Borrowing it
Nothing to install: this file belongs to CrackenReleased/boarderless.app_MCP. 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/CrackenReleased/boarderless.app_MCP/main/CLAUDE.mdgit clone --depth 1 https://github.com/CrackenReleased/boarderless.app_MCPWrote 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/crackenreleased/boarderless.app_mcp/claude-md)<a href="https://agentmods.dev/instructions/crackenreleased/boarderless.app_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/crackenreleased/boarderless.app_mcp/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/crackenreleased/boarderless.app_mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/crackenreleased/boarderless.app_mcp/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 | $0.00385 | $0.00385 |
| Opus 5.5 | $0.00154 | $0.00154 |
| Sonnet 5.5 | $0.00077 | $0.00077 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
boarderless.app_MCP 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.
What it actually says
CLAUDE.md
Before doing anything in this repo, read SOUL.md and AGENTS.md.
They are binding, not aspirational.
Boarderless visible-operation law: never run, attach to, enable, document, or tolerate a headless or otherwise invisible Boarderless browser. MCP work must bring the real canvas tab to the front so Joel can watch every Ai interaction. Run npm run verify:visible-operation before completion.
The one rule that governs all others: ZERO APATHY
Never do the minimum. Whatever lands in your lap gets finished, polished, functional, and beautiful — the first time, without being asked twice.
The standard is the castle wall: 12' wide, 30' tall, stone — two laden chariots race across the top and not a pebble moves. For what it is, perfect.
Non-negotiables (full detail in AGENTS.md):
- HTML deliverables are LIVE: real links (default: https://play.boarderless.app), working buttons, hover states. Never a div cosplaying as a button.
- Verify your own output by rendering/running it before presenting it.
- One flaw found = sweep every sibling file for the same flaw.
- Match the existing brand system (
ads/AD_SPEC.md); never freelance a look. - If you must deliver less than the full thing, say so out loud — no silent downgrades.
- Run the Definition of Done checklist in AGENTS.md before calling anything done.
Project context
Boarderless MCP server — connects AI agents (Claude Desktop, Cursor, Windsurf)
to the live Boarderless canvas via a typed spatial ledger. Windows + Chromium
first. See README.md and docs/features_catalog.md before proposing work.
Ad assets and brand tokens live in ads/.
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.
- 2mo ago First seen · 33 lines · 385 tokens per session scan A dfc88f585cce
boarderless.app_MCP CLAUDE.md is an instructions file published in the GitHub repository CrackenReleased/boarderless.app_MCP (1 stars, last pushed today), licensed Apache-2.0. It adds 385 tokens to every session, about $0.0015 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.
boarderless.app_MCP CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| boarderless.app_MCP CLAUDE.mdCrackenReleased/boarderless.app_MCP | Instructions file | 1 | today | Apache-2.0 | A | 385 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |