agentmods.dev

drywall: Instructions file for Claude Code

CLAUDE.md

drywall CLAUDE.md is an instructions file for Claude Code from nikhaldi/drywall. It costs 515 tokens per session, scanned A, original, MIT.

A Claude Code plugin that finds repeated or very similar code and helps consolidate it. It uses jscpd to detect duplication, presents ranked results, and includes an agent for refactoring and verification.

In plain words
What is it for?
Scanning a project for exact, near, or structural duplicates, reviewing the most important findings, and refactoring them into shared code.
Why use it?
It reduces the need to search manually for duplicated code and helps organize the resulting cleanup.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions .claude-plugin; mentions CLAUDE.md; mentions Claude Code.

This is nikhaldi/drywall's own configuration. It tells Claude Code how to work on drywall itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything drywall configures →

not rated 7repo 16d ago A scan 515 tokens original MIT
View source ↗ nikhaldi/drywall
Reuse

Borrowing it

Nothing to install: this file belongs to nikhaldi/drywall. 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/nikhaldi/drywall/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/nikhaldi/drywall

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.

agentmods badge for drywall CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nikhaldi/drywall/claude-md/github.svg)](https://agentmods.dev/instructions/nikhaldi/drywall/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nikhaldi/drywall/claude-md"><img src="https://agentmods.dev/badge/instructions/nikhaldi/drywall/claude-md/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.

agentmods 80×15 button for drywall CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/nikhaldi/drywall/claude-md"><img src="https://agentmods.dev/badge/instructions/nikhaldi/drywall/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 515 This file is loaded in full into every session.
When invoked 515 The same file — it is already loaded in full.
Security scan A 0 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00515 $0.00515
Opus 5.5 $0.00206 $0.00206
Sonnet 5.5 $0.00103 $0.00103
Haiku 4.5 $0.00052 $0.00052

Measured 2mo ago against content hash 91e5e1ad2663, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

drywall CLAUDE.md 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 2mo 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.md · 35 lines

How it starts

The opening of the file, as written. The whole thing — 35 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.

Project Overview

DRYwall is a Claude Code plugin for detecting and eliminating code duplication. It uses jscpd as its detection engine.

Architecture

The plugin has three components that work together:

  • MCP Server (source: src/jscpd.js, built: servers/jscpd.js) — A Node.js MCP server providing the detect_code_duplication tool. Reads .drywallrc.json, runs jscpd, and returns structured results ranked by impact. The skill and agent both use this tool for detection. Bundled via esbuild for distribution (no node_modules needed at runtime).

  • Skill (skills/scan/SKILL.md) — User-invocable command /drywall:scan that calls the MCP tool and presents the top 10 duplicates with consolidation suggestions.

  • Agent (agents/dedup-refactor.md) — Autonomous refactoring agent (Sonnet, max 30 turns) that calls the MCP tool, classifies duplicates (exact/near/structural), plans consolidation, refactors code, and verifies changes.

Configuration

Projects using DRYwall configure via .drywallrc.json at project root. Keys jscpdVersion and respectGitignore are DRYwall-specific; all other keys are passed through as jscpd CLI flags (camelCase is converted to kebab-case). User arguments override config file values.

Development

  • npm install — install dependencies
  • npm run build — bundle src/jscpd.js (and its dependency src/lib.js) to servers/jscpd.js via build.js
  • The bundle must be rebuilt and committed after changes to src/jscpd.js or src/lib.js
  • npm test — run unit tests (Node.js built-in test runner)
  • Tests live in test/**/*.test.js and cover src/lib.js (helpers extracted for testability)
  • test/fixtures/ contains a sample codebase with intentional duplication for manual testing

Version

The version is defined in package.json and injected into the bundle at build time via esbuild's define. It must also be kept in sync in .claude-plugin/plugin.json — CI verifies this.

Read the full file on GitHub · 35 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. 2mo ago First seen · 35 lines · 515 tokens per session scan A 91e5e1ad2663

Subscribe to this mod's changes

drywall CLAUDE.md is an instructions file published in the GitHub repository nikhaldi/drywall (7 stars, last pushed 16d ago), licensed MIT. It adds 515 tokens to every session, about $0.0021 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.

Code review
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens