What is claude-mini-hud AGENTS.md?

Repository instructions for claude-mini-hud, a small Claude Code status-line plugin. The plugin reads structured data from standard input and displays items such as context use, token details, tasks, and optionally the model name.

Use them when installing dependencies, building, type-checking, testing, or modifying the plugin's TypeScript modules and language settings.

They give coding agents the project background, architecture, supported platforms, and commands needed to work safely in the repository.

How zander-zyx/claude-mini-hud configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to zander-zyx/claude-mini-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/zander-zyx/claude-mini-hud/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/zander-zyx/claude-mini-hud

Made for: Claude Code, Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/zander-zyx/claude-mini-hud/agents-md.svg)](https://agentmods.dev/instructions/zander-zyx/claude-mini-hud/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/zander-zyx/claude-mini-hud/agents-md"><img src="https://agentmods.dev/badge/instructions/zander-zyx/claude-mini-hud/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,347 This file is loaded in full into every session.

When invoked 1,347 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.01347	$0.01347
Opus 5	$0.00674	$0.00674
Sonnet 5	$0.00269	$0.00269
Haiku 4.5	$0.00135	$0.00135

Measured 8d ago against content hash 9af31e523928, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

claude-mini-hud AGENTS.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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

claude-mini-hud CLAUDE.md — 97% identical, 4 lines differ

AGENTS.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.

Project Overview

claude-mini-hud is a minimal, zero-dependency Claude Code StatusLine plugin. It reads JSON from stdin (per the StatusLine contract) and outputs ANSI-colored status lines (context usage, token breakdown, current todo, optional model name). Multi-module architecture under src/.

Commands

npm install          # Install dev dependencies
npm run build        # Compile TypeScript to dist/
npm run dev          # Watch mode compilation
npm run typecheck    # Type-check tests (tsconfig.test.json, no emit)
npm test             # Full suite: build + typecheck + 57 tests

No linter is configured. Tests use Node.js built-in node:test + node:assert/strict, run via tsx.

Architecture

Multi-module design — src/ contains:

index.ts — Entry point, stdin reader, main() orchestrator
types.ts — Shared type definitions (StdinData, TodoItem, etc.)
i18n.ts — STRINGS object with zh/en/minimal/ultra-minimal keys, selected by CLAUDE_MINI_HUD_LANG
colors.ts — ANSI color helpers (zero-dependency)
themes.ts — Progress bar theme system (ThemeConfig), selected by CLAUDE_MINI_HUD_THEME
render.ts — All render functions (context, token, model, todo, usage)
transcript.ts — Transcript JSONL parser
usage.ts — Multi-platform usage/quota query (13 providers)

Plugin integration via .claude-plugin/plugin.json (registers the setup command) and commands/setup.md (interactive setup skill).

Two tsconfig files — tsconfig.json compiles only src/ → dist/; tsconfig.test.json adds tests/ with noEmit: true.

Supported Platforms

Platform	Detection	Query Method
Claude native	`rate_limits` in stdin	stdin (no HTTP)
MiniMax	URL contains `minimaxi.com` / `minimax.io`	HTTP API
智谱 (GLM)	URL contains `bigmodel.cn` / `z.ai`	HTTP API
小米 (MiMo)	URL contains `xiaomimimo`	HTTP + Cookie (`XIAOMI_COOKIE`)
阿里 (DashScope)	URL contains `dashscope`	Aliyun BSS OpenAPI (`ALIYUN_AK_ID`/`ALIYUN_AK_SECRET`)
火山引擎 (Ark)	URL contains `volces.com`	Detection only (management API not integrated)
百度千帆 (Qianfan)	URL contains `qianfan` / `baidubce`	No public API
腾讯混元 (Hunyuan)	URL contains `hunyuan`	No public API
讯飞星辰 (Astron)	URL contains `xfyun` / `spark-api`	Subscription (no API)
DeepSeek	URL contains `deepseek.com`	HTTP API
Kimi	URL contains `moonshot.cn` / `moonshot.ai`	HTTP API (`MOONSHOT_API_KEY` or proxy token)
阶跃星辰 (StepFun)	URL contains `stepfun.com` / `stepfun.ai`	HTTP API
硅基流动 (SiliconFlow)	URL contains `siliconflow.cn` / `siliconflow.com`	HTTP API

Read the full file on GitHub · 66 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.

8d ago First seen · 66 lines · 1,347 tokens per session scan A 9af31e523928

Subscribe to this mod's changes

claude-mini-hud AGENTS.md is an instructions file published in the GitHub repository zander-zyx/claude-mini-hud (10 stars, last pushed 12d ago), licensed MIT. It adds 1,347 tokens to every session, about $0.0067 per session on Opus 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.

Claude Code anthropic claude claude-code-plugin cli context-window

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

claude-mini-hud: Instructions file for Claude Code