boxento AGENTS.md

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/sushaantu/boxento/agents-md

Clone the repo

git clone --depth 1 https://github.com/sushaantu/boxento

Made for: Codex, OpenCode.

Per session 1,882 This file is loaded in full into every session.

When invoked 1,882 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.01882	$0.01882
Opus 5	$0.00941	$0.00941
Sonnet 5	$0.00376	$0.00376
Haiku 4.5	$0.00188	$0.00188

Measured today against content hash 089eacde9a90, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

boxento 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 today.

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.

AGENTS.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Instructions

When you provide instructions in addition to technical stuff, also include product manager ready instructions.

Use this file as the source of truth when creating, updating, or reviewing Boxento widgets.

Source Of Truth In Code

Read these files before making widget UX decisions:

docs/WIDGET_DEVELOPMENT.md
src/components/widgets/common/WidgetShell.tsx
src/components/widgets/common/WidgetSettingsDialog.tsx
src/components/widgets/common/widgetHeaderStyles.ts
src/components/dashboard/DashboardWidgetFrame.tsx
src/components/widgets/index.ts

Use these widgets as implementation anchors for size-spectrum behavior:

src/components/widgets/TodoWidget/index.tsx
src/components/widgets/NotesWidget/index.tsx
src/components/widgets/WeatherWidget/index.tsx
src/components/widgets/QuickLinksWidget/index.tsx
src/components/widgets/RSSWidget/index.tsx

Core Principle

Design every widget as a size spectrum, not a single squeezed layout:

1x1 glance state
compact widget state
standard widget state
panel state
app state

As the widget gets larger, reveal more workflow, context, and controls. Do not simply scale the same crowded UI up or down.

Shell Rules

Prefer WidgetShell for new or heavily refactored widgets.
Keep the root layout aligned with Boxento's flex model: widget-container, flex, h-full, flex-col.
Keep the content area resilient to resizing with min-h-0, flex-1, and deliberate overflow behavior.
Use contentClassName on WidgetShell to adjust density by size instead of creating a second shell system.
Keep the header visually integrated with content. Do not add a bottom border or separator line under the header.
Keep the settings entry point in the header unless the widget is tiny or fully app-sized and the app layout already has a clearer control surface.

Header Rules

Hide the outer header in tiny mode.
Prefer hiding the outer header in app mode when the app surface has its own title, toolbar, tabs, or filters.
Use compact header spacing only when the widget is short or dense enough that the default header would crowd the content.
Use a clear, short title that matches the widget's user value.
Keep header actions minimal. The settings button is standard; add other actions only when they are truly primary.
In one-column, tiny, or short-row sizes, do not show clipped titles such as Weat.... Hide the outer header and expose settings through a size-appropriate overlay/control when the standard header cannot fit.

Read the full file on GitHub · 196 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.

today First seen · 196 lines · 1,882 tokens per session scan A 089eacde9a90

Subscribe to this mod's changes

boxento AGENTS.md is an instructions file published in the GitHub repository sushaantu/boxento (153 stars, last pushed 20d ago), licensed MIT. It adds 1,882 tokens to every session, about $0.0094 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 2026-09-01.

Frontend Productivity startpage widgets

xtool CLAUDE.md

Instructions for 2389-research/xtool, covering xtool plugin, skills included, using-xtool (main skill), key patterns and xtool is not xcodegen.

2389-research/xtool · 525 tokens

ccstatuswidgets CLAUDE.md

Instructions for warunacds/ccstatuswidgets, covering ccstatuswidgets, what this is, build & test, architecture and package map.

warunacds/ccstatuswidgets · 2,359 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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

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 · 5,182 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 · 4,345 tokens