backend-building-swarm

backend-building-swarm is a skill for Claude Code, Codex from serejaris/kimi-skills. It costs 107 tokens per session (5,062 once invoked), scanned A, original, MIT.

A backend-building tool that adds a server side to an existing web application frontend. It uses tRPC for typed communication, Drizzle ORM for database access, Hono for web routes, MySQL for storage, and OAuth 2.0 for sign-in.

In plain words
What is it for?
Use it to add APIs, shared API contracts, database support, authentication, and full-stack features to a project created by the webapp-building-swarm workflow.
Why use it?
It lets a team add backend features without replacing the existing frontend files. It is designed for a shared repository where separate workers build and merge parts of the application.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash /app/.agents/skills/swarm-workspace/scripts/setup-local.sh <branch> $HOME/app-<branch>.

Good fit Use it to add APIs, shared API contracts, database support, authentication, and full-stack features to a project created by the webapp-building-swarm workflow.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/serejaris/kimi-skills
agentmods
npx agentmods add skills/serejaris/kimi-skills/backend-building-swarm

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for backend-building-swarm

README.md
[![agentmods](https://agentmods.dev/badge/skills/serejaris/kimi-skills/backend-building-swarm/github.svg)](https://agentmods.dev/skills/serejaris/kimi-skills/backend-building-swarm)
Your own site
<a href="https://agentmods.dev/skills/serejaris/kimi-skills/backend-building-swarm"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/backend-building-swarm/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.

agentmods 80×15 button for backend-building-swarm

Your own site · 80×15
<a href="https://agentmods.dev/skills/serejaris/kimi-skills/backend-building-swarm"><img src="https://agentmods.dev/badge/skills/serejaris/kimi-skills/backend-building-swarm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,062 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00107 $0.05062
Opus 5 $0.00053 $0.02531
Sonnet 5 $0.00021 $0.01012
Haiku 4.5 $0.00011 $0.00506

Measured 12d ago against content hash 18d9ce369a70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

backend-building-swarm 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 12d ago.

The scan reads SKILL.md. This mod also ships 37 executable files (scripts/.prepare-template.sh, scripts/init.sh, scripts/lib/merge-package-json.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/backend-building-swarm/SKILL.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backend Building Swarm

Stack: tRPC + Drizzle ORM + Hono + MySQL + OAuth 2.0

A swarm-aware backend skill that grafts onto an existing webapp-building-swarm project. Adds api/, contracts/, and optionally db/ directories — but never replaces or modifies existing frontend files.

Prerequisite: An existing shared repo created by webapp-building-swarm at /mnt/agents/output/app.

Architecture

This skill builds on the swarm-workspace two-tier filesystem — a shared coordination repo (branch hub) plus per-subagent worktrees. See swarm-workspace/SKILL.md for the full contract; it is not restated here.

init.sh grafts in place on $PROJECT_PATH and commits on whatever branch is checked out there — it does NOT manage worktrees or merge. In the swarm flow the main agent creates the backend worktree via swarm-workspace's setup-local.sh, runs init.sh in it with PROJECT_PATH pointed at the worktree, commits on the backend branch, and merges that branch into the integration line before page branches fork — so all page agents inherit the tRPC client and contracts. The main agent runs the graft itself rather than dispatching a subagent because init.sh writes a gitignored .env that never travels through the merge: it survives only in the sandbox where it ran, which must be the main agent's own — the one that later builds and stages .env into the other worktrees. Webapp commit history is preserved because the backend branch descends from the scaffolded frontend.

Features

Features can be installed incrementally. Base infrastructure (Hono server, tRPC, contracts) is always installed automatically on first run.

Feature What it provides Dependencies
db Drizzle ORM + MySQL — adds db/, api/queries/connection.ts, drizzle.config.ts
auth Kimi OAuth + user management — adds api/kimi/, Login page, useAuth, AuthLayout requires db (auto-included)

Read the full file on GitHub · 334 lines

Files

What ships with it

60 files 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.

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. 12d ago First seen · 334 lines · 107 tokens per session scan A 18d9ce369a70

Subscribe to this mod's changes

backend-building-swarm is a skill published in the GitHub repository serejaris/kimi-skills (6 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 5,062 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 2026-08-31.

Related

Other skills, from other repositories

go-database

Use when writing, reviewing, or debugging Go code that talks to a SQL database (PostgreSQL, MySQL, MariaDB, SQLite). Covers library choice (database/sql, sqlx, sqlc, pgx, GORM trade-offs), parameterized queries, context propagation, NULL handling, scanning, transactions and isolation, connection pool tuning, and…

muratmirgun/gophers · 98 tokens

backend-setup-stack

Bootstraps a local Node.js backend development stack with Docker, PostgreSQL, and an ORM (Prisma or Sequelize). Use this skill whenever the user wants to: initialize a new backend project, set up a Dockerized database locally, wire up an ORM with automated migrations, scaffold an Express server with a health endpoint…

WESTsyre21/setup-backend-stack · 155 tokens

backend-setup-stack

Use this skill when the user wants to initialize a local development environment using Docker, PostgreSQL, an npm server, and an ORM (Prisma/Sequelize) with automated migration workflows, including detection of existing migration metadata and database readiness checks.

WESTsyre21/setup-backend-stack · 54 tokens

supabase

Use when doing ANY task involving Supabase. Triggers: Supabase products (Database, Auth, Edge Functions, Realtime, Storage, Vectors, Cron, Queues); client libraries and SSR integrations (supabase-js, @supabase/ssr) in Next.js, React, SvelteKit, Astro, Remix; auth issues (login, logout, sessions, JWT, cookies…

supabase/agent-skills · 185 tokens

offensive-api-abuse

Advanced API exploitation methodology focused on business logic abuse and sophisticated attack patterns that bypass traditional security controls. Covers business logic bypass through API call chaining and workflow manipulation. Addresses GraphQL-specific attacks including batching for credential brute-force, query…

SnailSploit/Claude-Red · 184 tokens

nestjs

Provides comprehensive NestJS framework patterns with Drizzle ORM integration for building scalable server-side applications. Generates REST/GraphQL APIs, implements authentication guards, creates database schemas, and sets up microservices. Use when building NestJS applications, setting up APIs, implementing…

giuseppe-trisciuoglio/developer-kit · 65 tokens