Borrowing it
Nothing to install: this file belongs to ghostwriternr/sandbox-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/ghostwriternr/sandbox-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/ghostwriternr/sandbox-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/ghostwriternr/sandbox-mcp/agents-md)<a href="https://agentmods.dev/instructions/ghostwriternr/sandbox-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ghostwriternr/sandbox-mcp/agents-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/ghostwriternr/sandbox-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ghostwriternr/sandbox-mcp/agents-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 | $0.02235 | $0.02235 |
| Opus 5.5 | $0.00894 | $0.00894 |
| Sonnet 5.5 | $0.00447 | $0.00447 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
sandbox-mcp 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 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.
How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidelines for AI agents and human contributors working on this codebase.
Project Overview
This is an MCP server that delegates coding tasks to OpenCode running in Cloudflare Sandboxes. It's built on Cloudflare Workers with Durable Objects, Workflows, Containers, and R2.
Architecture
┌─────────────────────────────────────────────────────────────────┐
│ MCP Client (Claude, etc.) │
└────────────────────────────┬────────────────────────────────────┘
│ MCP Protocol
┌────────────────────────────▼────────────────────────────────────┐
│ Cloudflare Worker │
│ Routes: /mcp, /proxy/*, /session/{id}/ │
└────────────────────────────┬────────────────────────────────────┘
│ │ │
┌────▼────┐ ┌──────▼──────┐ ┌─────▼─────┐
│ Proxy │ │ MCP Agent │ │ Web UI │
│ Handler │ │ (DO) │ │ Proxy │
└────┬────┘ └──────┬──────┘ └─────┬─────┘
│ │ │
│ ┌───────▼───────┐ │
│ │ Workflow │ │
│ └───────┬───────┘ │
│ │ │
┌────▼───────────────────▼───────────────────▼────┐
│ Cloudflare Sandbox │
│ ┌─────────────────────────────────────────┐ │
│ │ OpenCode Agent │ │
│ │ - Autonomous coding │ │
│ │ - Git operations │ │
│ │ - Web UI on port 4096 │ │
│ └─────────────────────────────────────────┘ │
└─────────────────────────────────────────────────┘
Key Components
| Component | Purpose |
|---|---|
| Worker | HTTP routing, MCP endpoint, proxy |
| MCP Agent (DO) | Protocol handling, tool implementation |
| Workflow | Long-running task orchestration (up to 50min) |
| Sandbox | Isolated container running OpenCode |
| R2 | Session metadata, workspace persistence |
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 · 284 lines · 2,235 tokens per session scan A d8337aca4c62
sandbox-mcp AGENTS.md is an instructions file published in the GitHub repository ghostwriternr/sandbox-mcp (24 stars, last pushed 10mo ago), licensed MIT. It adds 2,235 tokens to every session, about $0.0089 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.
sandbox-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sandbox-mcp AGENTS.mdghostwriternr/sandbox-mcp | Instructions file | 24 | 10mo ago | MIT | A | 2,235 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| 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 |