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/capability-governancenpx skills add ArtisanCloud/PowerX --skill capability-governancegit 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/capability-governance)<a href="https://agentmods.dev/skills/artisancloud/powerx/capability-governance"><img src="https://agentmods.dev/badge/skills/artisancloud/powerx/capability-governance.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 | $0.00109 | $0.04538 |
| Opus 5 | $0.00055 | $0.02269 |
| Sonnet 5 | $0.00022 | $0.00908 |
| Haiku 4.5 | $0.00011 | $0.00454 |
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 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 — 320 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:
- 读取本 skill 的“必读文件”。
- 运行
make capability-gen,确保backend/config/platform_capabilities/generated.auto.yaml被重新生成。 - 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_codeagent_usablerisk_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
- 检查手写聚合能力 YAML 是否同样具备
permission_code / agent_usable / risk_level。 - 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。 - 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。
- 修完后重新运行
make capability-gen和make capability-check,直到通过。 - 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。 - 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.mkmake_files/dev.mkbackend/cmd/capability_gen/main.gobackend/cmd/capability_audit/main.gobackend/config/platform_capabilities/*.yamlbackend/config/capability_audit_required.yamlbackend/internal/service/integration_gateway/base_capabilities.gobackend/internal/service/integration_gateway/platform_capability_config.gobackend/internal/http/auth_subject_validator.gobackend/internal/http/auth_subject_validator_test.go- 相关 HTTP/gRPC/OpenAPI transport 源文件。
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.
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 · 320 lines · 109 tokens per session scan A 9700b143e262
capability-governance is a skill published in the GitHub repository ArtisanCloud/PowerX (364 stars, last pushed 3d ago), licensed Apache-2.0. It adds 109 tokens to every session and 4,538 once invoked, about $0.0005 per session on Opus 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
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…