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.
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.
curl -O https://raw.githubusercontent.com/jarrodwatts/claude-hud/main/CLAUDE.mdgit clone --depth 1 https://github.com/jarrodwatts/claude-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/instructions/jarrodwatts/claude-hud/claude-md)<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.
<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>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 | $0.00709 | $0.00709 |
| Opus 5.5 | $0.00284 | $0.00284 |
| Sonnet 5.5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
claude-hud CLAUDE.md 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 28d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- claude-hud-multiprovider CLAUDE.md — 86% identical, 128 lines differ
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Claude HUD is a Claude Code plugin: a status line command that prints a two-line HUD (model, project, git, context, usage), plus opt-in lines for tools, agents, todos, and more.
Commands
npm ci
npm test # builds dist/, then runs node --test
npm run test:update-snapshots # regenerate tests/golden/expected.txt after an intended output change
echo '{"model":{"display_name":"Opus"},"context_window":{"used_percentage":45,"context_window_size":200000}}' | node dist/index.js
How a render works
Claude Code runs the command after each message, /compact, a mode change, a rate-limit reset, or a prompt-cache expiry (debounced 300ms), plus on refreshInterval if set. Each run is a fresh process:
stdin.tsreads the payload. It targets Claude Code ≥ 2.1.260 and trusts its fields (version,cost,prompt_cache,session_name,output_style,workspace.repo,rate_limits) instead of deriving them.config.tsloadsplugins/claude-hud/config.jsonplus the per-directoryclaude-hud.jsonoverride.DEFAULT_CONFIGis the schema; a rules table validates each key.index.tsgathers only what enabled elements need, in parallel: the transcript (transcript.ts), git or jj (git.ts,jj.ts), the extra command, memory, auth, config counts, the usage snapshot, the cost ledger, and speed state. All I/O and state writes happen here.render/turns that into lines without I/O. Each element has one implementation inparts.ts,context.ts,usage.ts,vcs.ts,lines.ts, andactivity.ts.expanded.tsandcompact.tsonly arrange those parts, andansi.tsmeasures and wraps.
Invariants
- The default HUD is two lines. New display is opt-in; see the scope section of CONTRIBUTING.md.
- Text from stdin, the transcript, git, or config is untrusted terminal input. Sanitize it (
utils/sanitize.ts) before it's printed. - Rendering is pure: the clock and terminal width are sampled once in
renderLines. tests/golden.test.jspins end-to-end output. An output change must show up as a reviewed diff totests/golden/expected.txt.dist/is built by CI on main. Never commit it in a PR.README.mdandREADME.zh.mddocument every key inDEFAULT_CONFIG, andtests/readme-options.test.jsenforces it.
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.
- 28d ago Changed · -110 lines · -822 tokens per session scan B → A 3249ab03a208
- 2mo ago First seen · 147 lines · 1,531 tokens per session scan B 57e576c3156c
claude-hud CLAUDE.md is an instructions file published in the GitHub repository jarrodwatts/claude-hud (29,009 stars, last pushed today), licensed MIT. It adds 709 tokens to every session, about $0.0028 per session on Opus 5.5. 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 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.