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.
curl -O https://raw.githubusercontent.com/harness-base/harness-control/main/.agents/skills/hc-onboard/SKILL.mdgit clone --depth 1 https://github.com/harness-base/harness-controlWrote 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/skills/harness-base/harness-control/hc-onboard)<a href="https://agentmods.dev/skills/harness-base/harness-control/hc-onboard"><img src="https://agentmods.dev/badge/skills/harness-base/harness-control/hc-onboard/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/skills/harness-base/harness-control/hc-onboard"><img src="https://agentmods.dev/badge/skills/harness-base/harness-control/hc-onboard.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 | $0.00294 | $0.04771 |
| Opus 5 | $0.00147 | $0.02386 |
| Sonnet 5 | $0.00059 | $0.00954 |
| Haiku 4.5 | $0.00029 | $0.00477 |
Grade A, and why
hc-onboard 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 9d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
引导式把工程接进 harness（hc-onboard）
本 skill 管"把一个工程按 harness 规范搭好、接进控制面"——新项目：从零起挂进 projects/，配好最小骨架、决策记录、执行口接线（依据 ADR-0017）；老项目：已有代码 + 历史的工程倒着对齐，把项目原有规范 / 老资产扫→确认→搬进 harness 规矩（依据 ADR-0018）。两条岔路过审后都交棒给开发链条（hc-prd → hc-tech-design → hc-dev）。
形态 = 交互式引导（主 agent 当接入向导），同 hc-tech-design 的「引导 → 用户确认 → 派 reviewer 对抗挑刺 → 回改 loop」——一条连贯的接入对话、逐步确认、不可拆并行。
铁律（贯穿全程）：选型 / 结构 / 规矩都是"选择"——摆选项 + 讲取舍让用户拍板，不替用户定、不"看见啥落啥"。接入向导的活是把路铺清楚、把取舍讲明白，拍板权归用户。
本 skill 结构：编排骨架 + 横切规矩（①–⑧）在本文常驻；每步的详细 playbook（问什么 / 确认什么 / 落什么）按分支分档，进对应分支时读——新项目 →
references/new-project.md（7 步细节）、老项目 →references/old-project.md（8 步细节）。③④ 只留步号骨架 + 一句话，步号与 references 一一对应（hc-onboard-reviewer按步号回指，别改号）。
① 何时用 / 何时不用
- 用：把一个工程接进 harness——从零起一个新项目（配项目名 / 栈 / 目标 → 搭最小骨架 → 记第一个决策 ADR → 接执行口 → 过审 → 登记），或接管一个已有代码 + 历史的老工程（拆模块 → 按模块 扫→确认→搬进规范 → 接执行口发现+对齐 → 引入关联进主目录）。用户说「接入项目 / 新建项目 / 挂个工程 / onboard / 起个新工程 / 接入老项目 / 存量项目 / 对齐现有项目」时用。
- 不用：已接工程内写功能 / 改 bug / 重构走
hc-dev；产需求走hc-prd；产研发方案 / 接口设计走hc-tech-design；产测试用例走hc-test；固化一条规则走hc-add-rule；改 harness 本身 / 查 harness 漏洞走hc-self-evolution。 - 一句话边界：
hc-onboard只把工程接进来、搭壳、接线，不搭代码结构、不写实现、不产需求 / 方案 / 用例——那些是接进来之后的下游链条的活（交棒见 ③ 第 7 步 / ④ 第 8 步）。
② 入口分流（先问 新 / 老，两分支都已实现）
接入向导第一句先分流，别急着往下走：
- 先问：这是从零起的新项目，还是已有代码的老工程要挂进来？
- 新项目 → 走 ③ 的 7 步（从零搭最小骨架）——进此分支先读
references/new-project.md。 - 老项目 → 走 ④ 的 8 步（有代码有历史，倒着对齐：把项目原有规范 / 老资产扫 → 确认 → 搬进规范，让"控制面记的 ↔ 项目真实代码"对得上、不漂）——进此分支先读
references/old-project.md。同一个 skill 的第二条岔路：接执行口 / 评审 / 收尾 / 交棒的骨架与新项目共用，但取向不同——别拿新项目 7 步硬套老工程（老工程有存量代码 / 历史结构 / 隐性约定），也别拿老项目判据误伤新项目骨架。
③ 新项目 7 步（骨架；每步详情见 references/new-project.md）
一条连贯的引导对话，主 agent 当接入向导，每步先确认再落、每步守铁律（摆选项 + 讲取舍，用户拍板）。进新项目分支时先读 references/new-project.md 拿到每步「问 / 确认 / 落」的完整 playbook。
- 收基本信息——项目名（kebab、不撞现有工程）/ 目标 / 概述 / 栈；复述确认，先不落文件。
- 搭最小骨架——
projects/<名>/+ 精简AGENTS.md+CLAUDE.mdshim。红线：只搭壳、不搭代码结构 / 分层 / 脚手架（那是 hc-tech-design/hc-dev 的活）。 - 记第一个决策 ADR——把选型 / 结构的决策 / 备选 / 理由跟用户对齐，落项目自己的决策记录（背景→决策→备选+为何排除→影响）。
- 接执行口——verify/unit/api/e2e/sandbox 三字段/routelist 按三态（见 ⑤）逐条与用户确认后占进
workspace/verification.yaml；sandbox 只占位、由hc-create-sandbox单独接实。接线本体归主 agent 串行做。 - 对抗评审——派
hc-onboard-reviewer挑刺骨架，回改到过（判据见 ⑥）。 - 收尾——
make verify绿 + 登记好（按 ④ 第 5 步五项对一遍）；真实证据摆给用户，不假完成（rule-0002/0003）。 - 交棒——指路下游
hc-prd→hc-tech-design→hc-dev；提示用户"第一份需求建议先走hc-prd理清"（提示、非门禁——skill 间松耦合，ADR-0023）。
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 95 lines · 0 tokens per session scan A 48e54407f828
hc-onboard is a skill published in the GitHub repository harness-base/harness-control (22 stars, last pushed 1mo ago), licensed MIT. It adds 294 tokens to every session and 4,771 once invoked, about $0.0015 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.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.