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 nolte/claude-home-assistant --skill ha-translation-syncgit clone --depth 1 https://github.com/nolte/claude-home-assistantWrote 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/nolte/claude-home-assistant/ha-translation-sync)<a href="https://agentmods.dev/skills/nolte/claude-home-assistant/ha-translation-sync"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-translation-sync/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/nolte/claude-home-assistant/ha-translation-sync"><img src="https://agentmods.dev/badge/skills/nolte/claude-home-assistant/ha-translation-sync.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 | $0.00094 | $0.01377 |
| Opus 5.5 | $0.00038 | $0.00551 |
| Sonnet 5.5 | $0.00019 | $0.00275 |
| Haiku 4.5 | $0.00009 | $0.00138 |
Grade A, and why
ha-translation-sync 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HA Translation Sync
Spec: spec/claude/ha-translation-sync/en.md (EN canonical) / spec/claude/ha-translation-sync/de.md (DE translation).
Why this is a skill, not an agent
- Confirm-before-delete gate (decisive): orphaned keys are surfaced for operator confirmation before removal — a mid-flow approval an agent's fire-and-forget shape would lose.
- Quick, targeted change: structural drift fixes touch strings.json and the translation files of the integration in scope; main-conversation territory per the change-scope dimension.
- Counter-dimension considered: drift detection is mechanical and self-contained (agent bias), but detection without the interactive disposition step is only half the contract — the gate outweighs isolation.
When this skill activates
Use this skill to align strings.json with every translations/<lang>.json file in an HA Custom Integration and to surface drift against icons.json.
When NOT to activate
- machine translation → out of scope
- changing existing translation values → manual edit (no owning skill;
ha-entity-description-mapwhen entity strings need re-mapping) - creating a new language file from scratch → user decision; not this skill
- string content changes → covered by the producing skill (
ha-integration-scaffold,ha-entity-description-map, …)
Hard rules
- Never overwrite existing translation values. Only missing keys are added; existing values stay untouched.
- Never silently delete orphaned keys. Surface them; ask for confirmation.
- Never apply machine translations.
<TODO: translate '<EN value>'>is the only automatic placeholder. - Always run
reportfirst. Default mode isreport;applyis opt-in. - Always include
icons.jsondrift — and fill it. A translation key without an icon (or vice versa) is a defect even when both files are internally consistent; inapplymode, fill a missingicons.jsonentry with a<TODO: icon>marker via the same mechanism asstrings.json, rather than only reporting it. - Verify HA internals against the official docs. Don't reproduce HA API signatures, lifecycle hooks, conventions, or schemas from memory — when uncertain, consult the official docs before generating or relying on it: Developer docs
developers.home-assistant, architecture/blueprint/YAML docshome-assistant.io(seespec/ha/upstream-docs-verification/en.md).
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.
- 1mo ago First seen · 110 lines · 94 tokens per session scan A 1d673451c3ce
ha-translation-sync is a skill published in the GitHub repository nolte/claude-home-assistant (1 stars, last pushed 1mo ago), licensed MIT. It adds 94 tokens to every session and 1,377 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
i18n-localization
Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.
humanize-korean
A Korean editing tool that removes translation-like phrasing and common AI writing habits while preserving facts, numbers, names, and quotations. It is intended for existing Korean prose, not for writing new marketing copy.
agent-i18n-specialist
Specialist subagent: Expert internationalization specialist for multi-language support and localization.
i18n-integrity
Translation integrity: every key present in every language, no hardcoded strings, consistent placeholders and plurals. Runs when user-facing text changes.
korean-spell-check
Use Nara/PNU Korean spell-check surfaces conservatively to proofread Korean text, chunk long input, and return change-focused correction suggestions.
pptx-translator
This skill should be used when the user needs to translate PowerPoint presentations (.pptx) between languages, preserving formatting and layout. Supports parallel slide-by-slide translation with per-slide validation and retry. Default languages are Portuguese and English but any language pair is supported.