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 agentmods add commands/zander-zyx/claude-mini-hud/setupgit clone --depth 1 https://github.com/zander-zyx/claude-mini-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/zander-zyx/claude-mini-hud/setup)<a href="https://agentmods.dev/commands/zander-zyx/claude-mini-hud/setup"><img src="https://agentmods.dev/badge/commands/zander-zyx/claude-mini-hud/setup.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.04088 |
| Opus 5 | $0.00010 | $0.02044 |
| Sonnet 5 | $0.00004 | $0.00818 |
| Haiku 4.5 | $0.00002 | $0.00409 |
Grade B, and why
setup scanned grade B with 1 finding 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 5d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
把 `claude-mini-hud` 配成 Claude Code 的 statusline, 让 `~/.claude/settings.json` 里的 `statusLine.command` 指向本插件的 `dist/index.js`。 How it starts
The opening of the file, as written. The whole thing — 343 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-mini-hud Setup
把 claude-mini-hud 配成 Claude Code 的 statusline, 让 ~/.claude/settings.json 里的 statusLine.command 指向本插件的 dist/index.js。
Step 1: 选择语言 / Select Language
必须先调用 AskUserQuestion 弹出语言选择菜单, 根据用户选择决定后续步骤里的提示文案 + 写入 settings.json 的环境变量:
Use AskUserQuestion:
header: "Language"
question: "请选择显示模式 / Select display mode"
options:
- label: "中文 (Chinese)"
description: "上下文 + Token + 当前任务 全部中文"
- label: "English"
description: "Context + Token + Todos 全部英文"
- label: "简约 (Minimal)"
description: "英中混搭, 无前缀符号, 最紧凑布局"
- label: "极简 (Ultra-Minimal)"
description: "只显示 Context + Token 两行, 其余全部隐藏"
把用户选择存到 {LANG} 变量 (zh / en / minimal / ultra-minimal), 后续步骤用它:
- 决定 Step 6 输出提示的语种
- 写入
statusLine.command的CLAUDE_MINI_HUD_LANG={LANG}环境变量
4 种模式输出示例 (支持 emoji 的终端会自动显示 emoji 图标, 不支持的终端显示 ASCII 符号):
# 中文 (zh) — emoji 终端
📊 上下文 ███░░░░░░░░░░░░░░░░░ 13% 100k / 1M 剩余 900k
🪙 Token 23k (in 22k · out 342 · cache 768)
▶ 当前任务 调研充电行业政策 (2/5)
# 中文 (zh) — 无 emoji 终端
# 上下文 ███░░░░░░░░░░░░░░░░░ 13% 100k / 1M 剩余 900k
$ Token 23k (in 22k · out 342 · cache 768)
> 当前任务 调研充电行业政策 (2/5)
# English (en) — emoji 终端
📊 Context ███░░░░░░░░░░░░░░░░░ 13% 100k / 1M left 900k
🪙 Token 23k (in 22k · out 342 · cache 768)
▶ Todos Research charging industry policy (2/5)
# 简约 (minimal) — 无 emoji, 无前缀
Context ███░░░░░░░░░░░░░░░░░ 13% 100k / 1M 剩余 900k
Token 23k (in 22k · out 342 · cache 768)
当前任务 调研充电行业政策 (2/5)
# 极简 (ultra-minimal) — 只显示两行
Context ███░░░░░░░░░░░░░░░░░ 13% 100k / 1M 剩余 900k
Token 23k (in 22k · out 342 · cache 768)
Step 1.5: 选择主题风格 (可选)
调用 AskUserQuestion 弹出主题选择菜单:
Use AskUserQuestion:
header: "Theme"
question: "选择进度条风格 / Select progress bar theme"
options:
- label: "经典 Classic (默认)"
description: "███░░░░░░░░ 经典实心方块"
- label: "霓虹 Neon"
description: "⟦ CTX: ▓▓▓▓░░░░ ⟧ 霓虹矩阵风"
- label: "点阵 Braille"
description: "⣿⣷⣯⣟░░░░ Braille 点阵"
- label: "硬核 Hardcore"
description: "[■■■□□□□□] CTX │ 硬核风"
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.
- 5d ago First seen · 343 lines · 20 tokens per session scan B 11b35288140c
setup is a command published in the GitHub repository zander-zyx/claude-mini-hud (10 stars, last pushed 8d ago), licensed MIT. It adds 20 tokens to every session and 4,088 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
scrim
Cost and tool-output report. Retrieve a stashed original with scrim get.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.