agentmods.dev

dubbl AGENTS.md

Project-specific instructions for dubbl, a Next.js application with an MCP server and a database. MCP is a way for AI agents to call tools provided by an application.

In plain words
What is it for?
They guide feature work, MCP tool updates, Drizzle database migrations, TypeScript checks, and error handling.
Why use it?
They give coding agents the project's rules for verification, tool design, database changes, money values, and access control.

Instructions file for CodexOpenCode

43 +1 2mo ago A scan 349 tokens original Apache-2.0
View the source file dubbl-org/dubbl
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/dubbl-org/dubbl/agents-md
Clone the repo
git clone --depth 1 https://github.com/dubbl-org/dubbl

Made for: Codex, OpenCode.

Per session 349 This file is loaded in full into every session.
When invoked 349 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.

ModelPer sessionOnce invoked
Fable 5 $0.00349 $0.00349
Opus 5 $0.00175 $0.00175
Sonnet 5 $0.00070 $0.00070
Haiku 4.5 $0.00035 $0.00035

Measured 2d ago against content hash 8d17262cc731, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dubbl 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 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.

AGENTS.md · 26 lines

What it actually says

Agent Rules

Build & Verification

  • Do NOT run full builds (npm run build, next build, etc.)
  • Use lint (npm run lint) or typecheck (npx tsc --noEmit) instead for verification
  • Run dev server (npm run dev) only when explicitly asked
  • This project uses Next.js -- all dev/build/start commands go through next

MCP Server Conventions

  • Every user-facing feature must have corresponding MCP tools
  • Keep MCP tools updated when REST API routes change
  • Tool descriptions must be clear for AI agents -- state input expectations (e.g. "amounts in cents") and what is returned
  • All monetary amounts are in integer cents (e.g. $12.50 = 1250)
  • MCP tools use direct DB access via Drizzle, not HTTP self-calls
  • All tools are org-scoped via AuthContext passed at server creation time
  • Use wrapTool() from lib/mcp/errors.ts for consistent error handling
  • Tool files live in lib/mcp/tools/ and export a registerXTools(server, ctx) function
  • Register new tool files in lib/mcp/tools/index.ts
  • Use .describe() on every Zod field in tool input schemas
  • One tool per operation (no multi-purpose tools)

Database

  • All schema changes require Drizzle migration files -- run npx drizzle-kit generate after modifying any file in lib/db/schema/
  • Never use npx drizzle-kit push in production -- it applies changes directly without migrations
  • Migration files live in drizzle/ and must be committed alongside schema changes
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 · 26 lines · 349 tokens per session scan A 8d17262cc731

Subscribe to this mod's changes

dubbl AGENTS.md is an instructions file published in the GitHub repository dubbl-org/dubbl (43 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 349 tokens to every session, about $0.0017 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.

accountingbookkeepingbusinesscrminventory-management
Related

Other instructions, from other repositories

noxctl CLAUDE.md

Instructions for Magnus-Gille/noxctl, covering claude.md — noxctl, what is this?, cli-first in claude code, reading data and dry run first.

Magnus-Gille/noxctl · 698 tokens

counterpoise-ledger CLAUDE.md

Instructions for jeffjjohnston/counterpoise-ledger, covering claude.md, project overview, development commands, essential commands and testing.

jeffjjohnston/counterpoise-ledger · 22,175 tokens

bukio-cli AGENTS.md

AGENTS.md instructions for erikvankempen/bukio-cli, covering agents.md — bukio-cli agent manual, 1. house rules (non-negotiable), 2. environment, 3. command quick reference and 3.1 jurisdiction profiles (16 markets).

erikvankempen/bukio-cli · 24,344 tokens

counterpoise-ledger AGENTS.md

Instructions for jeffjjohnston/counterpoise-ledger: See CLAUDE.md for project instructions and AI coding assistant guidance.

jeffjjohnston/counterpoise-ledger · 27 tokens

lexware-office-mcp CLAUDE.md

Claude Code instructions for benethos-hub/lexware-office-mcp, covering working guidelines for claude, golden rules, environment, project layout and how to add or change a tool.

benethos-hub/lexware-office-mcp · 3,769 tokens

ledger AGENTS.md

AGENTS.md instructions for eternal-roman/ledger, covering ledger, zero-skip, non-negotiable, output contract and commands (when the host loads this plugin).

eternal-roman/ledger · 517 tokens