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/artisancloud/powerx/feature-guidenpx skills add ArtisanCloud/PowerX --skill feature-guidegit 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/feature-guide)<a href="https://agentmods.dev/skills/artisancloud/powerx/feature-guide"><img src="https://agentmods.dev/badge/skills/artisancloud/powerx/feature-guide.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 | $0.00062 | $0.01805 |
| Opus 5 | $0.00031 | $0.00903 |
| Sonnet 5 | $0.00012 | $0.00361 |
| Haiku 4.5 | $0.00006 | $0.00180 |
Grade A, and why
feature-guide scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- 1 个接口调用示例(curl + 响应片段) How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerX 功能使用指导文档技能(Feature Guide)
适用场景
当你需要为 PowerX 平台能力编写“可直接执行、跨角色可协作”的功能文档时使用本技能。典型场景:
- 新功能上线,需要给研发/QA/运维/项目负责人一份可照着操作的手册。
- 功能已经实现,但现有文档偏实现细节,缺少端到端操作链路。
- 需要把“Web Admin 页面 + Admin/Tenant API + 后端实现 + 观测指标”串成闭环。
目标
输出一份可执行 + 可验收 + 可追溯的 PowerX 文档,满足:
- 先讲清“为什么做”(业务背景/痛点/目标)。
- 再讲清“谁在什么环境下怎么用”(角色、范围、限制)。
- 给出“从 0 到跑通”的操作步骤(页面、接口、命令、预期结果、失败处理)。
- 关键行为可追溯到代码实现(路由/handler/service/config/test)。
- 包含流程图与泳道图,帮助跨角色理解协作与边界。
必须遵守的文档结构(强制)
最终文档必须按以下顺序组织章节:
- 功能背景与目标
- 角色与适用范围(谁看、在哪个环境用)
- 整体架构与模块关系(含模块关系图)
- 核心流程(含流程图)
- 跨角色协作流程(含泳道图)
- 前置条件与依赖(配置、权限、数据、Feature Flag)
- 操作步骤(按场景拆分)
- 页面操作步骤(Web Admin)
- 接口调用步骤(Admin/Tenant API)
- 本地联调步骤(backend/web-admin/脚本)
- 预期结果与验收标准
- 代码实现映射(路由/服务/配置/测试)
- 常见问题与排障
- 回滚与风险控制
- 变更记录(版本、日期、责任人)
图示规范(强制)
1) 流程图(必须)
- 使用 Mermaid
flowchart LR或flowchart TD - 必须包含“输入/处理/输出/失败分支”
- 至少体现 1 条失败分支与回退路径
2) 泳道图(必须)
- 使用 Mermaid
flowchart LR+subgraph模拟泳道 - 至少 3 条泳道(示例:Web Admin、PowerX Backend、External System)
- 必须标明跨泳道调用方向与返回结果
写作风格规范(强制)
- 先结论后细节。
- 每个步骤必须包含:
- 动作(做什么)
- 入口/命令(在哪做)
- 预期结果(看到什么算成功)
- 失败处理(失败后看哪里)
- 面向使用者写作,不假设读者了解全部实现细节。
- 禁止脱离实现:文档关键行为都必须能在代码中定位。
PowerX 代码对齐检查清单(发布前必过)
- 文档中的路由前缀与实际一致(如
/api/v1/admin、/api/v1/tenant)。 - 配置项名称、默认值与优先级说明一致(
.env/配置文件/运行时覆盖)。 - 页面入口与按钮文案与当前 Web Admin UI 一致。
- 接口请求/响应示例与 DTO/handler 行为一致。
- 文档提到的 feature flag / 权限 / 开关在当前分支真实存在。
- 至少 1 条测试或脚本命令可验证主链路。
- 观测项(日志字段、指标名、trace_id)可在运行环境检索。
执行步骤(建议流程)
-
收集上下文
- 读取
specs/<feature-id>/spec.md|plan.md|tasks.md|quickstart.md(如存在) - 读取后端路由注册、关键 handler/service、配置结构、测试用例
- 读取 Web Admin 页面入口与交互流程(如涉及前端)
- 读取
-
梳理功能地图
- 功能入口:页面/API/命令
- 核心链路:handler -> service -> repository/integration
- 输出与观测:日志、指标、事件、trace
-
先画图再写步骤
- 先产出模块关系图、主流程图、泳道图
- 再填操作步骤,确保步骤连续可执行
-
补齐验收与排障
- 每个场景定义“成功判定”
- 列出常见失败场景与定位命令
-
做代码映射表
- 每个关键文档步骤至少映射一个代码路径
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.
- today First seen · 152 lines · 62 tokens per session scan A e2a25396e830
feature-guide is a skill published in the GitHub repository ArtisanCloud/PowerX (364 stars, last pushed 3d ago), licensed Apache-2.0. It adds 62 tokens to every session and 1,805 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
scalar-docs
Skill for writing and updating scalar.config.json — Scalar Docs configuration reference for users and LLMs.
openapi-glossary
Use consistent OpenAPI terminology and definitions when writing documentation, educational material, and tooling guidance.
wxjava-api-contributor
按 WxJava 的 Maven 多模块、Java 8、公共 API 兼容性和 TestNG 约定,为微信官方接口新增或维护 SDK 支持。适用于新增 Service API、请求响应 Bean、序列化、HTTP 实现、Starter 配置或回归测试时。.
datamodel-code-generator
Use this skill when the user wants Python data models, Pydantic models, dataclasses, TypedDicts, msgspec structs, or type-safe Python classes generated from OpenAPI, AsyncAPI, JSON Schema, GraphQL, JSON/YAML/CSV sample data, MCP tool schemas, Protocol Buffers, XML Schema, Apache Avro, or existing Python model objects.…
langbot-deploy
Deploy and configure a LangBot instance — Docker / Docker Compose, Kubernetes, the config.yaml model, the Box sandbox runtime, the plugin runtime, and the global API key. Use when installing, deploying, upgrading, or configuring LangBot in production or self-hosted environments. Triggers on "deploy langbot", "langbot…
om-auto-sec-report-pr
Paranoid OWASP-oriented security analysis for a SINGLE unit of work — one PR, one spec under .ai/specs/, or one branch diff. Hunts non-obvious attack vectors beyond OWASP Top 10, flags same-pattern hotspots elsewhere, and emits "Next steps — go deeper" follow-ups. Writes markdown + HTML under .ai/analysis/; runs…