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/AGENTS.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/instructions/artisancloud/powerx/agents-md)<a href="https://agentmods.dev/instructions/artisancloud/powerx/agents-md"><img src="https://agentmods.dev/badge/instructions/artisancloud/powerx/agents-md/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/instructions/artisancloud/powerx/agents-md"><img src="https://agentmods.dev/badge/instructions/artisancloud/powerx/agents-md.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 | $0.01380 | $0.01380 |
| Opus 5.5 | $0.00552 | $0.00552 |
| Sonnet 5.5 | $0.00276 | $0.00276 |
| Haiku 4.5 | $0.00138 | $0.00138 |
Grade A, and why
PowerX AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PowerX Agent Governance
Git 分支管理
- 默认在用户当前所在的 Git 分支上进行修改。
- 创建、拆分或切换 Git 分支前,必须先获得用户的明确允许;不得擅自执行。
- 创建独立 worktree、checkout 或使用 detached HEAD 进行开发,同样必须先获得用户的明确允许,不得以隔离任务为由绕过上述规则。
调试服务进程管理
- Agent 可以为开发、联调和验收临时启动服务,启动时必须记录进程 PID、启动命令、工作目录及监听端口,明确进程归属。
- 调试结束后、向用户交付前,必须关闭 Agent 自己启动的服务及其子进程,并确认进程已经退出、相关监听端口已经释放。只有用户明确要求保留运行时,才可以继续运行。
- 日常服务由用户自行启动。需要重新编译或重启时,告知用户具体操作,不得在调试结束后遗留临时服务进程。
- 不得擅自关闭或重启用户启动的进程;清理前必须核实 PID 和进程归属。
Framework delegated Host capability rule
When a Core capability is intentionally consumed by PowerX Framework through a local Host simulation or a delegated Core binding, it MUST declare both authorization planes in the same formal platform capability contract:
- An Admin plane, when an admin surface exists:
admin_user+ user JWT + RBAC. - A service plane: a fixed typed
core_internalbinding withservice_actor. - When local Host simulation supports
PX_GATEWAY_API_KEY, the service binding MUST include explicitapi_keymetadata. Core MUST materialize it into anallow_api_key=true,api_key_explicit=trueIAM permission and evaluate it through published capability + tenant registration + live API-key grant.
Do not use an Admin REST permission as the service grant. Do not grant a broad
admin_manage capability merely for a Framework selector; define a
least-privilege service_read capability. A core_internal capability MUST
use a stable core:// endpoint, method INVOKE, and a typed operation DTO;
it MUST reject arbitrary HTTP method, endpoint, headers, or raw proxy payloads.
Changing this contract is a breaking change: callers using an old free-form
payload must fail explicitly and be migrated to the typed binding. After a
capability change, run make capability-check, make capability-seed, the
affected API-key/grant tests, and verify grant-status for the development
Host API key.
页面设计与产品体验
- 默认禁止将独立功能区、说明、表单和列表以瀑布式长页连续堆叠。多个独立主题默认采用“左侧纵向 TabView 导航 + 右侧当前内容”;已有顶部分类 Tab 时,各分类内部同样必须按任务分区,不能以顶部 Tab 替代内部信息层次。
- 一次只展示当前分区;切换时保留必要上下文、表单和进行中的任务。列表/表格/时间线等同类内容可以自然滚动,但不能借此堆叠不同任务。文章或用户明确要求连续阅读的页面除外。
- 页面设计必须具备产品思维:先明确目标用户、主要任务和查看/操作流程,再组织功能与信息;不得以“所有功能和元素都已放到页面上”作为完成标准。
- 信息呈现必须有层次。优先展示核心信息、关键状态和主要操作,辅助说明、低频操作及详细数据按需展开,避免同等突出地堆叠所有内容。
- 按照用户的查看逻辑组织“概览 → 分块 → 详情”。可以通过明确的按钮打开弹层、抽屉或详情页,让用户逐层查看,并保留当前操作上下文。
- 对具有独立主题的信息或不同任务阶段,可以使用 TabView 分块呈现;标签名称和默认选中项必须符合用户理解与使用频率,核心信息和主要操作应易于发现,避免为完成同一个任务频繁切换 Tab。
- 使用标题、分组、间距和视觉权重表达主次关系。弹层、Tab 和折叠应服务于阅读与操作效率,避免不必要的嵌套和跳转,也不得隐藏完成当前任务所必需的信息。
- 页面验收必须沿实际用户流程检查:能否快速理解当前状态、找到主要操作、按逻辑查看详情并完成任务;同时保证加载、空数据、失败与成功状态有清晰反馈。
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 · +19 lines · +811 tokens per session 835701ba059c
- 9d ago Changed · -62 lines · -3,266 tokens per session 281e2f10d414
- 1mo ago First seen · 102 lines · 3,835 tokens per session scan A 64b1112a33cc
PowerX AGENTS.md is an instructions file published in the GitHub repository ArtisanCloud/PowerX (382 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,380 tokens to every session, about $0.0055 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.