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 WESTsyre21/setup-backend-stack --skill templatesgit clone --depth 1 https://github.com/WESTsyre21/setup-backend-stackWrote 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/westsyre21/setup-backend-stack/templates)<a href="https://agentmods.dev/skills/westsyre21/setup-backend-stack/templates"><img src="https://agentmods.dev/badge/skills/westsyre21/setup-backend-stack/templates/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/westsyre21/setup-backend-stack/templates"><img src="https://agentmods.dev/badge/skills/westsyre21/setup-backend-stack/templates.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 | $0.00054 | $0.01965 |
| Opus 5.5 | $0.00022 | $0.00786 |
| Sonnet 5.5 | $0.00011 | $0.00393 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade A, and why
backend-setup-stack 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 1mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Docker + PostgreSQL + npm Server + ORM Architecture Setup
Objective
To scaffold a containerized local development ecosystem that connects an npm backend server to a Dockerized PostgreSQL instance via an ORM, establishing automated, version-controlled database migrations.
Phase 1: Environment Assessment & State Initialization
- Check capabilities: Confirm whether you have filesystem write access and shell execution access.
- If yes, perform actions and report outputs.
- If no, output exact commands and file contents and ask the user to execute them.
- Analyze Requirements: Scan the user's prompt for specific configuration choices:
- If the user does not specify an ORM, select Prisma.
- Only select Sequelize if the user explicitly includes the exact token
Sequelize(case-insensitive). - If both ORMs are mentioned or the request is ambiguous, ask: "Which ORM do you prefer: Prisma or Sequelize?"
- Chosen web framework (e.g., Express, Fastify).
- Custom port preferences (default to 3000 for server, 5432 for DB).
- Anchor State to Disk: If you have write access, create or update
.claude_history/setup_status.mdin the project root with the chosen ORM, DB connection string, and initialization checklist. If you do not have write access, print the exact commands and file contents to create or update that file and ask the user to confirm.
Phase 2: Structural Scaffolding & ORM Initialization
If running as an agent with filesystem access, execute the following commands and report results. Otherwise, print the exact shell commands and file contents and ask the user to run them.
- Confirm Docker availability:
- Run
docker --versionanddocker-compose --version. - If either command is missing, instruct: "Install Docker Desktop (https://www.docker.com/products/docker-desktop) or run your platform's Docker install instructions" and abort further steps.
- Run
- Initialize npm if no
package.jsonexists:npm init -y - Install the core backend and database dependencies:
- For Express apps:
npm install express - For Prisma:
npm install @prisma/clientandnpm install -D prisma - For Sequelize:
npm install sequelize pg pg-hstoreandnpm install -D sequelize-cli - If using
nodemonfor development, also runnpm install -D nodemon
- For Express apps:
- Ensure
package.jsoncontains adevscript. If absent, add one before running:- Example:
npm pkg set scripts.dev "node server.js" - Or:
npm pkg set scripts.dev "nodemon server.js"
- Example:
- Trigger the ORM initialization command:
- Prisma:
npx prisma init(generates/prisma/schema.prismaand updates.env) - Sequelize:
npx sequelize-cli init(generates/models,/migrations,/seeders,/config)
- Prisma:
What ships with it
4 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.
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.
- 1mo ago First seen · 106 lines · 54 tokens per session scan A b7c42d12c15f
backend-setup-stack is a skill published in the GitHub repository WESTsyre21/setup-backend-stack (4 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 1,965 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 2026-08-31.
Other skills, from other repositories
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…
postgres
Use when working with PostgreSQL specifically. Covers indexing, MVCC and vacuum, connection pooling, partitioning, JSONB, replication, and the operational realities that separate Postgres from generic SQL. Trigger on "postgres table is bloated", "autovacuum isn't keeping up", "set up pgbouncer", "add a column without…
postgres-drizzle
Write or review PostgreSQL schemas, queries, migrations, and Drizzle ORM code. Use for Postgres/Drizzle relations, indexing, pooling, or query performance; not for unrelated databases or generic backend work.
supabase
Expert Supabase assistance covering PostgreSQL, Row Level Security (RLS), Edge Functions, Auth, and pgvector. Use when building full-stack web/mobile applications with Postgres backends and instant REST/GraphQL APIs.
golang-database
This skill should be used when the user asks to "configure a Go database connection pool", "use database/sql in Go", "set up pgxpool", "why is my Go app running out of connections", "scan rows into a Go struct", "handle sql.ErrNoRows", or writes Go code that opens, pools, queries, or scans a PostgreSQL/MySQL…
sc-supabase
(STUB / NOT IMPLEMENTED YET) Supabase backend as an alternative to self-hosted Convex. Create project, apply migrations from supabase/migrations, deploy Edge Functions, generate types. For projects where Postgres + Row-Level-Security is a better fit than Convex's reactive query model.