PowerX: Skill for Codex

.codex/skills/governance/capability-governance/SKILL.md

capability-governance is a skill for Codex from ArtisanCloud/PowerX. It costs 109 tokens per session (4,810 once invoked), scanned A, original, Apache-2.0.

A governance and release-checking tool for capabilities exposed by the PowerX platform. It examines API-based functions and their permissions, risk labels, agent availability, and registration records before they are published.

In plain words
What is it for?
Use it to audit or complete capability registrations, check generated and hand-written capability files, and verify that build and capability checks pass.
Why use it?
It helps prevent incomplete, duplicate, or overly accessible functions from entering the platform's capability catalogue. It distinguishes real implementations from declarations that only exist in configuration files.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

This is ArtisanCloud/PowerX's own configuration. It tells Codex how to work on PowerX itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything PowerX configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is cd backend && go test ./cmd/capability_audit.

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/ArtisanCloud/PowerX/release/v1.0.0/.codex/skills/governance/capability-governance/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ArtisanCloud/PowerX

Made for: Codex.

Wrote 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.

agentmods badge for capability-governance

README.md
[![agentmods](https://agentmods.dev/badge/skills/artisancloud/powerx/capability-governance/github.svg)](https://agentmods.dev/skills/artisancloud/powerx/capability-governance)
Your own site
<a href="https://agentmods.dev/skills/artisancloud/powerx/capability-governance"><img src="https://agentmods.dev/badge/skills/artisancloud/powerx/capability-governance/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.

agentmods 80×15 button for capability-governance

Your own site · 80×15
<a href="https://agentmods.dev/skills/artisancloud/powerx/capability-governance"><img src="https://agentmods.dev/badge/skills/artisancloud/powerx/capability-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,810 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, 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 Rogue Agent · line 174
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.04810
Opus 5.5 $0.00044 $0.01924
Sonnet 5.5 $0.00022 $0.00962
Haiku 4.5 $0.00011 $0.00481

Measured 9d ago against content hash e477d155f665, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

capability-governance 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 9d 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.

.codex/skills/governance/capability-governance/SKILL.md · 338 lines

How it starts

The opening of the file, as written. The whole thing — 338 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PowerX Capability Governance

目标

按统一规则判断 PowerX 底座能力候选是否可以进入 backend/config/platform_capabilities/*.yaml,并区分:

  • 可发布为租户能力目录中的正式能力。
  • 可登记但不能作为 agent 可选能力。
  • 已由手写业务聚合能力覆盖,不应重复发布 raw route。
  • 不应发布,只能进入带原因的 ignore。
  • 缺真实实现,不能靠 YAML 声明补齐。
  • 生成器或审计器误判,需要修工具。

正式 YAML 不是文档。进入 backend/config/platform_capabilities 后会被 BaseCapabilitySeeder 写入 CapabilityRecord 并给 active tenants 建 registration,因此必须按运行时授权事实处理。

使用方式

在对话里直接点名 skill。完整审计使用:

用 $capability-governance 做一次完整能力治理审计

完整补齐使用:

用 $capability-governance 做一次完整能力治理补齐

执行“完整能力治理补齐”时,不只解释结果,必须按下面顺序实际处理:

  1. 读取本 skill 的“必读文件”。
  2. 运行 make capability-gen,确保 backend/config/platform_capabilities/generated.auto.yaml 被重新生成。
  3. 检查 generated.auto.yaml 是否作为正式 platform capability 文件存在,并包含所有生成能力的治理字段:
    • permission_code
    • agent_usable
    • risk_level
    • REST binding 的 actor_context
    • REST binding 的 resource_scope
    • sts_direct 只能显式为 true,不得默认打开
  4. 检查手写聚合能力 YAML 是否同样具备 permission_code / agent_usable / risk_level。
  5. 如果审计插件 capability descriptor,检查面向普通成员的能力是否显式声明 default_role_grants: [role_user],并确认未使用非法默认角色码。
  6. 运行 make capability-check。如果失败,先判断是:
    • 缺真实 transport/service:先补实现,再补 YAML。
    • capability_gen/audit 误判:先修工具,例如 Gin Group("") 丢父路径。
    • 正式能力缺元数据:补 YAML 或生成器。
    • 路由不应发布:写入带 category/reason 的 ignore,不允许静默忽略。
  7. 修完后重新运行 make capability-gen 和 make capability-check,直到通过。
  8. 需要验证运行时 Registry 时,运行 make capability-seed,把正式 platform_capabilities/*.yaml 写入 capability_registry_records 并为 active tenants 补齐 registrations。
  9. 如果改了 Go 工具或 STS 规则,运行对应 Go 测试。

也可以按问题缩小范围:

用 $capability-governance 检查 make capability-check 的失败原因
用 $capability-governance 判断这些候选能力哪些可以进 platform_capabilities
用 $capability-governance 分析 com.corex.customer.accounts.* 需要补哪些实现

必读文件

先读取这些位置,再给结论或改代码:

  • make_files/capability.mk
  • make_files/dev.mk
  • backend/cmd/capability_gen/main.go
  • backend/cmd/capability_audit/main.go
  • backend/config/platform_capabilities/*.yaml
  • backend/config/capability_audit_required.yaml
  • backend/internal/service/integration_gateway/base_capabilities.go
  • backend/internal/service/integration_gateway/platform_capability_config.go
  • backend/internal/http/auth_subject_validator.go
  • backend/internal/http/auth_subject_validator_test.go
  • 相关 HTTP/gRPC/OpenAPI transport 源文件。

Read the full file on GitHub · 338 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 9d ago Changed · +18 lines e477d155f665
  2. 1mo ago First seen · 320 lines · 109 tokens per session scan A 9700b143e262

Subscribe to this mod's changes

capability-governance is a skill published in the GitHub repository ArtisanCloud/PowerX (382 stars, last pushed 2d ago), licensed Apache-2.0. It adds 109 tokens to every session and 4,810 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

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.

binarywang/WxJava · 68 tokens

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…

langbot-app/LangBot · 104 tokens

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.…

koxudaxi/datamodel-code-generator · 147 tokens

implementing-api-schema-validation-security

Implement API schema validation using OpenAPI specifications and JSON Schema to enforce input/output contracts and prevent injection, data exposure, and mass assignment attacks.

xalgorix/xalgorix · 35 tokens

performing-api-fuzzing-with-restler

Uses Microsoft RESTler to perform stateful REST API fuzzing by automatically generating and executing test sequences that exercise API endpoints, discover producer-consumer dependencies between requests, and find security and reliability bugs. The tester compiles an OpenAPI specification into a RESTler fuzzing…

xalgorix/xalgorix · 123 tokens

om-system-extension

Extend installed Open Mercato modules through UMES enrichers, interceptors, mutation guards, widgets, menus, entity extensions, events, component/page replacements, and overrides. Use for "extend core", "add field/column/action", "hide page", "intercept API", "UMES", or "rozszerz moduł".

open-mercato/open-mercato · 73 tokens