What is dory AGENTS.md?

Repository guidance for coding agents working on Dory, a Yarn workspace monorepo with web, admin, and Electron applications that share core packages.

Use it when changing the web, admin, or Electron applications, authentication, database code, connection drivers, or runtime selection.

It explains Dory’s desktop and self-hosted web modes and where their shared runtime logic lives, preventing inconsistent environment handling.

dory AGENTS.md — Instructions file by dorylab

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/dorylab/dory/agents-md

Clone the repo

git clone --depth 1 https://github.com/dorylab/dory

Made for: Codex, OpenCode.

Per session 1,955 This file is loaded in full into every session.

When invoked 1,955 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.01955	$0.01955
Opus 5	$0.00978	$0.00978
Sonnet 5	$0.00391	$0.00391
Haiku 4.5	$0.00196	$0.00196

Measured yesterday against content hash cfa1204de3b4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dory AGENTS.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 yesterday.

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.

AGENTS.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Overview

This repository is a Yarn workspace monorepo for Dory.

apps/web: main product application
apps/admin: admin application
apps/electron: Electron wrapper for the web app
packages/auth-core: shared auth package

Most product work happens in apps/web.

Product Model

The product has two runtime forms:

Desktop
Web self-hosting

These are runtime variants of the same apps/web application, not two separate frontends.

Runtime is determined by DORY_RUNTIME and NEXT_PUBLIC_DORY_RUNTIME
Do not scatter direct runtime env checks in feature code
Use apps/web/lib/runtime/runtime.ts as the runtime helper layer
Direct runtime env reads are only allowed inside the runtime helper layer or boot/injection code such as Electron startup

Core Source Areas

Treat these as the primary source of truth:

apps/web/app
apps/web/components
apps/web/lib
apps/web/lib/database
apps/web/lib/database/postgres/schemas
apps/web/lib/database/postgres/impl
apps/web/lib/connection/drivers
apps/web/lib/utils/ensure-connection.ts
apps/web/hooks
apps/web/shared
apps/admin/app
apps/admin/lib
apps/electron/main
packages/i18n/src
packages/auth-core/src
tests/e2e

Avoid editing generated or local artifact paths unless the task explicitly targets them:

**/.next/**
**/node_modules/**
apps/web/dist-scripts
apps/web/release
apps/web/.tmp
apps/web/localdata
apps/electron/dist
apps/electron/dist-electron
apps/electron/dist/mac-arm64
playwright-report
test-results

Commands

Run from the repository root unless workspace-local execution is more appropriate.

yarn
yarn dev
yarn admin:dev
yarn electron:dev
yarn build
yarn admin:build
yarn electron:build
yarn lint
yarn typecheck
yarn format:check
yarn format:write
yarn test:e2e

Useful workspace commands:

yarn workspace web run lint
yarn workspace web run typecheck
yarn workspace admin run lint
yarn workspace admin run typecheck

Read the full file on GitHub · 228 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.

yesterday First seen · 228 lines · 1,955 tokens per session scan A cfa1204de3b4

Subscribe to this mod's changes

dory AGENTS.md is an instructions file published in the GitHub repository dorylab/dory (280 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,955 tokens to every session, about $0.0098 per session on Opus 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.

Data and AI Databases ai clickhouse data-studio developer-tools mysql

dory AGENTS.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

AGENTS.md

Overview

Product Model

Core Source Areas

Commands

What this file has done since we first saw it

Other instructions, from other repositories

mcp CLAUDE.md

mcp-toolbox GEMINI.md

whodb AGENTS.md

jitsu AGENTS.md

openlit AGENTS.md

Tracely-ai CLAUDE.md