agentmods.dev

scaffold CLAUDE.md

Project instructions for a Claude Code plugin and TypeScript command-line tool that assembles software-project prompts from Markdown pipeline files. It emphasizes simple changes, test-first development, and verifying behavior before completion.

In plain words
What is it for?
Use it when working on the zigrivers/scaffold repository, especially its pipeline content, TypeScript CLI, Claude Code plugin structure, tests, and project documentation.
Why use it?
It gives an AI coding assistant a shared understanding of the project’s structure, priorities, and source-of-truth files. This reduces inconsistent changes and skipped verification work.

Instructions file

5 2d ago C scan 9,300 tokens original MIT
View the source file zigrivers/scaffold
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 instructions/zigrivers/scaffold/claude-md
Clone the repo
git clone --depth 1 https://github.com/zigrivers/scaffold
Per session 9,300 This file is loaded in full into every session.
When invoked 9,300 The same file — it is already loaded in full.
Security scan C 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 $0.09300 $0.09300
Opus 5 $0.04650 $0.04650
Sonnet 5 $0.01860 $0.01860
Haiku 4.5 $0.00930 $0.00930

Measured 2d ago against content hash a12483f862b5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

scaffold CLAUDE.md scanned grade C 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 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.

Recursive force deletehighDestructive command

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

D="$(mktemp -d)"; trap 'rm -rf "$D"' EXIT INT TERM # cleanup even on Ctrl-C/early exit
CLAUDE.md · 524 lines

How it starts

The opening of the file, as written. The whole thing — 524 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Core Principles

  • Simplicity First: Make every change as simple as possible. Minimal code, minimal impact. Don't over-engineer.
  • No Laziness: Find root causes. No temporary fixes. Senior developer standards.
  • TDD Always: Write failing tests first, then make them pass, then refactor. No exceptions.
  • Prove It Works: Never mark a task complete without demonstrating correctness — tests pass, logs clean, behavior verified.

Project Overview

This is a prompt pipeline — a curated sequence of structured meta-prompts used to scaffold new software projects with Claude Code and other supported AI tools. The pipeline is defined as individual .md files in content/pipeline/, organized into 16 phases, and assembled into full prompts at runtime by the TypeScript CLI.

Structure

This repo is a Claude Code plugin (installable via /plugin marketplace add) and a TypeScript CLI distributed via npm and Homebrew.

Source of Truth

  • content/pipeline/ — 99 meta-prompt files organized into 16 phases (source of truth for pipeline steps)
  • content/tools/ — 12 tool meta-prompts (category: tool, stateless: true) orthogonal to the pipeline
  • content/knowledge/ — 301 domain expertise entries in 21 categories (injected into prompts during assembly)
  • content/skills/ — Skill templates with {{markers}} for multi-platform resolution
  • content/methodology/ — Preset configs (deep, mvp, custom, brownfield — brownfield is adopt-selected, not an init choice) plus project-type and domain overlays
  • src/types/frontmatter.ts — Canonical PHASES constant defining all 16 phase slugs, numbers, and display names

Legacy (v1)

The original v1 prompt content is archived at docs/archive/prompts-v1.md. It is not the source of truth — pipeline steps in content/pipeline/ are authoritative.

Plugin Structure

  • .claude-plugin/plugin.json — Plugin manifest (name: scaffold)
  • skills/ — Generated skills (built from content/skills/ templates; gitignored)
  • scripts/ — Bash utility scripts

Read the full file on GitHub · 524 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 · 524 lines · 9,300 tokens per session scan C a12483f862b5

Subscribe to this mod's changes

scaffold CLAUDE.md is an instructions file published in the GitHub repository zigrivers/scaffold (5 stars, last pushed 2d ago), licensed MIT. It adds 9,300 tokens to every session, about $0.0465 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code GenerationData and AITestingWriting and docsai-assisted-developmentbeadsclaudeclaude-codedeveloper-tools
Related

Other instructions, from other repositories

drogon-claude-plugin CLAUDE.md

Claude Code instructions for voidvec/drogon-claude-plugin, covering drogon 后端开发规则, a. 异步回调模型（所有 handler 的最高纪律）, b. 事件循环模型（trantor io）, skill 路由表 and 通用纪律（跨 skill）.

voidvec/drogon-claude-plugin · 1,799 tokens

speckit AGENTS.md

AGENTS.md instructions for jmanhype/speckit, covering agents.md - instructions for ai coding agents, core philosophy, pivotal methodology alignment, pivotal-style epic format and priority levels (pivotal-aligned).

jmanhype/speckit · 4,083 tokens

speckit CLAUDE.md

Claude Code instructions for jmanhype/speckit, covering claude.md, repository structure, directory layout, pivotal labs methodology and pivotal-style beads workflow.

jmanhype/speckit · 4,289 tokens

sdd CLAUDE.md

Claude Code instructions for LiorCohen/sdd, covering claude.md, task management rules (mandatory), output rules, git rules and build rules.

LiorCohen/sdd · 1,242 tokens

claude-code-templates CLAUDE.md

Instructions for Justdvp/claude-code-templates, covering claude.md, project overview, development commands, package management and application commands.

Justdvp/claude-code-templates · 4,007 tokens

flow AGENTS.md

Instructions for cofin/flow: Flow is a toolkit for context-driven development. It has no flow executable; invoke the Flow skill or a /flow: command.

cofin/flow · 202 tokens