What is platform-maker?

A generator for complete SaaS platforms from a YAML configuration file. SaaS means software delivered as an online service; the generated platform can include application screens, database structures, server routes, translations, payments, referrals, and deployment settings.

Use it to generate the starting structure for a SaaS product, including its web interface, database, API routes, internationalization, payment integration, referral system, and deployment configuration.

It reduces the amount of repetitive setup needed to start a configurable online product. It also records important generation decisions and can retry fixable build or type errors.

How djbelieny/nova configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to djbelieny/nova. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/djbelieny/nova/main/.claude/skills/platform-maker/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/djbelieny/nova

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/djbelieny/nova/platform-maker/github.svg)](https://agentmods.dev/skills/djbelieny/nova/platform-maker)

Your own site

<a href="https://agentmods.dev/skills/djbelieny/nova/platform-maker"><img src="https://agentmods.dev/badge/skills/djbelieny/nova/platform-maker/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/djbelieny/nova/platform-maker"><img src="https://agentmods.dev/badge/skills/djbelieny/nova/platform-maker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,260 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 3 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.07260
Opus 5.5	$0.00028	$0.02904
Sonnet 5.5	$0.00014	$0.01452
Haiku 4.5	$0.00007	$0.00726

Measured 1mo ago against content hash 8f14e8c826dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

platform-maker scanned grade D with 3 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.

The scan reads SKILL.md. This mod also ships 4 executable files (templates/router.template.ts, templates/schema.postgres.template.ts, templates/seed.template.ts, …), 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo rm -rf

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf /

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:3001/api/health | grep -q '"status":"ok"'

.claude/skills/platform-maker/SKILL.md · 1,012 lines

How it starts

The opening of the file, as written. The whole thing — 1,012 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Platform Maker Skill

Overview

This skill autonomously generates complete SaaS platforms from a YAML configuration. It runs with minimal user interruption, spawning parallel subagents that communicate via shared memory to build faster.

Invocation

/platform-maker
/platform-maker /path/to/project
/platform-maker /path/to/project/platform.config.yaml

AUTONOMOUS OPERATION PRINCIPLES

Minimal Interruption Policy

ONLY interrupt the user for:

Initial project folder (if not provided)
Missing critical config information that cannot be inferred
Destructive command confirmation (see safeguards)
Unrecoverable errors after 3 retry attempts

DO NOT interrupt for:

Validation errors you can fix automatically
Missing optional fields (use sensible defaults)
Build errors (fix and retry)
Type errors (fix and retry)
Minor decisions (make the best choice and document it)

Decision Logging (Enhanced)

Log ALL significant events to .platform-maker/decisions.log:

Log Format:

[YYYY-MM-DD HH:MM:SS] TYPE: Message

Event Types:

Type	When to Use
`INIT`	Generation started
`CONFIG`	Config parsed/validated
`AUTO-DECISION`	Autonomous choice made
`USER-PROMPT`	Question shown to user
`USER-RESPONSE`	User's answer received
`AGENT-START`	Agent began work
`AGENT-FILE`	Agent created/modified file
`AGENT-COMPLETE`	Agent finished successfully
`AGENT-ERROR`	Agent encountered error
`VALIDATION`	Validation check result
`AUTO-FIX`	Automatic error fix applied
`DB-PUSH`	Database schema pushed
`COMPLETE`	Generation finished
`FAILED`	Generation failed

Example Complete Log:

[2026-02-05 12:48:00] INIT: Platform generation started for BookVault
[2026-02-05 12:48:00] CONFIG: Parsed platform.config.yaml successfully
[2026-02-05 12:48:00] CONFIG: Languages: en, pt-BR, es
[2026-02-05 12:48:00] CONFIG: Payment provider: Square
[2026-02-05 12:48:05] AUTO-DECISION: Using SQLite for development database
[2026-02-05 12:48:10] AGENT-START: Database agent started
[2026-02-05 12:50:00] AGENT-FILE: Created drizzle/schema.ts
[2026-02-05 12:50:30] AGENT-FILE: Created drizzle/seed.ts
[2026-02-05 12:51:00] DB-PUSH: Pushing schema to database
[2026-02-05 12:51:05] DB-PUSH: Schema push successful
[2026-02-05 12:51:10] DB-PUSH: Seed data inserted
[2026-02-05 12:52:00] AGENT-COMPLETE: Database agent finished (4 files)
[2026-02-05 12:52:30] AGENT-START: Backend agent started
...
[2026-02-05 12:59:00] VALIDATION: TypeScript check passed
[2026-02-05 12:59:05] VALIDATION: Build succeeded
[2026-02-05 12:59:10] VALIDATION: Server health check passed
[2026-02-05 13:00:00] COMPLETE: Platform generation finished (16 files, 4 agents)

Read the full file on GitHub · 1,012 lines

Files

What ships with it

10 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.

1mo ago First seen · 1,012 lines · 71 tokens per session scan D 8f14e8c826dd

Subscribe to this mod's changes

platform-maker is a skill published in the GitHub repository djbelieny/nova (5 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 7,260 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it D with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Backend and APIs Frontend Multi-Agent ai-agents automation bun claude self-hosted

testing

Testing and code quality context for Jest, React Testing Library, ESLint, and test patterns. Use when writing tests or fixing linting issues.

Team-Commonly/commonly · 31 tokens

webhook-transforms

Generic framework for converting external events (SMS, meetings, social mentions) into brain-ingestible signals. Define a transform function, point the event source at the receiving endpoint, and incoming events get processed through the brain pipeline.

timurgaleev/memex · 52 tokens

tushare

A Python interface for Tushare, a financial data service that provides market and company information for stocks, funds, futures, and digital assets. It returns queried data as pandas tables.

HKUDS/Vibe-Trading · 79 tokens

groq-inference

Ultra-fast LLM inference on custom LPU hardware. OpenAI-compatible API at api.groq.com. Lowest latency in the industry (500-1000+ tok/s). Supports chat completions, vision, audio (Whisper STT + TTS), tool calling, JSON mode, and streaming. Free tier available. Inference only — no training.

synthetic-sciences/openscience · 77 tokens

pod-chat-tone

In-product voice rewrite for agents posting to Commonly pods — kills the report-in-a-chatbox shape (bold-lead sentences, ✅/❌ ladders, em-dash density, mirror clauses, self-narration of one's own reasoning) that makes agent rooms unreadable to the humans they are for. Mandatory pre-post pass on every pod message.…

Team-Commonly/commonly · 135 tokens

pandic-office

Convert Markdown to PDF (or DOCX/EPUB/HTML) using the pandoc CLI. Use when asked to produce a PDF report, brief, summary, or any document where the input is Markdown and the output should be a polished, paginated file.

Team-Commonly/commonly · 59 tokens

nova: Skill for Claude Code