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/holyshite/claude-hud-for-apiWrote 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/holyshite/claude-hud-for-api/configure)<a href="https://agentmods.dev/commands/holyshite/claude-hud-for-api/configure"><img src="https://agentmods.dev/badge/commands/holyshite/claude-hud-for-api/configure/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/holyshite/claude-hud-for-api/configure"><img src="https://agentmods.dev/badge/commands/holyshite/claude-hud-for-api/configure.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 | $0.00014 | $0.01279 |
| Opus 5 | $0.00007 | $0.00639 |
| Sonnet 5 | $0.00003 | $0.00256 |
| Haiku 4.5 | $0.00001 | $0.00128 |
Grade A, and why
configure 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 8d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
配置 Claude HUD
交互式配置 HUD 插件，无需手动编辑 JSON。
你的任务
Step 1: 读取当前配置
Read ~/.claude/plugins/claude-hud/config.json。如果文件不存在，说明插件尚未初始化，提醒用户先运行 /claude-hud:setup。
Step 2: 展示当前配置和可选菜单
用 AskUserQuestion 让用户选择要配置的模块：
- 显示设置 — 布局、显示开关、token 分解等
- 颜色主题 — 阈值颜色、模型名称颜色、进度条样式
- 格式设置 — 模型名称格式、百分比精度
- Git 状态 — 显示分支、脏标记等
- 恢复默认 — 删除配置文件，恢复出厂设置
Step 3: 根据选择进行配置
如果选了「显示设置」：
先展示当前 display 配置，然后询问用户想修改哪些项。可配置项及说明：
| 字段 | 当前值 | 说明 | 可选值 |
|---|---|---|---|
lineLayout |
— | 布局模式 | compact（紧凑单行）、expanded（多行展开）、detailed（经典详细） |
showSeparators |
— | 各区块间用 | 分隔 |
true / false |
showModel |
— | 显示模型名称 | true / false |
showContextBar |
— | 显示上下文进度条 | true / false |
contextValue |
— | 上下文数值显示模式 | percent（百分比）、tokens（绝对数）、both（百分比+绝对数）、remaining（剩余百分比） |
showTokenCounts |
— | 显示输入/输出/总计 token | true / false |
showTokenBreakdown |
— | 显示 token 分类（in/cache） | true / false |
compactNumbers |
— | 大数字用 k/M 单位 | true / false |
showDuration |
— | 显示会话时长 | true / false |
showSpeed |
— | 显示 token 生成速率 | true / false |
showUsage |
— | 显示 API 速率限制（5h/7d） | true / false |
usageBarEnabled |
— | 速率限制进度条 | true / false |
usageThreshold |
— | 速率限制警告阈值（0-100） | 数字 |
showSessionTokens |
— | 显示会话累计 token | true / false |
showSessionName |
— | 显示会话名称 | true / false |
AskUserQuestion 每次最多 4 个选项，分多次询问或让用户在回答中自由描述想改什么。
用户说明要改的项后，使用 Edit 工具更新 config.json 中对应字段。
如果选了「颜色主题」：
先展示当前 color 配置，然后询问用户想修改的项：
| 字段 | 当前值 | 说明 | 可选值 |
|---|---|---|---|
safeThreshold |
— | 安全阈值（绿色） | 0–100 |
warningThreshold |
— | 警告阈值（红色） | 0–100 |
modelColor |
— | 模型名称颜色 | green、yellow、red、cyan、blue、magenta、dim |
progressStyle |
— | 进度条样式 | bar（条形 ████）、text（纯文本）、percentage（仅百分比） |
如果选了「格式设置」：
先展示当前 format 配置，然后询问用户想修改的项：
| 字段 | 当前值 | 说明 | 可选值 |
|---|---|---|---|
modelFormat |
— | 模型名称格式，支持 {name}（显示名）、{id}（模型 ID） |
字符串 |
percentagePrecision |
— | 百分比小数位数 | 0–3 |
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.
- 8d ago First seen · 92 lines · 14 tokens per session scan A ac6e104cd651
configure is a command published in the GitHub repository holyshite/claude-hud-for-api (2 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 1,279 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
visual
Restate a spec, task, diff, or the current topic as a compact markdown visual digest.
explore
Fast codebase exploration with Antigravity's agy CLI (Gemini 3.7 Flash, read-only). EXPERIMENTAL.
statusline
Show the governor fleet in your Claude Code statusline. Explicit, opt-in, and chains — it never replaces an existing statusline.
tasks
Inspect Modellix task status and recover tasks after a timeout or unknown submission.
resume
Auto-detect and resume any interrupted Plan Cascade task. Detects mega-plan, hybrid-worktree, or hybrid-auto context and routes to the appropriate resume command.
brief
Cold-start session orientation — use when starting fresh or returning after a long absence (days or weeks). Scales depth to how long you've been away. Not for quick mid-session checks (use /tools:status) or planning (use /tools:overview).