What is cloud-sandbox-mcp-v2 AGENTS.md?

A set of operating instructions for an MCP-managed development workstation, which is a coding workspace controlled through a standard tool connection.

It helps agents create or resume workspaces, check project status and instructions, apply controlled file edits, run verification, review diffs, and report results.

It gives an agent a consistent process for inspecting, editing, testing, reviewing, and committing project changes while limiting actions such as pushing code.

How BernydotJar/cloud-sandbox-mcp-v2 configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to BernydotJar/cloud-sandbox-mcp-v2. 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/BernydotJar/cloud-sandbox-mcp-v2/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/BernydotJar/cloud-sandbox-mcp-v2

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/bernydotjar/cloud-sandbox-mcp-v2/agents-md/github.svg)](https://agentmods.dev/instructions/bernydotjar/cloud-sandbox-mcp-v2/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/bernydotjar/cloud-sandbox-mcp-v2/agents-md"><img src="https://agentmods.dev/badge/instructions/bernydotjar/cloud-sandbox-mcp-v2/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/bernydotjar/cloud-sandbox-mcp-v2/agents-md"><img src="https://agentmods.dev/badge/instructions/bernydotjar/cloud-sandbox-mcp-v2/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,068 This file is loaded in full into every session.

When invoked 1,068 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.

Model	Per session	Once invoked
Fable 5.1	$0.01068	$0.01068
Opus 5.5	$0.00427	$0.00427
Sonnet 5.5	$0.00214	$0.00214
Haiku 4.5	$0.00107	$0.00107

Measured 18d ago against content hash b031671b9ec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

cloud-sandbox-mcp-v2 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 18d 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.

AGENTS.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent operating protocol

When using this MCP server:

Create or resume one workspace per task.
Inspect workspace_status, repository instructions, and current diffs before editing.
Prefer file_apply_patch or file_write with expected_sha256 for controlled edits.
Use workspace_exec for repository inspection and development commands; do not attempt Docker, sudo, or git push there.
Run project_verify and inspect failures before claiming completion.
Review git_diff, then create a local commit.
Use git_push only after explicit authorization and only when enabled by the operator.
Report commands, exit codes, changed files, tests, assumptions, and remaining risks.

Optional capability: ArtCraft creative-production tools

ArtCraft (https://getartcraft.com/apps) is an optional, on-demand tool family for PDFs, images, UI design, video, presentations, and other creative artifacts. Treat each application and its automation interface independently; a website listing is not proof that a CLI, MCP server, or headless feature works.

Verified baseline and discovery

The canonical Linux ARM64 workstation previously passed PdfCraft CLI v0.10.1 smoke tests for info, text, and PDF-page render.
Its versioned installation is /workspace/.local/opt/artcraft/pdfcraft-cli/0.10.1, with entry point /workspace/.local/bin/pdfcraft-cli. Check that the executable is available in the active workstation before using it; installations are not assumed to exist in other containers, runtimes, or developer machines.
PhotoCraft, FigCraft, FilmCraft, VectorCraft, DeckCraft, and other ArtCraft applications are candidates, not installed or validated capabilities. Do not claim that they are operational or register nonexistent tools.
Prefer an existing documented native CLI/API over simulated GUI interaction when it meets the task requirements. Use browser automation only for actual UI flows and their reproducible QA.

Read the full file on GitHub · 98 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.

18d ago Changed · +85 lines · +916 tokens per session b031671b9ec4
2mo ago First seen · 13 lines · 152 tokens per session scan A e7ba3830d012

Subscribe to this mod's changes

cloud-sandbox-mcp-v2 AGENTS.md is an instructions file published in the GitHub repository BernydotJar/cloud-sandbox-mcp-v2 (0 stars, last pushed 19d ago), licensed MIT. It adds 1,068 tokens to every session, about $0.0043 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.

cloud-sandbox-mcp-v2 AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
cloud-sandbox-mcp-v2 AGENTS.mdBernydotJar/cloud-sandbox-mcp-v2	Instructions file	0	19d ago	MIT	A	1,068	Codex, OpenCode
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

cloud-sandbox-mcp-v2: Instructions file for Codex