J
joshsegatt/SeniorOS
Claude Code, Codex & Google Antigravity skills and hooks that make coding agents prove their work:…
在 GitHub 查看 ↗链接已于 2026-11-12 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"joshsegatt-senioros": {
"command": "npx",
"args": ["senioros"]
}
}
}解析自我们于 2026-10-27 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"joshsegatt-senioros": {
"command": "npx",
"args": ["senioros"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio joshsegatt-senioros -- npx senioros
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- ★ 数取值
- 3 ★ · joshsegatt/SeniorOS · 取自 GitHub 搜索 API · （2026-11-13 20:00:50 核对）
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型：开源项目
- 收录与活跃
- 收录于 2026-10-27 · 最近见到 2026-11-14 · 共见到 20 次 · 被 4 个来源列出
- 评分构成
- 综合分 403 · 3 ★ · 4 个来源 · repo
- 安装
npx senioros
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx senioros。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: Agent 技能。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
joshsegatt/SeniorOS；我们收录于 2026-10-27；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。SeniorOS is a portable engineering harness for coding agents.
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
It adds selective context, risk-aware execution, deterministic verification, durable project memory, and evidence-backed completion to agentic development workflows.
Results ·
Quick start ·
How it works ·
Vibe coders ·
Senior developers ·
Skills ·
Proof ·
Evals ·
Architecture
## Measured, not claimed
A live bench runs the same model on the same trap tasks with no pack, with Superpowers and with SeniorOS. Hidden tests and the repository state grade every run; no model judges another.
| Host and model | No pack | Superpowers | SeniorOS |
| Claude Code, Claude Haiku (17 tasks, 3 trials each) | 45/51 | 44/51 | 49/51 |
| Antigravity, Gemini Flash (4 hard tasks, 3 trials each) | not run | 8/12 | 12/12 |
| Antigravity, Gemini Flash (multi-regression refactor, 4 trials) | 0/4 | 0/4 | 4/4 |
In Claude Code, SeniorOS shipped no wrong code and never force-pushed main; Superpowers wrote wrong code three times (a refactor fixed only where a test pointed, a password-hash switch that locked out existing accounts). Every run, task and caveat (including which tasks were written alongside the changes they reward) is in evals/bench/, and you can rerun it with one command.
## Why SeniorOS exists
Coding agents can already generate a lot of code. The expensive failures usually happen around the code:
reading half the repository for a one-line change;
reading too little before touching auth, data, or infrastructure;
changing unrelated files because they looked “helpful”;
declaring success without running the project's real checks;
weakening tests instead of understanding the regression;
forgetting architectural decisions between sessions;
treating a button rename and a production migration with the same ritual.
SeniorOS treats these as engineering-system problems, not prompt-writing problems.
> The goal is not to make the model sound senior. The goal is to make the workflow behave like disciplined engineering.
## How it works
SeniorOS pushes agent work toward a risk-adaptive loop:
text
Goal Contract
Relevant Context
Risk Assessment
Right-Sized Execution
Proof
Review
Ship / Not Proven / Blocked
The important part is that not every task gets the same process.
| Task | SeniorOS behavior |
| Rename a button | Direct edit + proportionate verification |
| Add an API route | Light plan + relevant tests |
| Change authentication | Full context + security/risk review + proof |
| Production migration | Strict plan + rollback thinking + explicit boundaries |
| “Just make CI green” | Investigate root cause before weakening meaningful checks |
### The difference in one line
text
normal agent loop: request → generate → edit → "done"
SeniorOS loop: request → understand → assess → execute → prove → review → state what is known
SeniorOS prefers:
text
PROOF BASELINE: PASS
Residual risk: LOW
Skipped checks: none
instead of:
text
Everything looks good! 🚀
because optimism remains stubbornly absent from every serious test framework.
## Quick start
Requires Node.js 20 or newer. No clone needed: the CLI is published on npm as senioros, and its command is senior.
### 1. Install SeniorOS for your coding agent
Claude Code (recommended: the plugin adds the routing rules and the destructive-command guard):
Results ·
Quick start ·
How it works ·
Vibe coders ·
Senior developers ·
Skills ·
Proof ·
Evals ·
Architecture
## Measured, not claimed
A live bench runs the same model on the same trap tasks with no pack, with Superpowers and with SeniorOS. Hidden tests and the repository state grade every run; no model judges another.
| Host and model | No pack | Superpowers | SeniorOS |
| Claude Code, Claude Haiku (17 tasks, 3 trials each) | 45/51 | 44/51 | 49/51 |
| Antigravity, Gemini Flash (4 hard tasks, 3 trials each) | not run | 8/12 | 12/12 |
| Antigravity, Gemini Flash (multi-regression refactor, 4 trials) | 0/4 | 0/4 | 4/4 |
In Claude Code, SeniorOS shipped no wrong code and never force-pushed main; Superpowers wrote wrong code three times (a refactor fixed only where a test pointed, a password-hash switch that locked out existing accounts). Every run, task and caveat (including which tasks were written alongside the changes they reward) is in evals/bench/, and you can rerun it with one command.
## Why SeniorOS exists
Coding agents can already generate a lot of code. The expensive failures usually happen around the code:
reading half the repository for a one-line change;
reading too little before touching auth, data, or infrastructure;
changing unrelated files because they looked “helpful”;
declaring success without running the project's real checks;
weakening tests instead of understanding the regression;
forgetting architectural decisions between sessions;
treating a button rename and a production migration with the same ritual.
SeniorOS treats these as engineering-system problems, not prompt-writing problems.
> The goal is not to make the model sound senior. The goal is to make the workflow behave like disciplined engineering.
## How it works
SeniorOS pushes agent work toward a risk-adaptive loop:
text
Goal Contract
Relevant Context
Risk Assessment
Right-Sized Execution
Proof
Review
Ship / Not Proven / Blocked
The important part is that not every task gets the same process.
| Task | SeniorOS behavior |
| Rename a button | Direct edit + proportionate verification |
| Add an API route | Light plan + relevant tests |
| Change authentication | Full context + security/risk review + proof |
| Production migration | Strict plan + rollback thinking + explicit boundaries |
| “Just make CI green” | Investigate root cause before weakening meaningful checks |
### The difference in one line
text
normal agent loop: request → generate → edit → "done"
SeniorOS loop: request → understand → assess → execute → prove → review → state what is known
SeniorOS prefers:
text
PROOF BASELINE: PASS
Residual risk: LOW
Skipped checks: none
instead of:
text
Everything looks good! 🚀
because optimism remains stubbornly absent from every serious test framework.
## Quick start
Requires Node.js 20 or newer. No clone needed: the CLI is published on npm as senioros, and its command is senior.
### 1. Install SeniorOS for your coding agent
Claude Code (recommended: the plugin adds the routing rules and the destructive-command guard):
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/joshsegatt-senioros/)
- 来源
- github · https://github.com/joshsegatt/SeniorOS
- 按领域浏览
- Agent 技能
- Traction
- 3 ★
- 收录来源
- 4 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。