What is hc-create-sandbox?

A guided workflow for turning a project's test sandbox from a placeholder into a real test environment. A sandbox is the environment used to start, stop, inspect, and sometimes reset test runs.

Use it to implement and verify sandbox start, stop, and status commands, optionally add reset or seed operations, and connect them to verification settings.

It prevents tests from depending on an unfinished environment setup and checks that the required sandbox commands work repeatedly.

How harness-base/harness-control configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to harness-base/harness-control. 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/harness-base/harness-control/main/.agents/skills/hc-create-sandbox/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/harness-base/harness-control

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/harness-base/harness-control/hc-create-sandbox.svg)](https://agentmods.dev/skills/harness-base/harness-control/hc-create-sandbox)

Your own site

<a href="https://agentmods.dev/skills/harness-base/harness-control/hc-create-sandbox"><img src="https://agentmods.dev/badge/skills/harness-base/harness-control/hc-create-sandbox.svg" alt="Measured on agentmods" height="20"></a>

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,497 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00110	$0.03497
Opus 5	$0.00055	$0.01749
Sonnet 5	$0.00022	$0.00699
Haiku 4.5	$0.00011	$0.00350

Measured 8d ago against content hash 548f7d3e145c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hc-create-sandbox 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 8d 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/skills/hc-create-sandbox/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

引导式给工程把 sandbox 接实（hc-create-sandbox）

本 skill 管"给某个已接入 harness 的被管工程，把 sandbox（跑 e2e / 测试脚本要的运行环境）从 PENDING: 占位接成真命令"——照 sandbox 契约（唯一真相源 = docs/harness/SANDBOX_CONTRACT.md，依据 ADR-0019）建 起 / 停 / 查（+ 可选重置 / 导资产），真跑验收 → 接线登记 → 对抗评审到过。契约细节本文引用不复刻——语义有出入，以 SANDBOX_CONTRACT.md 为准。

形态 = 交互式引导（主 agent 当 sandbox 向导），同 hc-onboard / hc-tech-design 的「引导 → 用户确认 → 派 reviewer 对抗挑刺 → 回改 loop」——一条连贯对话、逐步确认、不可拆并行。

铁律（贯穿全程）：

形式源驱动、不预设：sandbox 底层形式（容器编排 / 虚拟机 / 本地进程 / 远程环境……）看项目实际有啥，摆选项 + 讲取舍让用户拍，不默认某种形式、不替用户定（rule-0015 / rule-0008）。
只建测试基础设施，绝不动业务代码：sandbox 脚本 / 配置 = 测试基础设施，落在工程自己里面（projects/<名>/ 下），不算业务代码、不越 hc-dev 的界；但本 skill 不改工程任何业务代码。

① 何时用 / 何时不用

用：给已接入的工程把 sandbox 接实——verification.yaml 里 sandbox / sandbox_down / sandbox_status 还是 PENDING:（或缺 status 这类不全），要按契约建齐起 / 停 / 查（+按需 reset / seed）并接线。用户说「接 sandbox / 建沙箱 / 补 sandbox_status / 测试环境接实 / 把沙箱接起来」时用。
不用：
- 跑测试 / 用例转脚本 → hc-test 脚本线（已实现，ADR-0024 写跑一体；sandbox 是它的硬前置，脚本线跑前的运行时卡门 up → status 归脚本线，不归本 skill）；
- 把工程接进 harness → hc-onboard（那里 sandbox 只留三态占位，接实来这）；
- 写功能 / 改业务代码 → hc-dev。
一句话边界：本 skill 只建"环境的起 / 停 / 查"这层测试基础设施并接线，不写测试、不跑测试、不动业务代码。

② 前置

工程已在 workspace/verification.yaml 有条目——还没有 = 工程没接入，先走 hc-onboard。
确认给哪个工程建：projects/ 是多工程目录，先明确目标工程，全程只动它那份。
动笔前先读 docs/harness/SANDBOX_CONTRACT.md（入口语义 / 数据口径 / 硬约束都在那，本 skill 各步引用它）。

③ 6 步流程（每步：问什么 / 确认什么 / 落什么）

第 1 步 · 定工程

问什么：给哪个工程建；读 workspace/verification.yaml 现状——该工程 sandbox / sandbox_down / sandbox_status 现在各是哪态（真命令 / PENDING: / N/A:），哪些要接实、哪些已有现成可对齐。
确认什么：目标工程 + 接实范围（三个必须入口之外，reset / seed 可选槽要不要，第 2 步聊完数据再定也行）跟用户核准。
落什么：先不落文件，确认的范围是后续所有步骤的边界。

第 2 步 · 摸现状 + 聊形式（源驱动，数据也这步聊定）

问什么：看项目实际有啥——已有容器编排配置就着它、纯本地进程就本地、依赖远程环境就远程；把可行形式摆选项 + 讲取舍（起停速度 / 可重建性 / 依赖多少 / 团队现有习惯）让用户拍，不预设形式。
资产数据也这步聊定：测试要用的基础数据有哪些（账号、基础配置、字典……）、从哪来（seed 文件？现有库导出后落仓版本化？压根没有=不需要 reset/seed？）；据此定可选槽 reset / seed 建不建（口径见 ④）。
确认什么：形式 + 资产数据清单 + 可选槽取舍，全部用户拍板了才动笔。
落什么：确认过的方案（形式 / 组件 / 资产来源 / 建哪几个入口），作为第 3 步的输入。

Read the full file on GitHub · 97 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.

8d ago First seen · 97 lines · 110 tokens per session scan A 548f7d3e145c

Subscribe to this mod's changes

hc-create-sandbox is a skill published in the GitHub repository harness-base/harness-control (22 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 3,497 once invoked, about $0.0006 per session on Opus 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

harness-control: Skill for Claude Code