claude-hud: Instructions file for Claude Code

CLAUDE.md

claude-hud CLAUDE.md is an instructions file for Claude Code from jarrodwatts/claude-hud. It costs 1,531 tokens per session, scanned B, original, MIT.

A project instruction file for Claude Code that explains how to build, test, and understand the Claude HUD plugin. It documents how the plugin receives data and renders its status display.

In plain words
What is it for?
Use it when asking Claude Code to modify, build, or test the Claude HUD project. It also helps explain how input data becomes the displayed status lines.
Why use it?
It gives the coding agent the project-specific context and commands needed to work on the repository correctly. This reduces guesswork about the code structure and testing process.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the TodoWrite tool.

This is jarrodwatts/claude-hud's own configuration. It tells Claude Code how to work on claude-hud itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-hud configures →

About the project

Claude HUD is a Claude Code plugin that displays information about the current coding-agent session, including context usage, active tools, running agents, and todo progress. It is used by Claude Code users who want session status visible while they work. The catalogue includes the plugin and related commands and instructions.

jarrodwatts/claude-hud · 27,889 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to jarrodwatts/claude-hud. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jarrodwatts/claude-hud/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jarrodwatts/claude-hud

Made for: Claude Code.

Wrote 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.

agentmods badge for claude-hud CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jarrodwatts/claude-hud/claude-md/github.svg)](https://agentmods.dev/instructions/jarrodwatts/claude-hud/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jarrodwatts/claude-hud/claude-md"><img src="https://agentmods.dev/badge/instructions/jarrodwatts/claude-hud/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.

agentmods 80×15 button for claude-hud CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jarrodwatts/claude-hud/claude-md"><img src="https://agentmods.dev/badge/instructions/jarrodwatts/claude-hud/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,531 This file is loaded in full into every session.
When invoked 1,531 The same file — it is already loaded in full.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01531 $0.01531
Opus 5 $0.00766 $0.00766
Sonnet 5 $0.00306 $0.00306
Haiku 4.5 $0.00153 $0.00153

Measured 10d ago against content hash 57e576c3156c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

claude-hud CLAUDE.md 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- MCP count from `~/.claude/settings.json` (mcpServers)
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code when working with this repository.

Project Overview

Claude HUD is a Claude Code plugin that displays a real-time multi-line statusline. It shows context health, tool activity, agent status, and todo progress.

Build Commands

npm ci               # Install dependencies
npm run build        # Build TypeScript to dist/

# Test with sample stdin data
echo '{"model":{"display_name":"Opus"},"context_window":{"current_usage":{"input_tokens":45000},"context_window_size":200000}}' | node dist/index.js

Architecture

Data Flow

Claude Code → stdin JSON → parse → render lines → stdout → Claude Code displays
           ↘ transcript_path → parse JSONL → tools/agents/todos

Key insight: The statusline is invoked by Claude Code after each interaction (new assistant message, /compact finishing, permission-mode changes, vim-mode toggles), debounced at 300ms — not on a fixed polling loop. Each invocation:

  1. Receives JSON via stdin (model, context, tokens - native accurate data)
  2. Parses the transcript JSONL file for tools, agents, and todos
  3. Renders multi-line output to stdout
  4. Claude Code displays all lines

Data Sources

Native from stdin JSON (accurate, no estimation):

  • model.display_name - Current model
  • context_window.current_usage - Token counts
  • context_window.context_window_size - Max context
  • transcript_path - Path to session transcript

From transcript JSONL parsing:

  • tool_use blocks → tool name, input, start time
  • tool_result blocks → completion, duration
  • Running tools = tool_use without matching tool_result
  • TodoWrite calls → todo list
  • Task calls → agent info

From config files:

  • MCP count from ~/.claude/settings.json (mcpServers)
  • Hooks count from ~/.claude/settings.json (hooks)
  • Rules count from CLAUDE.md files

From Claude Code stdin rate limits:

  • rate_limits.five_hour.used_percentage - 5-hour subscriber usage percentage
  • rate_limits.five_hour.resets_at - 5-hour reset timestamp
  • rate_limits.seven_day.used_percentage - 7-day subscriber usage percentage
  • rate_limits.seven_day.resets_at - 7-day reset timestamp

Read the full file on GitHub · 147 lines

Changes

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.

  1. 10d ago First seen · 147 lines · 1,531 tokens per session scan B 57e576c3156c

Subscribe to this mod's changes

claude-hud CLAUDE.md is an instructions file published in the GitHub repository jarrodwatts/claude-hud (27,889 stars, last pushed 3d ago), licensed MIT. It adds 1,531 tokens to every session, about $0.0077 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.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens