claude-board: Instructions file for Claude Code

CLAUDE.md

claude-board CLAUDE.md is an instructions file for Claude Code from LukeLIN-web/claude-board. It costs 757 tokens per session, scanned A, original, MIT.

Project instructions for claude-board, including rules for testing the project with real Claude sessions. They describe which test model and session to use for live checks.

In plain words
What is it for?
Use them when performing live tests of claude-board, such as checking message delivery, verification, menus, or overlays.
Why use it?
They help keep test messages separate from normal work, reducing accidental costs and preventing test activity from changing the main conversation.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is LukeLIN-web/claude-board's own configuration. It tells Claude Code how to work on claude-board 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 claude-board configures →

Reuse

Borrowing it

Nothing to install: this file belongs to LukeLIN-web/claude-board. 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/LukeLIN-web/claude-board/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/LukeLIN-web/claude-board

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 claude-board CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lukelin-web/claude-board/claude-md"><img src="https://agentmods.dev/badge/instructions/lukelin-web/claude-board/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 757 This file is loaded in full into every session.
When invoked 757 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 $0.00757 $0.00757
Opus 5.5 $0.00303 $0.00303
Sonnet 5.5 $0.00151 $0.00151
Haiku 4.5 $0.00076 $0.00076

Measured 19d ago against content hash 70c6d09a1b44, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

claude-board 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 19d 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 · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core Engineering Principles

These principles apply unless a repository defines stricter rules.

1. Occam’s Razor

Do not introduce concepts, abstractions, states, mechanisms, or exceptions unless they are necessary.

This does not mean minimizing complexity at all costs. Complete systems may be complex, but their complexity should emerge from a small set of distilled, essential structures, composed through abstraction, encapsulation, and nesting.

Distilled is not the same as simple.

A superficially simple primitive may merely push complexity onto every caller. Prefer a small number of expressive, coherent primitives over many narrow primitives connected by ad hoc conventions.

Optimize for the minimum conceptual surface area, not the minimum line count.

Prefer:

  • composition over special cases;
  • general invariants over repeated local patches;
  • a small coherent core over many overlapping mechanisms;
  • removing a concept over adding machinery to compensate for it.

Before adding a new entity, determine whether it expresses an essential distinction or merely preserves accidental complexity.

2. Single Source of Truth

Every fact, rule, schema, configuration value, or state transition must have one semantic owner.

Other representations must be derived, generated, referenced, cached, or validated against that source. They must not become independent authorities.

When duplication is necessary, make the relationship explicit:

  • identify the canonical source;
  • derive secondary forms mechanically where possible;
  • define synchronization and invalidation rules;
  • prevent silent divergence.

SSOT does not require centralizing all code. It requires that each truth be defined exactly once.

When two representations disagree, remove the competing authority rather than adding reconciliation logic.

3. Eliminate Slop

我们要的是:基于凝练的原语,通过封装、抽象形成的复杂完整的系统.

Do not over-engineer unstable functionality. Early implementation should establish the correct behavior and expose the essential model, not anticipate every hypothetical requirement.

Read the full file on GitHub · 78 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. 19d ago Changed · +71 lines · +532 tokens per session 70c6d09a1b44
  2. 1mo ago Changed · +1 lines · +129 tokens per session 8470e2ed0108
  3. 2mo ago First seen · 6 lines · 96 tokens per session scan A fb7a6e631fe2

Subscribe to this mod's changes

claude-board CLAUDE.md is an instructions file published in the GitHub repository LukeLIN-web/claude-board (7 stars, last pushed today), licensed MIT. It adds 757 tokens to every session, about $0.0030 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.

Related

claude-board CLAUDE.md compared with instructions from other repositories

claude-board CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
claude-board CLAUDE.mdLukeLIN-web/claude-boardInstructions file7todayMITA757Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file279ktodayMITA4,325Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,086GitHub Copilot