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 lazysheep-z/apdr-product-design-runtime --skill backend-engineergit clone --depth 1 https://github.com/lazysheep-z/apdr-product-design-runtimeWrote 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/lazysheep-z/apdr-product-design-runtime/backend-engineer)<a href="https://agentmods.dev/skills/lazysheep-z/apdr-product-design-runtime/backend-engineer"><img src="https://agentmods.dev/badge/skills/lazysheep-z/apdr-product-design-runtime/backend-engineer/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/lazysheep-z/apdr-product-design-runtime/backend-engineer"><img src="https://agentmods.dev/badge/skills/lazysheep-z/apdr-product-design-runtime/backend-engineer.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 | $0.00049 | $0.00792 |
| Opus 5.5 | $0.00020 | $0.00317 |
| Sonnet 5.5 | $0.00010 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
apdr-backend-engineer 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 27d 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.
What it actually says
Backend Engineer (APDR)
Stage: backend_codegen(可选)。上游:PRD + CodeBundle(前端)。
何时运行
- Intake 已问过用户「是否需要生成后端代码?」
ProjectBrief.includeBackend === true(或meta.includeBackend === true)- 若为
false/ 未设置:引擎在advance_pipeline时自动跳过本阶段 →code_intelligence
External / drop-in skills
| 来源 | 路径 | 说明 |
|---|---|---|
| Superpowers | vendor/superpowers/skills/writing-plans、test-driven-development |
计划 + TDD |
| Addy | vendor/addy-agent-skills/documentation-and-adrs |
API/架构决策 ADR |
| 用户后续提供 | skills/backend-skills/*/SKILL.md |
优先调用;你提供新 skill 后放入此目录即可 |
执行本阶段时:
- 列出
skills/backend-skills/下所有*/SKILL.md - 按 description 匹配当前栈/任务,先读再执行用户 skill
- 若目录为空:用本文件下方「默认实现」完成最小可用后端
Workflow
get_latest_artifact—PRD、CodeBundle、ProjectBrief(确认includeBackend)- 若
includeBackend !== true:告知用户将跳过 →advance_pipeline - 与用户确认栈(默认
node-express或用户 skill 指定) - Invoke writing-plans(或用户 backend skill 的计划步骤)
- 在
projects/{projectId}/server/(或用户 skill 指定路径)实现:- 路由 / handlers 对齐 PRD 功能与前端
CodeBundle.routes所需 API - 数据模型、校验、错误形状
.env.example(不要写入真实密钥)
- 路由 / handlers 对齐 PRD 功能与前端
- TDD:至少覆盖核心 endpoint 的 happy path
write_artifacttypeBackendCodeBundle:
{
"stack": "node-express",
"rootPath": "projects/{projectId}/server",
"apiBasePath": "/api",
"endpoints": [{ "method": "GET", "path": "/api/...", "description": "..." }],
"dataModels": [{ "name": "Entity", "fields": ["id", "..."] }],
"envVars": ["DATABASE_URL", "PORT"],
"notes": "skills used: ..."
}
- 可选 approve → advance →
code_intelligence
默认实现(无用户 skill 时)
- Express + TypeScript 最小脚手架
- 按 PRD
must功能生成 REST stub(可先返回 mock) README.md:启动命令、环境变量说明- 禁止把生产密钥写入仓库
Do not
- 在
includeBackend=false时仍强行写后端 - 跳过
write_artifact BackendCodeBundle - 把 app_secret / 数据库密码写入 artifact 或代码明文
- 替代前端
CodeBundle(两端分开)
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.
- 27d ago First seen · 72 lines · 49 tokens per session scan A 73820079889a
apdr-backend-engineer is a skill published in the GitHub repository lazysheep-z/apdr-product-design-runtime (3 stars, last pushed 3d ago), licensed MIT. It adds 49 tokens to every session and 792 once invoked, about $0.0002 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 2026-09-21.
Other skills, from other repositories
server-side-calls
Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.
django-tdd
Django testing strategies with pytest-django, TDD methodology, factoryboy, mocking, coverage, and testing Django REST Framework APIs.
ring:running-dev-cycle
Running the backend dev cycle: implements every task in a rolling-wave plan.md (ring:writing-plans format) for a Go/TS service, driving specialist agents through Gate 0 implementation/TDD, Gate 8 parallel review, and Gate 9 validation per epic, elaborating later phases at each phase boundary. Use when starting or…
nw-fp-domain-modeling
Domain modeling with algebraic data types, smart constructors, and type-level error handling.
ring:instrumenting-streaming-events
Instrumenting streaming events: wires lib-streaming event emission end-to-end into a Lerian Go service via a 13-gate cycle (catalog, Builder bootstrap, Emit sites, outbox, HTTP manifest, NoopEmitter fallback, integration and chaos tests), dispatching ring:backend-go under TDD. Consumes the validated…
django-tdd
Django testing strategies with pytest-django, TDD methodology, factoryboy, mocking, coverage, and testing Django REST Framework APIs.