Borrowing it
Nothing to install: this file belongs to ArtisanCloud/PowerX. 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/ArtisanCloud/PowerX/release/v1.0.0/.codex/skills/sts/SKILL.mdgit clone --depth 1 https://github.com/ArtisanCloud/PowerXWrote 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/artisancloud/powerx/sts)<a href="https://agentmods.dev/skills/artisancloud/powerx/sts"><img src="https://agentmods.dev/badge/skills/artisancloud/powerx/sts/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/artisancloud/powerx/sts"><img src="https://agentmods.dev/badge/skills/artisancloud/powerx/sts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 27 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 32 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 36 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 50 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 77 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00025 | $0.01431 |
| Opus 5.5 | $0.00010 | $0.00572 |
| Sonnet 5.5 | $0.00005 | $0.00286 |
| Haiku 4.5 | $0.00003 | $0.00143 |
Grade A, and why
sts 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 1mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerX STS
步骤
- 打开
本文件内嵌规则。 - 按规则执行实现/校对。
- 完成后按核对清单验收。
核对点
- 与 PowerX 当前代码结构、路径与命名一致。
- 仅在传输层/契约层做职责内改动，不跨层越界。
规则（内嵌）
dev_sts_guides.md
# PowerX STS & 插件对接规范
> 目标：定义插件以**租户维度**访问 PowerX 的鉴权方式（STS 令牌交换）、凭证生成/轮换、令牌使用与安全要求。
> 传输层可为 gRPC/HTTP，拦截器/中间件与 Crypto KeyRing 统一。
## 1. 范围与术语
- STS（Security Token Service）：`Exchange(client_id, client_secret, aud, scope, ttl)` → 短期 JWT。
- 客户端：插件进程（per-tenant）。
- KeyRing：HS256 密钥集合（带 `kid`），STS 与 gRPC 拦截器共用。
## 2. 架构与目录
- STS 服务：`internal/transport/grpc/auth/sts_handler.go`（`Exchange`）
- KeyRing：`internal/transport/grpc/auth/key_ring.go`
- gRPC 拦截器：`internal/transport/grpc/auth/middleware/auth_interceptor.go`
- Proto：`api/grpc/contracts/powerx/auth/sts/v1/sts.proto`（Buf 生成到 `api/grpc/gen/go/...`）
- 插件-宿主关系与访问形态：详见《powerx_agent_plugin.md》。
## 3. 凭证模型（租户维度）
- 启用插件生成：`plugin_instance_configs(tenant_id, plugin_id, key="auth.credentials")`
- 字段：`client_id`（`<pluginID>.<tenantID>`）、`client_secret_hash`（仅存 hash）。
- 明文 `client_secret` 仅创建/轮换时展示一次，插件自行安全保存。
- 轮换：旧 secret 立即失效，插件更新后继续 Exchange。
## 4. 令牌交换（STS Exchange）
- 请求：`client_id`、`client_secret`、`audience=powerx:api`、`scope=access`、`ttl=300（秒）`。
- 返回：`access_token`（HS256，header.kid 写入）、`expires_in`、`aud`、`scope`、`iss`、`sub=client:<client_id>`。
- 验证：STS 验签与 gRPC 拦截器使用**同一 KeyRing**（kid 选择密钥）。
## 5. 令牌使用（插件 → PowerX）
- gRPC：在 metadata 设置 `authorization: Bearer <token>`；拦截器校验通过后带入 `tenant_id/actor` 上下文。
- HTTP（如需）：中间件与 STS 对齐验签策略（issuer/secret/kid）。
- 客户端缓存：仅内存缓存；若剩余寿命 <60s 先刷新；401/403 触发强制刷新再重试一次。
### 5.1 HTTP direct route 边界
- 插件调用底座能力的推荐主路径是 `/api/v1/tenant/invocations`。
- 插件 STS token 直接访问 Core HTTP 时，允许集合由 capability governance 管理：
`static plugin runtime contracts + formal platform_capabilities REST endpoints - STS blocklist`。
- 普通开放 REST 能力必须先进入正式 `backend/config/platform_capabilities/*.yaml` 的 REST protocol；不得通过手工改 STS validator 代替能力登记。
- `/api/v1/admin/*` 是后台用户态 API 命名空间。插件 Admin 页面、PowerX Admin 页面、以及任何携带用户 JWT 的后台请求，仍然由用户鉴权、租户成员、RBAC 和业务权限判定，不受服务态 STS direct blocklist 影响。
- 普通 STS token 是插件服务态身份，不携带 `uid/mid`，不能代表登录用户调用 `/api/v1/admin/*` 绕过用户 RBAC。插件后端如果要代表当前用户调用底座后台 API，必须引入 delegated/on-behalf-of 机制。
- 对服务态 STS direct call，`/admin/*`、`/internal/*`、`/public/*`、`/auth/*`、`/setup/*`、debug、migration、root、drain、bootstrap、mock、health、根级动态路径默认不允许。确认为插件服务运行时合同的少量入口必须进入 static allow 并补测试。
## 6. 安全与审计
- TTL 建议 2–10 分钟；`client_secret` 安全存储；校验 `aud/scope` 最小权限；
- 审计：记录 Exchange/业务调用的 `tenant/plugin/subject/trace_id`；异常 401/403 计数告警。
- 禁止在 `tenant_id=0` 上下文下生成租户凭证。
## 7. 与 Agent/插件关系（何时走 MCP）
- 插件直调 PowerX（gRPC/HTTP）或对外自暴露服务；
- 需要纳入统一“工具目录/市场”时，将插件能力包装为 MCP 工具（详见《powerx_agent_plugin.md》）。
## 8. 验收要点（Checklist）
- [ ] 存在 STS `Exchange` 实现与注册，Proto 契约落在 `powerx/auth/sts/v1`；
- [ ] KeyRing（HS256+`kid`）与拦截器复用，STS 签发的 token 可直接通过业务 RPC 鉴权；
- [ ] 插件凭证落在 `plugin_instance_configs`（仅存 hash），支持“轮换”；
- [ ] 客户端仅内存缓存 token，支持预刷新与 401/403 强制刷新；
- [ ] 审计与安全策略（TTL/aud/scope/告警）到位；
- [ ] 与 HTTP/gRPC 的错误语义一致（Unauthenticated/PermissionDenied）。
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.
- 1mo ago First seen · 83 lines · 25 tokens per session scan A ed92c0e25552
sts is a skill published in the GitHub repository ArtisanCloud/PowerX (382 stars, last pushed 2d ago), licensed Apache-2.0. It adds 25 tokens to every session and 1,431 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
fastapi
FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.
langbot-eba-adapter-dev
Build, refactor, and test LangBot platform adapters for the Event-Based Agents architecture. Use when adding or migrating Telegram, Discord, or other messaging platform adapters to the EBA adapter layout, validating unified event/message conversion, writing live adapter probes, or using standalone plugin runtime plus…
langbot-dev
Develop, build, and debug the LangBot core backend and web frontend. Use when working inside the LangBot repository — backend (Python/Quart, src/langbot/pkg), the Vite/React web UI, HTTP API controllers/services, Alembic migrations, or the MCP server. Covers the dev environment (uv, pnpm), repo layout, the API auth…
wxjava-module-selector
A decision guide for choosing the correct WxJava Maven module, dependency management file, and example for a WeChat use case. WxJava is a Java software development kit for services such as official accounts, mini programs, and payments.
wxjava-api-contributor
A contributor guide for adding or maintaining official WeChat API support in WxJava, a Java software development kit. It covers services, request and response data objects, data conversion, HTTP handling, starter configuration, and regression tests.
wxjava-integration-guide
A setup guide for connecting Java, Spring Boot, or Solon applications to WxJava, a Java software development kit for WeChat services. It covers choosing modules, adding dependencies, configuring accounts, and making an initial API call.