 29 tokens per session scan A 5057a4a8439f
magical-translation is a skill published in the GitHub repository hon454/grimoire (2 stars, last pushed 21d ago), licensed MIT. It adds 29 tokens to every session and 382 once invoked, about $0.0001 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
wechat-article-formatter
A formatting skill that converts Markdown, a plain-text writing format, into styled HTML for WeChat Official Accounts, Chinese public publishing pages.
baoyu-translate
A translation workflow for converting articles and other text into another language. It offers quick, standard, and publication-focused approaches with different levels of review.
oma-translation
Context-aware translation and localization for UI strings, documentation, marketing copy, and prose. Preserves meaning, register, terminology, placeholders, structure, and natural target-language phrasing.
zh-tw
Rewrite the previous reply in Traditional Chinese.
content-translator
Translate text content between languages with high quality and natural phrasing. Covers document translation, content localization, and multi-language research support for teams working across language barriers.
translator
Translate content across languages while preserving brand voice and cultural nuance.