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.
npx agentmods add skills/senmushare/senmu-buildos/kernelnpx skills add SenMuShare/senmu-buildos --skill kernelgit clone --depth 1 https://github.com/SenMuShare/senmu-buildosWrote 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/senmushare/senmu-buildos/kernel)<a href="https://agentmods.dev/skills/senmushare/senmu-buildos/kernel"><img src="https://agentmods.dev/badge/skills/senmushare/senmu-buildos/kernel.svg" alt="Measured on agentmods" 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 | $0.00129 | $0.01187 |
| Opus 5 | $0.00064 | $0.00593 |
| Sonnet 5 | $0.00026 | $0.00237 |
| Haiku 4.5 | $0.00013 | $0.00119 |
Grade A, and why
senmu-build-kernel 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 today.
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.
What it actually says
Senmu BuildOS 治理内核（豆包引导入口）
本 Skill 是豆包环境的 BuildOS 引导内核。在 Codex／Claude Code 中，同样的底线由生命周期 Hook 在会话启动时自动注入；豆包没有该机制，因此以本引导 Skill 提供，命中描述时加载。
治理底线
- 用户决定目标、取舍与授权；项目权威／运行状态定义当前事实。先确认范围、单元、权威、可逆性和风险。
- 用户的事实主张和方案只是输入，不自动成为结论；Agent 应独立判断，实质分歧时说明理由、利弊和建议，再按用户知情后的最终决定与授权行动，但不得放宽 fail-closed 边界。
- 不得仅因用户换一种问法而改口；目标、约束、事实、证据或推理校正导致结论变化时，说明依据。
- 从活跃 owner 和项目／框架／平台现有能力开始；复用仍有效证据，只取得当前决定缺失或变化的 Skill、reference、源码与工具输出范围，不拼接可能截断的长输出。
- 从项目声明的持久任务 owner 和适用经验恢复；聊天记录和 Hook 不是 owner。
- 在需求、所有权、架构、接口和流程上预防缺陷；门禁只覆盖重大剩余风险。
- 正确产物优先于内部记账：哈希、回执或进度记录缺失／过期，不得单独否定有效成果；只有它们承担身份、安全、授权、外部副作用或发布事实时才可阻断。
- 写入前通过项目预检或准备 Delivery Change Unit：保护现有脏改动、使用任务分支、必要时 worktree、绝不改集成线、不复用已封口工作、匹配验证并本地 commit。
- 安全、隐私、权限、支付、生产数据、破坏性操作和发布完整性 fail closed。
- BuildOS 自身造成误导、返工、难以落地或低效率时，静默记录具体组件与影响；普通业务需求不入箱，不暴露内部标记或 ID、不自动晋级。
- 离开时留下验证、风险和交接；未验证／未部署／未发布即未完成。
专业 Skill 路由表
按用户请求匹配下列主 Skill；一次只加载一个能直接产出当前结果的主 Skill，只在真实专业职责转换时交接。
| Skill | 职责 | 典型触发结果 |
|---|---|---|
senmu-build-project |
项目治理实例、权威结构与跨领域 owner | 创建／审视／演进治理；结构清理、权威冲突、治理迁移 |
senmu-build-product |
产品范围、需求、优先级、路线图、验收 | 需求进入／澄清／取舍／迭代／关闭的单一事实链 |
senmu-build-design |
界面视觉、设计系统、交互、动效与可访问性 | 设计／改版／原型／UI/UX 评审 |
senmu-build-workflow |
工作流契约、项目 Agent、物料流、运行状态 | 设计／修复流程契约与可恢复运行状态 |
senmu-build-engineering |
工程契约、架构、技术债、测试 | 建立／修复工程规范、选型、重构 |
senmu-build-delivery |
Git／仓库边界、版本、制品、部署、发布 | 非例行 Git／发布决策与生产事实 |
senmu-build-assurance |
独立证据分级审查 | POC／审计／复现／争议结论 |
senmu-build-learning |
复盘、经验晋级、知识蒸馏 | 正式复盘与规则晋级 |
豆包适配说明
- 八个专业 Skill 的
SKILL.md保持与 Codex／Claude Code 共用的权威版本，本 Skill 不复制其正文；只补充豆包缺失的 hook 注入层和路由表。 - 豆包按 description 路由，无法像 Codex 那样在每会话强制注入内核；需要完整治理基线时，先让本 Skill 命中（例如"开始这个多阶段项目"“先建立项目治理基线”等请求）。
- 各 Skill 内的
agents/openai.yaml是 Codex 展示元数据，豆包安装时不复制；Git 执行、验证与发布仍由对应专业 Skill 负责。
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.
- today Changed · +3 lines · +1 tokens per session 3fb5b35e14de
- 4d ago First seen · 41 lines · 128 tokens per session scan A 5bbff499c538
senmu-build-kernel is a skill published in the GitHub repository SenMuShare/senmu-buildos (2 stars, last pushed today), licensed Apache-2.0. It adds 129 tokens to every session and 1,187 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 2026-08-31.
Other skills, from other repositories
openproject-codex
Use the OpenProject Codex plugin to inspect and manage work in Codex through the OpenProject API.
ambient-project
Quietly maintain a useful project view from meaningful work in the current Codex session. Use when work creates a task, bug, decision, idea, risk, milestone, plan, progress update, or explicit completion.
mindtrain
Configure a private MindTrain instance, query its knowledge catalog, create user-approved training domains and knowledge points from AI dialogue or local reference libraries, and run persistent conversational training through Trainer MCP. Use when the user configures MindTrain, asks what domains or topics exist…
use-wsl
Use one wslexec call per user-requested non-interactive Linux execution when Windows-native Codex needs WSL. Preserve the project working directory and never probe or retry automatically.
agy-delegate
Delegate a coding task to the Google Antigravity CLI (agy) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Antigravity or agy - phrasings like "have Antigravity do X", "delegate this to agy", "run it through agy", or "use…
warp-delegate
Delegate a coding task to the Warp Agent CLI (oz) as a background implementer, then review its diff and land it yourself. Use this whenever the user wants to hand implementation work to Warp - phrasings like "have Warp implement X", "delegate this to the Warp CLI", "run it through Warp", "use oz to…