agentmods.dev

dory: Instructions file for Claude Code

CLAUDE.md

dory CLAUDE.md is an instructions file for Claude Code from dorylab/dory. It costs 499 tokens per session, scanned A, original, Apache-2.0.

Project instructions for a Yarn 4 monorepo containing several applications and shared packages. A monorepo is one repository that holds multiple related projects.

In plain words
What is it for?
Working on the repository's web, admin, and desktop apps, shared authentication code, shadcn/ui components, and dependencies.
Why use it?
They give contributors the correct commands, file locations, and dependency-upgrade rules for this repository. This reduces mistakes when changing apps, shared code, or UI components.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions Claude Code.

This is dorylab/dory's own configuration. It tells Claude Code how to work on dory 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 dory configures →

not rated 309repo +1 3d ago A scan 499 tokens original Apache-2.0
View source ↗ dorylab/dory getdory.dev
Reuse

Borrowing it

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

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 dory CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dorylab/dory/claude-md"><img src="https://agentmods.dev/badge/instructions/dorylab/dory/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 499 This file is loaded in full into every session.
When invoked 499 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 $0.00499 $0.00499
Opus 5.5 $0.00200 $0.00200
Sonnet 5.5 $0.00100 $0.00100
Haiku 4.5 $0.00050 $0.00050

Measured 2mo ago against content hash 108d0f0e0a9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dory 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 · 41 lines

What it actually says

Dory - Claude Code Guidelines

Project Structure

  • Monorepo managed by Yarn 4 (Berry) workspaces
  • apps/web — Next.js web app (main product)
  • apps/admin — Next.js admin panel
  • apps/electron — Electron desktop app
  • packages/auth-core — Shared auth package

Package Manager

  • Yarn 4 — use yarn commands, NOT npm or pnpm
  • yarn workspace <name> <cmd> to run workspace-specific commands
  • yarn install to install dependencies
  • yarn workspace web typecheck to check types

shadcn/ui

  • Components live in apps/web/registry/new-york-v4/ui/
  • Chart demos live in apps/web/registry/new-york-v4/charts/
  • To add/update components: yarn dlx shadcn@latest add <component-name> --overwrite
  • To update multiple: yarn dlx shadcn@latest add comp1 comp2 comp3 --overwrite
  • shadcn CLI may pin dependency versions (remove ^) or change versions — review package.json after running
  • shadcn CLI installs to default path; if components are in a custom directory, you may need to move files after

Dependency Upgrades

  • Use npx npm-check-updates --workspaces to check for outdated dependencies across all workspaces
  • Use yarn npm audit to check for known vulnerabilities
  • For TypeScript major upgrades: run npx @andrewbranch/ts5to6 --fixBaseUrl <tsconfig> and --fixRootDir <tsconfig> to verify config compatibility
  • When upgrading packages that have shadcn wrappers (recharts, react-day-picker, react-resizable-panels), update via yarn dlx shadcn@latest add <component> --overwrite to get compatible wrapper code
  • Always run yarn workspace web typecheck after upgrades to catch breaking changes
  • Prefer ^ prefix for dependency versions in package.json

Code Style

  • All git commits, PR titles, and branch names must be in English
  • TypeScript strict mode is enabled across all workspaces
  • ESLint with flat config (eslint.config.mjs)
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 · 41 lines · 499 tokens per session scan A 108d0f0e0a9c

Subscribe to this mod's changes

dory CLAUDE.md is an instructions file published in the GitHub repository dorylab/dory (309 stars, last pushed 3d ago), licensed Apache-2.0. It adds 499 tokens to every session, about $0.0020 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 2026-08-30.

DatabasesFrontendaiclickhousedata-studiodeveloper-toolsmysql
Related

dory CLAUDE.md compared with instructions from other repositories

dory CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dory CLAUDE.mddorylab/doryInstructions file3093d agoApache-2.0A499Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode