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.
git clone --depth 1 https://github.com/BFRKQSB7/balance-hudWrote 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/commands/bfrkqsb7/balance-hud/language)<a href="https://agentmods.dev/commands/bfrkqsb7/balance-hud/language"><img src="https://agentmods.dev/badge/commands/bfrkqsb7/balance-hud/language/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/commands/bfrkqsb7/balance-hud/language"><img src="https://agentmods.dev/badge/commands/bfrkqsb7/balance-hud/language.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 | $0.00023 | $0.00274 |
| Opus 5 | $0.00012 | $0.00137 |
| Sonnet 5 | $0.00005 | $0.00055 |
| Haiku 4.5 | $0.00002 | $0.00027 |
Grade A, and why
language 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.
What it actually says
Toggle Balance HUD Language
Switch the HUD label language between English and 中文 (Chinese).
Steps
-
Read
~/.claude/plugins/balance-hud/config.json. -
Check the
languagefield:"zh-Hans"→ the HUD is currently Chinese. Set it to"en"(English)."en"→ the HUD is currently English. Set it to"zh-Hans"(中文).- Any other / missing value → set it to
"zh-Hans".
-
Write the file back, keeping every other key unchanged. Use a real JSON serializer (not manual string concatenation).
-
Confirm to the user which language the HUD now uses:
✅ HUD 语言已切换为 中文（上下文 / 缓存效果 / 用量…）
or
✅ HUD language switched to English.
The HUD refreshes automatically on every statusline poll (~300ms) — no restart needed. Labels affected include Context → 上下文, Cache Effect → 缓存效果, Usage → 用量, Tokens → 词元.
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 · 27 lines · 23 tokens per session scan A 30edc003dd7e
language is a command published in the GitHub repository BFRKQSB7/balance-hud (2 stars, last pushed 24d ago), licensed MIT. It adds 23 tokens to every session and 274 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 commands, from other repositories
translate
Translate content into 15 languages while preserving brand voice, citations, and SEO optimization.
moodle-string-check
You will find untranslated user-facing strings in a Moodle plugin.
msd-release-notes
Generate "What's New" release notes for all locales — outputs a single consolidated file per platform with locale XML tags for easy copy-paste.
msd-status
Show current state of a registered app — version, first release status, locale coverage, pending actions.
msd-aso
Run ASO keyword research and metadata optimization for one or all locales.
msd-select-locales
Select or update the app's supported locales before metadata, screenshots, or i18n work.