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/352727664/claude-hud-multiproviderWrote 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/352727664/claude-hud-multiprovider/configure)<a href="https://agentmods.dev/commands/352727664/claude-hud-multiprovider/configure"><img src="https://agentmods.dev/badge/commands/352727664/claude-hud-multiprovider/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/352727664/claude-hud-multiprovider/configure"><img src="https://agentmods.dev/badge/commands/352727664/claude-hud-multiprovider/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 | $0.00017 | $0.02886 |
| Opus 5 | $0.00009 | $0.01443 |
| Sonnet 5 | $0.00003 | $0.00577 |
| Haiku 4.5 | $0.00002 | $0.00289 |
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 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.
This is a copy
88% identical to configure — 60 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Claude HUD
FIRST: Use the Read tool to load ~/.claude/plugins/claude-hud/config.json if it exists.
Store current values and note whether config exists (determines which flow to use).
Always On (Core Features)
These are always enabled and NOT configurable:
- Model name
[Opus] - Context bar
████░░░░░░ 45%
Advanced settings such as colors.*, pathLevels, display.usageThreshold, and
display.environmentThreshold are preserved when saving but are not edited by this guided flow.
Two Flows Based on Config State
Flow A: New User (no config)
Questions: Layout → Preset → Turn Off → Turn On
Flow B: Update Config (config exists)
Questions: Turn Off → Turn On → Git Style → Layout/Reset → Custom Line (5 questions max)
Flow A: New User (5 Questions)
Q1: Layout
- header: "Layout"
- question: "Choose your HUD layout:"
- multiSelect: false
- options:
- "Expanded (Recommended)" - Split into semantic lines (identity, project, environment, usage)
- "Compact" - Everything on one line
- "Compact + Separators" - One line with separator before activity
Q2: Preset
- header: "Preset"
- question: "Choose a starting configuration:"
- multiSelect: false
- options:
- "Full" - Everything enabled (Recommended)
- "Essential" - Activity + git, minimal info
- "Minimal" - Core only (model, context bar)
Q3: Turn Off (based on chosen preset)
- header: "Turn Off"
- question: "Disable any of these? (enabled by your preset)"
- multiSelect: true
- options: ONLY items that are ON in the chosen preset (max 4)
- "Tools activity" - ◐ Edit: file.ts | ✓ Read ×3
- "Agents status" - ◐ explore [haiku]: Finding code
- "Todo progress" - ▸ Fix bug (2/5 tasks)
- "Project name" - my-project path display
- "Git status" - git:(main*) branch indicator
- "Config counts" - 2 CLAUDE.md | 4 rules
- "Token breakdown" - (in: 45k, cache: 12k)
- "Output speed" - out: 42.1 tok/s
- "Usage limits" - 5h: 25% | 7d: 10%
- "Session duration" - ⏱️ 5m
- "Session name" - fix-auth-bug (session slug or custom title)
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 · 306 lines · 17 tokens per session scan A 310626684ce5
configure is a command published in the GitHub repository 352727664/claude-hud-multiprovider (2 stars, last pushed 2mo ago), licensed MIT. It adds 17 tokens to every session and 2,886 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to configure, differing in 60 lines, and is treated as a copy.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.