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/hadamyeedady12-dev/claude-ultimate-hud/setupgit clone --depth 1 https://github.com/hadamyeedady12-dev/claude-ultimate-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/hadamyeedady12-dev/claude-ultimate-hud/setup)<a href="https://agentmods.dev/commands/hadamyeedady12-dev/claude-ultimate-hud/setup"><img src="https://agentmods.dev/badge/commands/hadamyeedady12-dev/claude-ultimate-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 | $0.00011 | $0.01673 |
| Opus 5 | $0.00005 | $0.00837 |
| Sonnet 5 | $0.00002 | $0.00335 |
| Haiku 4.5 | $0.00001 | $0.00167 |
Grade B, and why
setup scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Read `~/.claude/settings.json` (or `$env:USERPROFILE\.claude\settings.json` on Windows). How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Ultimate HUD Setup
Configure the claude-ultimate-hud status line plugin with automatic runtime and platform detection.
Step 0: Ask User Preferences (if not provided via arguments)
Use AskUserQuestion to ask for both language and plan in a single call (up to 2 questions):
Question 1 - Language (if $1 not provided):
- header: "Language"
- question: "Which language do you prefer for the HUD?"
- options:
en: English (Recommended)ko: Korean (한국어)auto: Auto-detect from system locale
Question 2 - Plan (if $2 not provided):
- header: "Plan"
- question: "Which subscription plan are you on?"
- options:
max200: Max $200/mo (20x) - 5h + 7d all + 7d Sonnet (Recommended)max100: Max $100/mo (5x) - 5h + 7d all + 7d Sonnetpro: Pro - 5h onlyenterprise: Enterprise - Cost in $ + 5h
Use the selected values for the rest of the setup.
Arguments (optional, skips interactive selection)
-
$1: Language preferenceauto(default): Detect from system languageen: Englishko: Korean (한국어)
-
$2: Subscription planpro: Shows 5h rate limit onlymax100: Shows 5h + 7d all + 7d Sonnet (Max $100/월 플랜)max200(default): Shows 5h + 7d all + 7d Sonnet (Max $200/월 플랜)enterprise: Shows cost in $ + 5h rate limit (Enterprise 플랜)
Step 1: Detect Platform & Runtime
macOS/Linux (if uname -s returns "Darwin", "Linux", or MINGW*/MSYS*/CYGWIN*):
-
Get plugin path (check cache/marketplace first, then manual install):
ls -td ~/.claude/plugins/cache/claude-ultimate-hud/claude-ultimate-hud/*/ 2>/dev/null | head -1 || ls -d ~/.claude/plugins/claude-ultimate-hud/ 2>/dev/nullIf empty, plugin is not installed.
-
Get runtime absolute path (prefer bun, fallback to node):
command -v bun 2>/dev/null || command -v node 2>/dev/nullIf empty, tell user to install Node.js or Bun.
-
Determine source file based on runtime:
- If runtime is
bun: usesrc/index.ts - Otherwise: use
dist/index.js
- If runtime is
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 · 168 lines · 11 tokens per session scan B c1a0f57232a2
setup is a command published in the GitHub repository hadamyeedady12-dev/claude-ultimate-hud (48 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 1,673 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 2026-08-30.
Other commands, from other repositories
setup
Configure cc-hud statusline in Claude Code settings.
configure
Configure HUD display options (layout, language, presets, display elements) while preserving advanced manual overrides.
inbox
Check and respond to inter-agent messages.
recover-context
Strategically explore the most recent parent session from the session lineage (shown in the first user message) to extract the full context of the last task.
orchestrate
複数Issueを並列オーケストレーション（準備→開発→PR→マージ→UAT→修正ループ→完了）.
issue-enhance
Issue内容を分析し、ユーザーに質問しながら不足情報を補完・更新.