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 skills add cass-2003/local-workflow-skill --skill platform-engineeringgit clone --depth 1 https://github.com/cass-2003/local-workflow-skillWrote 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/cass-2003/local-workflow-skill/platform-engineering)<a href="https://agentmods.dev/skills/cass-2003/local-workflow-skill/platform-engineering"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/platform-engineering/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/cass-2003/local-workflow-skill/platform-engineering"><img src="https://agentmods.dev/badge/skills/cass-2003/local-workflow-skill/platform-engineering.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 | $0.00112 | $0.08901 |
| Opus 5 | $0.00056 | $0.04450 |
| Sonnet 5 | $0.00022 | $0.01780 |
| Haiku 4.5 | $0.00011 | $0.00890 |
Grade A, and why
platform-engineering 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 6d 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
平台工程
首次自称：平台工程（platform-engineering，兼容 slug: plt）。 requires 仅表示条件联动：只有当前任务已经明确需要发布、观测、云原生或相邻能力时，才把相关技能升级为 must；不得把 manifest requires 写成自动必选。
定位：把平台工程从“装门户/堆工具/写模板”拉回平台产品：用户是谁、能力边界是什么、入口如何闭环、执行面是否可追踪、证据能否证明 DevEx 与治理同时改善。 铁律：没有用户旅程、服务目录事实、执行面链路、权限/租户模型、指标基线、支持闭环和迁移/弃用策略，不得宣布 IDP、Golden Path 或 self-service 成熟。
快速总则（用户 / 能力 / 入口 / 证据）
- 用户：先分清应用开发、SRE、平台团队、安全、FinOps、合规、运营、管理者；每类用户的目标、痛点、权限、交互模式和支持路径不同。
- 平台产品：先定义平台消费者、平台提供的产品/能力、非目标和边界；只上线工具或模板仓库不等于平台工程。
- 能力：区分 Portal、Service Catalog、templates、workflow/orchestrator、CI/CD、GitOps、IaC、Kubernetes 平台、policy、observability、FinOps、support；不要把入口当能力。
- 入口：确认 Backstage/Port/Cortex/OpsLevel/自研门户、CLI、API、ChatOps、CI 模板、GitOps PR、云控制台哪一个是主入口，入口后必须能追到执行面。
- 证据：结论绑定 adoption、onboarding time、lead time、change failure rate、MTTR、工单量、满意度、SPACE 信号、scorecard 趋势、catalog drift、成本标签覆盖率。
- 版本：确认 Backstage/插件、scaffolder、catalog schema、CI runner、IaC provider、GitOps controller、K8s、policy engine、身份源版本。
- 环境：确认组织/团队/租户、云账号/project/namespace、RBAC、网络隔离、Secret、制品库、日志索引、成本中心、合规等级。
- 复现：按用户旅程复现创建服务、首次部署、申请资源、发布、观测、扩缩容、故障定位、回滚、清理资源。
- Golden Path：必须覆盖 repo、模板、测试、CI、artifact、deploy、config、secret、observability、SLO、runbook、security、cost、rollback、owner。
- Guardrails：治理落到模板、CI/CD、IaC plan、admission/runtime policy、scorecard、审计和例外到期，不只写文档。
- 平台即产品：必须有 roadmap、用户反馈、支持 SLO、release notes、迁移计划、弃用策略、adoption funnel 和 owner。
- 认知负担：用默认值、分层参数、渐进披露、错误解释、文档同源和支持入口降低复杂度，不能把云/K8s 复杂度换成门户表单复杂度。
- 服务目录真实性：Catalog 必须能被 repo、CI、runtime、APM、云资源和 on-call 证据反查；只靠人工 yaml 或门户表单不算可信。
- 执行面闭环：任何 self-service 按钮、模板或 API 都要能追踪到 workflow run、CI job、GitOps commit、IaC plan/apply、审计日志和最终资源状态。
- 开发者平台门禁：平台能力进入生产默认要过 identity、RBAC、tenant、quota、environment、credential、policy、SLO、cost、audit、rollback、migration 和 support gate。
- 真实交付：不能只证明按钮可点或模板可生成；必须证明服务能创建、部署、观测、告警、回滚、升级、删除，并能被 owner 接手运营。
强制落地流程
- 先定平台产品：目标用户、要卖给内部团队的能力、非目标、成功指标、支持边界和 owner。
- 再读事实：服务目录、仓库、CI/CD、GitOps、IaC、runtime、权限、工单、事故、成本和绕行路径。
- 再画旅程：从创建服务到上线、观测、故障、扩容、回滚、升级、删除，每一步标入口、等待、失败点和证据。
- 再定控制面：Portal/CLI/API 只做入口，真实状态以 workflow/GitOps/IaC/runtime 的单一事实源为准。
- 再定权限链：identity、team、tenant、role、approval、runner token、cloud IAM、K8s RBAC、Secret、artifact、logs 必须一致。
- 再定 guardrails：allow/warn/block/exception、例外 owner、到期、审计、自动修复和用户可理解解释。
- 再定验证：端到端走一条 Golden Path，故意触发权限不足、配额不足、policy fail、runner fail、GitOps fail 和 rollback。
- 再定门禁：生产准入、环境保护、凭证轮换、模板版本、配额、成本预算、SLO、审计、回滚、迁移和弃用必须有可执行 owner。
- 最后定运营：adoption funnel、支持 SLO、office hour、release notes、迁移批次、弃用公告、回滚和复盘节奏。
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.
- 6d ago First seen · 348 lines · 112 tokens per session scan A 4ded0074888b
platform-engineering is a skill published in the GitHub repository cass-2003/local-workflow-skill (12 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 8,901 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
atmos-modernization
Atmos Modernization: migrate deprecated or legacy Atmos patterns to current names, Native CI, Atmos Pro drift detection, dependencies.components, nametemplate, and declared secrets.
production-orchestrator
Use this agent for end-to-end PRD-to-production pipeline execution with zero-tolerance validation, compliance gates, and rollback capability.
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
devloop
Goal-driven development loop — define objective, write rules with key-results, verify visually, sync to issue tracker.
goal
Set and track project goals. Triggered by "/goal" to define objectives, track milestones, or review progress.
atmos-migration
This skill helps you migrate a repository to Atmos. It covers native Terraform, Terraform Workspaces, Terramate, Terragrunt, Makefiles, Justfiles, and Taskfiles. It gives minimum-disruption paths, file-layout options, workspace mapping, task-to-command mapping, generatehcl/script decomposition, and the remote-state…