benday: Instructions file for Claude Code

CLAUDE.md

benday CLAUDE.md is an instructions file for Claude Code from KacemMathlouthi/benday. It costs 1,409 tokens per session, scanned A, original, MIT.

A set of instructions for contributing to Benday, a web project built with Bun workspaces and Turbo, tools for managing multiple JavaScript packages. It lists the repository commands and its rule for validating changes.

In plain words
What is it for?
Use it when developing in the repository, running linting, formatting, type checks, tests, unused-code checks, registry generation, or the full build.
Why use it?
It tells coding agents how to install dependencies, check code, run tests, build the project, and confirm generated files were not changed unexpectedly.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is KacemMathlouthi/benday's own configuration. It tells Claude Code how to work on benday 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 benday configures →

Reuse

Borrowing it

Nothing to install: this file belongs to KacemMathlouthi/benday. 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/KacemMathlouthi/benday/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/KacemMathlouthi/benday

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 benday CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kacemmathlouthi/benday/claude-md"><img src="https://agentmods.dev/badge/instructions/kacemmathlouthi/benday/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,409 This file is loaded in full into every session.
When invoked 1,409 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01409 $0.01409
Opus 5.5 $0.00564 $0.00564
Sonnet 5.5 $0.00282 $0.00282
Haiku 4.5 $0.00141 $0.00141

Measured 2mo ago against content hash 352057c1efe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

benday 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 2mo 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.

CLAUDE.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 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 (claude.ai/code) when working with code in this repository.

CONTRIBUTING.md is the human-facing guide and is accurate — read it for the contribution workflow, the changeset rules, and the test rationale. This file covers what is only visible after reading across several files.

Commands

Bun workspaces driven by turbo. Run everything from the repo root.

bun install
bun run dev              # registry:build, then the docs site on :5173
bun run check            # lint and format (ultracite / oxlint + oxfmt)
bun run fix              # apply what check reports
bun run typecheck
bun run test             # the registry suite
bun run knip             # unused files, exports, dependencies
bun run build            # registry payloads, then every app
bun run registry:build   # regenerate apps/web/public/r/*.json only

CI runs check, typecheck, test, knip, registry:build, a git diff --exit-code on apps/web/public/r, and build.

A single test file or a single test — bun test has no turbo wrapper worth using here:

cd registry && bun test tests/bake.test.ts
cd registry && bun test -t "normalizes depth"

The one structural rule

registry/ is the product. It mirrors the tree the shadcn CLI writes into a consumer's project, which is why its internal imports are relative (./benday/renderer) and never aliased, and why only React may be imported. apps/web reaches the same source through the @registry/* alias instead of keeping a copy, so every example on the docs site is the code that ships.

apps/web/public/r/*.json is generated by registry:build and committed. Any change under registry/ must be committed together with the regenerated payloads and a changeset, or CI fails on drift.

Architecture

The pipeline is image → DotMap → canvas. bake.ts rasterizes a logo, separates ink from background (alpha when the source has soft pixels, otherwise a luminance mask estimated from the corners), derives a separate tone channel, runs an exact Euclidean distance transform so every dot carries its depth inside the shape, and grid-samples the result. The output is small and JSON-serializable on purpose: consumers can run the bake at build time and pass dotMap instead of src, skipping all of it on the client. bake is browser-only — it goes through a canvas.

Read the full file on GitHub · 65 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. 2mo ago First seen · 65 lines · 1,409 tokens per session scan A 352057c1efe6

Subscribe to this mod's changes

benday CLAUDE.md is an instructions file published in the GitHub repository KacemMathlouthi/benday (42 stars, last pushed 2mo ago), licensed MIT. It adds 1,409 tokens to every session, about $0.0056 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.

Related

benday CLAUDE.md compared with instructions from other repositories

benday CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
benday CLAUDE.mdKacemMathlouthi/bendayInstructions file422mo agoMITA1,409Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode