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 it235/multica-best-practices --skill multica-backend-implgit clone --depth 1 https://github.com/it235/multica-best-practicesWrote 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/it235/multica-best-practices/multica-backend-impl)<a href="https://agentmods.dev/skills/it235/multica-best-practices/multica-backend-impl"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-backend-impl/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/it235/multica-best-practices/multica-backend-impl"><img src="https://agentmods.dev/badge/skills/it235/multica-best-practices/multica-backend-impl.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 | $0.00051 | $0.01118 |
| Opus 5 | $0.00026 | $0.00559 |
| Sonnet 5 | $0.00010 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
multica-backend-impl 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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backend Implementation
Purpose
在已批准的技术设计与 Issue 范围内，契约先行 + TDD 完成后端实现。
与
multica-artifact-api-sync分工：backend-impl 管怎么读上游、怎么写代码与测试；artifact-backend 管 API 契约文档规范与 Confluence 落地。
Platform 协作
| Platform skill | 本 skill 用途 |
|---|---|
multica-platform-jira |
读 Issue / AC（经 Issue Hub 或 JIRA URL） |
multica-platform-confluence |
读 PRD / 架构设计（fetch_page.py） |
发布契约走 multica-artifact-api-sync → platform skill；本 skill 不直接写 REST。
开工前：读上游（必做）
| 顺序 | 来源 | 方式 |
|---|---|---|
| 1 | Issue / 验收标准 | multica-platform-jira → get-issue；含 linked_issues |
| 2 | 关联 JIRA（Relates/依赖等） | get_issue.py --with-linked → 必读关联的 Confluence/Figma（见 upstream-read.md） |
| 3 | PRD / 需求正文 | JIRA 解析 Confluence → fetch_page.py |
| 4 | 架构设计 | Leader 派活链接或 JIRA 描述中的设计链接 → fetch_page.py |
| 5 | 现有代码 | codegraph / 局部阅读，遵循项目约定 |
信息不足 → BLOCKED，写入待确认项，不猜接口形状。
G2 前：单元测试（硬门禁）
merge 到 deploy branch 之前，必须在本地（或项目标准 dev 容器）跑通 全部 单元测试：
1. 跑项目约定的 unit test 命令（如 mvn test / npm test / pytest tests/unit）
2. 必须 0 failure；既有测试不得因本次改动失败（无退步）
3. 新增/变更 API 须有对应单元测试（Red-Green-Refactor）
4. 失败 → 自行修复后再跑，直至全绿
5. 仅当本地无法跑（缺依赖/缺硬件）→ BLOCKED 列环境缺口，不得 push 后「等 CI 再看」
禁止：把单元测试失败留给 Jenkins/CICD 才发现；禁止为通过而删除或 skip 既有测试（除非 Architect/Leader 书面砍 scope）。
CI 是 二次确认，不是第一次跑单测的地方。
TDD 流程（核心）
1. 读 AC- / 架构「实现步骤（后端）」→ 列出 API-ID 与行为
2. 写/更新 api-contract.md（交 multica-artifact-api-sync 发布，供前端并行）
3. Red — 写失败单元测试（业务逻辑、边界、异常）
4. Green — 最小实现使测试通过
5. Refactor — 保持测试绿，不扩 scope
6. 集成验证 — 跑项目约定命令，贴证据
规则：
- 业务逻辑须有单元测试；纯 CRUD 也需覆盖异常分支与边界。
- 先改契约文档再改实现；Breaking change 须升版本并知会 Leader / @FrontendDev。
- 不静默改字段名/语义；与 Architect 设计偏离须说明。
编码规则
- 先读再改；遵循现有分层与命名。
- 范围聚焦；不无关重构。
- 错误处理：超时、幂等、并发按设计实现。
- 报告可复跑的命令与结果。
完成证据
- API 契约 Confluence 链接（
multica-artifact-api-sync） - 变更文件列表
- 单元测试：命令 + 全绿结果（merge deploy branch 前已跑通；0 failure、无测试退步）
- 集成测试（若项目要求）命令 + 结果
- 与 API-ID / AC- 的追溯说明
- 已知限制
挂载顺序（@BackendDev）
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.
- 2d ago First seen · 93 lines · 51 tokens per session scan A 753a2dd6eb78
multica-backend-impl is a skill published in the GitHub repository it235/multica-best-practices (108 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 1,118 once invoked, about $0.0003 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 2026-09-07.
Other skills, from other repositories
backend-testing
Write comprehensive backend tests including unit tests, integration tests, and API tests. Use when testing REST APIs, database operations, authentication flows, or business logic. Handles Jest, Pytest, Mocha, testing strategies, mocking, and test coverage.
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.
convex-test
Generate convex-test tests for the app's Convex functions.
composing-matchers
Build compound Gomega assertions by combining matchers — And/SatisfyAll (all pass), Or/SatisfyAny (any pass), Not (negate), WithTransform to map the actual before matching, Satisfy for an ad-hoc predicate, HaveValue to dereference pointers/interfaces, HaveField for struct fields and method results, HaveEach for every…
platform-apex-test-generate
Generate and validate Apex test classes with TestDataFactory patterns, bulk testing (251+ records), mocking strategies, assertion best practices, and disciplined test-fix loops. Use this skill when creating new Apex test classes, improving test coverage, debugging and fixing failing Apex tests, running test execution…
nw-fp-hexagonal-architecture
Hexagonal architecture patterns with pure core and side-effect shell for functional codebases.