workflow-implement-backend

A workflow for building backend APIs, application rules, and database access. It covers database models and migrations, input checks with Zod, and type-safe API routes with tRPC.

In plain words
What is it for?
Use it to add backend features such as database tables, validated create and update requests, migrations, and tRPC API procedures.
Why use it?
It gives backend work a defined order and helps keep stored data and incoming requests valid. It also reduces mismatches between API inputs and the code that handles them.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/rcdelacruz/claude-code-agents/workflow-implement-backend
Clone the repo
git clone --depth 1 https://github.com/rcdelacruz/claude-code-agents

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,012 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00010 $0.02012
Opus 5 $0.00005 $0.01006
Sonnet 5 $0.00002 $0.00402
Haiku 4.5 $0.00001 $0.00201

Measured yesterday against content hash 93997f2ca45e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-implement-backend 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 yesterday.

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.

.claude/commands/workflow-implement-backend.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.

You are in BACKEND IMPLEMENTATION MODE.

Use backend-api agent to build type-safe, secure backend services.

Implementation Workflow

1. Database Schema (10 mins)

Use database agent first:

// Define models, relations, indexes
model Post {
  id        String   @id @default(cuid())
  title     String
  content   String   @db.Text
  authorId  String
  author    User     @relation(fields: [authorId], references: [id])

  @@index([authorId])
}

Run migration:

npx prisma migrate dev --name add_posts
npx prisma generate

2. Input Validation Schemas (5 mins)

Define Zod schemas for type-safe validation:

// lib/validations/post.ts
import { z } from 'zod'

export const createPostSchema = z.object({
  title: z.string().min(1).max(255),
  content: z.string().min(1),
  published: z.boolean().default(false),
})

export const updatePostSchema = createPostSchema.partial()

export type CreatePostInput = z.infer<typeof createPostSchema>
export type UpdatePostInput = z.infer<typeof updatePostSchema>

3. tRPC Router (20-30 mins)

Build type-safe API with tRPC:

// server/routers/post.ts
import { router, publicProcedure, protectedProcedure } from '../trpc'
import { createPostSchema, updatePostSchema } from '@/lib/validations/post'

export const postRouter = router({
  // Public queries
  list: publicProcedure
    .input(z.object({
      limit: z.number().min(1).max(100).default(10),
      cursor: z.string().optional(),
      published: z.boolean().optional(),
    }))
    .query(async ({ ctx, input }) => {
      const posts = await ctx.db.post.findMany({
        take: input.limit + 1,
        cursor: input.cursor ? { id: input.cursor } : undefined,
        where: { published: input.published },
        orderBy: { createdAt: 'desc' },
        include: { author: { select: { name: true, image: true } } },
      })

      let nextCursor: string | undefined
      if (posts.length > input.limit) {
        const nextItem = posts.pop()
        nextCursor = nextItem!.id
      }

      return { posts, nextCursor }
    }),

  // Protected mutations
  create: protectedProcedure
    .input(createPostSchema)
    .mutation(async ({ ctx, input }) => {
      return await ctx.db.post.create({
        data: {
          ...input,
          authorId: ctx.session.user.id,
        },
      })
    }),

  update: protectedProcedure
    .input(z.object({
      id: z.string(),
      data: updatePostSchema,
    }))
    .mutation(async ({ ctx, input }) => {
      // Check ownership
      const post = await ctx.db.post.findUnique({
        where: { id: input.id },
        select: { authorId: true },
      })

      if (!post) {
        throw new TRPCError({ code: 'NOT_FOUND' })
      }

      if (post.authorId !== ctx.session.user.id) {
        throw new TRPCError({ code: 'FORBIDDEN' })
      }

      return await ctx.db.post.update({
        where: { id: input.id },
        data: input.data,
      })
    }),

  delete: protectedProcedure
    .input(z.string())
    .mutation(async ({ ctx, input }) => {
      // Check ownership
      const post = await ctx.db.post.findUnique({
        where: { id: input },
        select: { authorId: true },
      })

      if (!post) {
        throw new TRPCError({ code: 'NOT_FOUND' })
      }

      if (post.authorId !== ctx.session.user.id) {
        throw new TRPCError({ code: 'FORBIDDEN' })
      }

      return await ctx.db.post.delete({ where: { id: input } })
    }),
})

Read the full file on GitHub · 338 lines

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. yesterday First seen · 338 lines · 10 tokens per session scan A 93997f2ca45e

Subscribe to this mod's changes

workflow-implement-backend is a command published in the GitHub repository rcdelacruz/claude-code-agents (2 stars, last pushed 10mo ago), licensed MIT. It adds 10 tokens to every session and 2,012 once invoked, about $0.0001 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 2026-08-31.