agentmods.dev

modal-workspace

modal-workspace is a skill for Claude Code, Codex from xiaoqianran/modal-workspace-mcp. It costs 36 tokens per session (302 once invoked), scanned A, original, MIT.

A skill for running work in a user-owned Modal workspace, which is a remote computing environment, when the local machine is unsuitable.

In plain words
What is it for?
It is for creating sandboxes, running commands and long jobs remotely, managing files, calling deployed Modal functions, and safely handling approved secrets.
Why use it?
It provides an alternative when local networking, dependencies, graphics hardware, or task length cause problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 0repo 2mo ago A scan 36 tokens original MIT

Good fit It is for creating sandboxes, running commands and long jobs remotely, managing files, calling deployed Modal functions, and safely handling approved secrets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xiaoqianran/modal-workspace-mcp/modal-workspace
View source ↗ xiaoqianran/modal-workspace-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add xiaoqianran/modal-workspace-mcp --skill modal-workspace
Clone the repo
git clone --depth 1 https://github.com/xiaoqianran/modal-workspace-mcp

Made for: Claude Code, Codex.

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 modal-workspace

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaoqianran/modal-workspace-mcp/modal-workspace/github.svg)](https://agentmods.dev/skills/xiaoqianran/modal-workspace-mcp/modal-workspace)
Your own site
<a href="https://agentmods.dev/skills/xiaoqianran/modal-workspace-mcp/modal-workspace"><img src="https://agentmods.dev/badge/skills/xiaoqianran/modal-workspace-mcp/modal-workspace/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 modal-workspace

Your own site · 80×15
<a href="https://agentmods.dev/skills/xiaoqianran/modal-workspace-mcp/modal-workspace"><img src="https://agentmods.dev/badge/skills/xiaoqianran/modal-workspace-mcp/modal-workspace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00036 $0.00302
Opus 5.5 $0.00014 $0.00121
Sonnet 5.5 $0.00007 $0.00060
Haiku 4.5 $0.00004 $0.00030

Measured 2mo ago against content hash 4ba53f1ac780, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

modal-workspace scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

1. 本地 `apt/curl/git/pip/uv` 因网络或权限失败时，不要反复重试本地容器，改用 `sandbox_create` + Modal 工具。
plugins/modal-workspace/skills/modal-workspace/SKILL.md · 16 lines

What it actually says

  1. 本地 apt/curl/git/pip/uv 因网络或权限失败时，不要反复重试本地容器，改用 sandbox_create + Modal 工具。
  2. 短命令使用 sandbox_exec；安装、下载、编译、长测试使用 sandbox_exec_start，再轮询 sandbox_job_status。
  3. 同一任务尽量复用 sandbox_id，任务完成后 sandbox_terminate。
  4. 读写普通文本文件优先使用 sandbox_file_*，不要为了简单文件操作拼复杂 shell quoting。
  5. 不得通过 env、echo、set、日志或聊天正文泄露 Secret。需要凭据时只传已 allowlist 的 secret_names。
  6. 需要稳定低延迟创建 Sandbox 时优先使用 Named Image (image_name)；临时依赖才用 apt_packages/pip_packages 动态构建。
  7. 可使用 function_spawn + function_call_get 处理已部署 Modal Function 的异步调用。
  8. 删除路径前核对目标；网关拒绝删除 Sandbox 根目录 /。
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 · 16 lines · 36 tokens per session scan A 4ba53f1ac780

Subscribe to this mod's changes

modal-workspace is a skill published in the GitHub repository xiaoqianran/modal-workspace-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 302 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

CloudDevOps and cloud
Related

modal-workspace compared with skills from other repositories

modal-workspace next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
modal-workspacexiaoqianran/modal-workspace-mcpSkill02mo agoMITA36Claude Code, Codex
gke-compute-classesgoogle/skillsSkill24k2d agoApache-2.0A83Claude Code, Codex
gke-workload-securitygoogle/skillsSkill24k2d agoApache-2.0A171Claude Code, Codex
gke-reliabilitygoogle/skillsSkill24k2d agoApache-2.0A85Claude Code, Codex
cloud-architectJeffallan/claude-skillsSkill12k9d agoMITA71Claude Code
nemo-automodel-launcher-configNVIDIA/skillsSkill3.9k2d agoApache-2.0A30Claude Code
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2k2d agoMITA78Claude Code