Borrowing it
Nothing to install: this file belongs to sj817/claude-code-plugin-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/sj817/claude-code-plugin-hud/main/CLAUDE.mdgit clone --depth 1 https://github.com/sj817/claude-code-plugin-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/sj817/claude-code-plugin-hud/claude-md)<a href="https://agentmods.dev/instructions/sj817/claude-code-plugin-hud/claude-md"><img src="https://agentmods.dev/badge/instructions/sj817/claude-code-plugin-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/sj817/claude-code-plugin-hud/claude-md"><img src="https://agentmods.dev/badge/instructions/sj817/claude-code-plugin-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 | $0.01758 | $0.01758 |
| Opus 5.5 | $0.00703 | $0.00703 |
| Sonnet 5.5 | $0.00352 | $0.00352 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
claude-code-plugin-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-code-plugin-hud — project notes
A Rust CLI that renders the Claude Code statusline, shipped as a Claude Code plugin.
- Package name:
claude-code-plugin-hud - Binary name:
claude-hud(kept short) - Prebuilt per-platform binaries ship in
dist/. - The namespaced
/claude-code-plugin-hud:setupcommand wires a binary into the user'ssettings.json. Plugins cannot set the mainstatusLinethemselves; only a command can.
How the statusline contract works
- Claude Code streams session JSON to the binary on stdin. Whatever the binary prints to stdout is shown, one rendered row per printed line.
- It runs after each assistant message, after
/compact, and on permission/vim changes (debounced 300ms). Setup also setsstatusLine.refreshInterval: 30(seconds) so cache/quota countdowns advance while idle. No background loop belongs in the binary: render once and exit on every invocation. - Terminal size comes from the
COLUMNS/LINESenv vars (v2.1.153+), nottput. KeepstatusLine.paddingat 0 because it adds spacing on top of Claude Code's built-in gutter. Reserve a small safety margin insideCOLUMNS. - Width math must count emoji as terminals paint them.
unicode-widthfollows East_Asian_Width, which calls⏱(U+23F1) one cell;char_cellsinrender.rsoverrides that range to 2. - Many JSON fields are optional or null (see
src/input.rs). Never unwrap. - Newer fields are also version-gated:
prompt_cacheandrate_limits.spend_limitneed v2.1.251+,pr.kindneeds v2.1.234+. Model them asOptionand keep a fallback, so older builds still render fully. - Permission mode (auto/plan/…) is not in the statusline JSON, so the HUD does
not show it. Hooks expose
permission_mode, but no hook fires on a bare shift+tab toggle, so it cannot be shown reliably. Omitted intentionally.
Architecture
| File | Responsibility |
|---|---|
src/main.rs |
Read stdin, parse, read $COLUMNS/$LINES, reserve the UI safety margin, print. |
src/input.rs |
Serde structs; every field optional/defaulted. |
src/ribbon.rs |
Model badge, plain context and secondary row, colored metrics, and width fitting. |
src/render.rs |
Layout rules: constant height, width-aware drop by priority, single bar, smart path. Start here for display changes. |
src/git.rs |
Branch + dirty flag; GitHub origin URL with a separate directory/session cache (5s TTL). |
src/theme.rs |
Calm 16-color palette, three accents (pink cache, soft-gold folder, orange quota band), and the usage / four-band quota threshold colors. |
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.
- 1mo ago Changed · +37 lines · +593 tokens per session 70e8ad24f30a
- 2mo ago First seen · 88 lines · 1,165 tokens per session scan A 95501c7f2157
claude-code-plugin-hud CLAUDE.md is an instructions file published in the GitHub repository sj817/claude-code-plugin-hud (4 stars, last pushed 1mo ago), licensed MIT. It adds 1,758 tokens to every session, about $0.0070 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 2026-08-31.
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).
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.