scaffold-backend

scaffold-backend is a skill for Claude Code, Codex from emilyLi2020/WAVE. It costs 86 tokens per session (2,714 once invoked), scanned A, original, Apache-2.0.

A tool that scaffolds a FastAPI backend from a project's PRD.md and AGENTS.md files. FastAPI is a Python framework for building web APIs, and backend routes are the URLs through which an application provides data or actions.

In plain words
What is it for?
It creates a server/ directory with FastAPI routes, data models, and optional Supabase integration based on the documented backend requirements.
Why use it?
It creates only the backend described in the requirements and stops when the required documents are missing or the project does not need a backend.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

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 skills/emilyli2020/wave/scaffold-backend
Any agent
npx skills add emilyLi2020/WAVE --skill scaffold-backend
Clone the repo
git clone --depth 1 https://github.com/emilyLi2020/WAVE

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 scaffold-backend

README.md
[![agentmods](https://agentmods.dev/badge/skills/emilyli2020/wave/scaffold-backend.svg)](https://agentmods.dev/skills/emilyli2020/wave/scaffold-backend)
Your own site
<a href="https://agentmods.dev/skills/emilyli2020/wave/scaffold-backend"><img src="https://agentmods.dev/badge/skills/emilyli2020/wave/scaffold-backend.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,714 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00086 $0.02714
Opus 5 $0.00043 $0.01357
Sonnet 5 $0.00017 $0.00543
Haiku 4.5 $0.00009 $0.00271

Measured 5d ago against content hash 27d820c1cefe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

scaffold-backend scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

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

curl http://localhost:8000/health
.agents/skills/scaffold-backend/SKILL.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scaffold Backend

This skill creates the backend for the user's project inside a server/ directory at the repo root. Like scaffold-frontend, it is driven entirely by PRD.md and AGENTS.md. Every route, every Pydantic model, and the decision to include Supabase are all derived from the PRD.

Preflight: PRD, AGENTS, and Backend Needed

Before doing anything else, check three conditions:

  1. AGENTS.md exists at the repo root.
  2. PRD.md exists at the repo root.
  3. PRD.md > Backend Needed? starts with Yes.
test -f AGENTS.md && test -f PRD.md || { echo "MISSING_DOCS"; exit 1; }
grep -A1 "^## Backend Needed?" PRD.md | tail -n1

Fail-fast responses

  • If AGENTS.md or PRD.md is missing, STOP and respond exactly:

    This skill cannot run yet. AGENTS.md and PRD.md must exist at the repo root. Run the domain-to-spec skill first, or run the quickstart skill to chain everything automatically.

  • If Backend Needed? is No (or empty), STOP and respond exactly:

    This project does not need a backend according to PRD.md > Backend Needed?. If that is wrong, rerun the domain-to-spec skill to update the PRD. Otherwise, run the feature-builder skill to build out frontend features.

Do not create any files in either fail case.

Step 1: Read the PRD and AGENTS

Extract from PRD.md:

  • Routes list (from PRD.md > Backend Routes). Each bullet becomes a FastAPI route.
  • Data model (from PRD.md > Data Model). Each entity becomes a Pydantic model.
  • Domain constraints (from PRD.md > Domain Constraints). Used to decide what validation rules to add.
  • Auth requirement. Check if PRD.md > Core Features (MVP) or PRD.md > User Flow mention login, accounts, or user-specific data. If yes, Supabase Auth is needed.

Extract from AGENTS.md:

  • The Python version and FastAPI conventions.
  • Whether Supabase is listed under ## Tech Stack > Database.

Step 2: Ask About Supabase

Prompt the user:

"Your PRD implies this app needs a database. I recommend Supabase because it is free, hosted, and integrates auth, Postgres, and storage in one service. Should I wire it up now? (yes / no / later)"

Read the full file on GitHub · 345 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. 5d ago First seen · 345 lines · 86 tokens per session scan A 27d820c1cefe

Subscribe to this mod's changes

scaffold-backend is a skill published in the GitHub repository emilyLi2020/WAVE (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 86 tokens to every session and 2,714 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…

K-Dense-AI/scientific-agent-skills · 98 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

rocm-kernels

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…

huggingface/kernels · 93 tokens

holoscan-install-wheel

Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.

NVIDIA/skills · 37 tokens

typing-exclusion-worker

Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.

getsentry/skills · 57 tokens