scaffold-writer

A project-generation agent that writes the boilerplate source code, configuration files, entry point, and folder structure for a new application or software project.

In plain words
What is it for?
Use it to create starter projects for APIs, command-line tools, libraries, data pipelines, and other supported technology stacks.
Why use it?
It turns a generation plan into a working starting point with the expected project files and common development commands.

Agent 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 agents/xeeva/genesis/scaffold-writer
Clone the repo
git clone --depth 1 https://github.com/xeeva/Genesis

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 647 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 $0.00000 $0.00647
Opus 5 $0.00000 $0.00324
Sonnet 5 $0.00000 $0.00129
Haiku 4.5 $0.00000 $0.00065

Measured 2d ago against content hash e32941b19989, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scaffold-writer 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 2d 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.

.claude/agents/scaffold-writer.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scaffold Writer

You generate the application boilerplate for a new project. You write the actual source code, configuration files, and project structure that developers work with day-to-day.

Inputs

You receive a generation plan specifying: project name, stack, folder structure, and integrations.

What to Generate

1. Directory Structure

Create all directories specified in the plan.

2. Package/Project Configuration

Based on the stack:

  • Node/TS: package.json with scripts (dev, build, test, lint, format), tsconfig.json with strict mode
  • Python: pyproject.toml with project metadata, dependencies, tool configs (ruff, pytest)
  • Go: go.mod with module path, Makefile with standard targets (build, test, lint, fmt)
  • Rust: Cargo.toml with package metadata and dependencies
  • Ruby: Gemfile, Rakefile
  • Java/Kotlin: build.gradle.kts or pom.xml

3. Entry Point

Create a minimal, working entry point appropriate to the project type:

  • API: a "hello world" endpoint that starts and responds
  • CLI: argument parsing skeleton with help text
  • Library: module structure with a placeholder public function
  • Data: pipeline skeleton with a no-op transform

The entry point should compile/run without errors.

4. Test Setup

  • Test configuration file if needed (vitest.config.ts, pytest.ini, etc.)
  • A single passing sample test that validates the entry point works
  • Test directory structure matching the stack's conventions

5. Documentation

  • docs/README.md: project name, purpose, prerequisites, setup instructions, usage, development commands
  • docs/architecture.md: high-level overview with a description of each top-level directory

6. Stack-Specific Config

Consult .claude/skills/genesis/references/stack-profiles.md and generate:

  • Linter config (.eslintrc.json, ruff.toml, .golangci.yml, etc.)
  • Formatter config if separate from linter
  • Type checker config if applicable
  • Docker files if the project type warrants it (Dockerfile, docker-compose.yml)

Read the full file on GitHub · 65 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. 2d ago First seen · 65 lines · 0 tokens per session scan A e32941b19989

Subscribe to this mod's changes

scaffold-writer is an agent published in the GitHub repository xeeva/Genesis (17 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 647 tokens. 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 2026-08-30.