Borrowing it
Nothing to install: this file belongs to uppinote20/claude-dashboard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/uppinote20/claude-dashboard/main/CLAUDE.mdgit clone --depth 1 https://github.com/uppinote20/claude-dashboardWrote 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/instructions/uppinote20/claude-dashboard/claude-md)<a href="https://agentmods.dev/instructions/uppinote20/claude-dashboard/claude-md"><img src="https://agentmods.dev/badge/instructions/uppinote20/claude-dashboard/claude-md/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/instructions/uppinote20/claude-dashboard/claude-md"><img src="https://agentmods.dev/badge/instructions/uppinote20/claude-dashboard/claude-md.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 | $0.04662 | $0.04662 |
| Opus 5 | $0.02331 | $0.02331 |
| Sonnet 5 | $0.00932 | $0.00932 |
| Haiku 4.5 | $0.00466 | $0.00466 |
Grade C, and why
claude-dashboard CLAUDE.md scanned grade C 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 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
3. Test with expired cache (`rm -rf ~/.cache/claude-dashboard/`) How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Configuration
Project Overview
claude-dashboard is a Claude Code plugin that provides a comprehensive status line with modular widget system, multi-line display, context usage, API rate limits, and cost tracking.
Tech Stack
- Runtime: Node.js 18+
- Language: TypeScript 5.0+
- Build: esbuild
- Target: Claude Code Plugin
Project Structure
claude-dashboard/
├── .claude-plugin/
│ ├── plugin.json # Plugin manifest
│ └── marketplace.json # Marketplace metadata
├── commands/
│ ├── setup.md # /claude-dashboard:setup command
│ └── check-usage.md # /claude-dashboard:check-usage command
├── hooks/
│ ├── hooks.json # SessionStart hook registration
│ └── ensure-statusline.mjs # Shim sync + settings migration
├── scripts/
│ ├── statusline-shim.mjs # Version-agnostic entry point (copied to PLUGIN_DATA)
│ ├── statusline.ts # Main entry point (status line)
│ ├── check-usage.ts # CLI usage dashboard entry point
│ ├── types.ts # TypeScript interfaces
│ ├── widgets/ # Widget system
│ │ ├── base.ts # Widget interface
│ │ ├── index.ts # Widget registry & orchestrator
│ │ ├── model.ts # Model widget
│ │ ├── context.ts # Context usage widget
│ │ ├── cost.ts # Cost widget
│ │ ├── rate-limit.ts # Rate limit widgets (5h, 7d)
│ │ ├── project-info.ts # Project info widget
│ │ ├── config-counts.ts # Config counts widget
│ │ ├── session-duration.ts # Session duration widget
│ │ ├── tool-activity.ts # Tool activity widget
│ │ ├── agent-status.ts # Agent status widget
│ │ ├── todo-progress.ts # Todo progress widget
│ │ ├── burn-rate.ts # Burn rate widget
│ │ ├── cache-hit.ts # Cache hit rate widget
│ │ ├── depletion-time.ts # Depletion time widget
│ │ ├── codex-usage.ts # Codex CLI usage widget
│ │ ├── gemini-usage.ts # Gemini CLI usage widget
│ │ ├── antigravity-usage.ts # Antigravity CLI usage widget
│ │ ├── zai-usage.ts # z.ai/ZHIPU usage widget
│ │ ├── usage-format.ts # Shared percent + reset countdown formatter
│ │ ├── token-breakdown.ts # Token breakdown widget
│ │ ├── performance.ts # Performance badge widget
│ │ ├── forecast.ts # Cost forecast widget
│ │ ├── budget.ts # Budget tracking widget
│ │ ├── token-speed.ts # Token speed widget
│ │ ├── session-name.ts # Session name widget
│ │ ├── today-cost.ts # Today cost widget
│ │ ├── last-prompt.ts # Last prompt widget
│ │ └── peak-hours.ts # Peak hours widget
│ └── utils/
│ ├── api-client.ts # OAuth API client with caching
│ ├── codex-client.ts # Codex CLI API client
│ ├── gemini-client.ts # Gemini CLI API client
│ ├── antigravity-client.ts # Antigravity CLI API client
│ ├── zai-api-client.ts # z.ai/ZHIPU API client
│ ├── provider.ts # Provider detection (anthropic/zai/zhipu)
│ ├── colors.ts # ANSI color codes + theme system
│ ├── credentials.ts # Keychain/credentials extraction (60s backoff on failure)
│ ├── debug.ts # Debug utilities
│ ├── formatters.ts # Token/cost/time/duration formatting
│ ├── hash.ts # Token hashing for cache keys
│ ├── i18n.ts # Internationalization
│ ├── progress-bar.ts # Progress bar rendering
│ ├── session.ts # Session duration tracking
│ ├── budget.ts # Budget tracking utilities
│ └── transcript-parser.ts # Transcript JSONL parsing
├── locales/
│ ├── en.json # English translations
│ └── ko.json # Korean translations
├── dist/
│ ├── index.js # Status line built output (committed)
│ └── check-usage.js # CLI usage dashboard built output (committed)
└── package.json
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 · 378 lines · 4,662 tokens per session scan C fb23dac5de6b
claude-dashboard CLAUDE.md is an instructions file published in the GitHub repository uppinote20/claude-dashboard (565 stars, last pushed 17d ago), licensed MIT. It adds 4,662 tokens to every session, about $0.0233 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.