dx-toolkit AGENTS.md

dx-toolkit AGENTS.md is an instructions file for Codex, OpenCode from youdotcom-oss/dx-toolkit. It costs 1,314 tokens per session, scanned A, original, MIT.

Maintainer instructions for You.com’s DX Toolkit, a Bun workspace containing developer packages and integrations. They describe repository workflow, minimal changes, and verification practices.

In plain words
What is it for?
Use them when maintaining the toolkit, especially for feature or bug work that should follow test-driven development, meaning tests are written before the implementation. The excerpt does not provide the full validation commands.
Why use it?
They help an agent make focused changes that fit the existing project and verify behavior before handing it over.

Instructions file for CodexOpenCode

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/youdotcom-oss/dx-toolkit/agents-md
Clone the repo
git clone --depth 1 https://github.com/youdotcom-oss/dx-toolkit

Made for: Codex, OpenCode.

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 dx-toolkit AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/youdotcom-oss/dx-toolkit/agents-md.svg)](https://agentmods.dev/instructions/youdotcom-oss/dx-toolkit/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/youdotcom-oss/dx-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/youdotcom-oss/dx-toolkit/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,314 This file is loaded in full into every session.
When invoked 1,314 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 $0.01314 $0.01314
Opus 5 $0.00657 $0.00657
Sonnet 5 $0.00263 $0.00263
Haiku 4.5 $0.00131 $0.00131

Measured 3d ago against content hash a93e6426c400, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dx-toolkit 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 3d 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 · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You.com DX Toolkit

Bun workspace for You.com developer packages and integrations.

Prefer the root README.md for user-facing setup. This file is for maintainers and coding agents working inside the repo.


Behavioral Guidelines

Think Before Coding

State assumptions. Surface tradeoffs. If multiple interpretations exist, present them instead of picking silently. If the repo already answers the question, use the codebase as the source of truth.

Simplicity First

Make the smallest change that solves the request. Do not add abstractions, fallbacks, or cleanup outside the task unless the change requires them.

Surgical Changes

Touch only the files the task needs. Match existing style. Remove imports or variables you orphan, but leave unrelated code alone.

Goal-Driven Execution

Turn work into verifiable outcomes. For behavior-changing feature or fix work, use the tdd skill and work in red-green-refactor slices. For docs-only or instruction-only edits, targeted doc validation is enough.

Validate Before Handoff

Run the narrowest checks that prove the change. If you skip executable tests, say why. Before trusting repo docs, verify the current state with rg, find, git log, or the relevant workflow/package files.


Repo Shape

Core Paths

Path Purpose
.agents/skills/ Canonical skill directory for this repo
packages/ Publishable packages
.github/workflows/ CI, review, publish, and security workflows
scripts/ Repo utilities and validation scripts
docs/ Supporting docs such as performance notes

Current Packages

  • packages/cli
  • packages/mcp
  • packages/ai-sdk-plugin
  • packages/langchain

Skill Surface

Prefer .agents/skills/ as the canonical agent workflow surface. Current shared skills:

  • grill-me for stress-testing plans or designs
  • optimize-agents-md for tightening repo instructions
  • review-guidelines for code review conventions
  • tdd for behavior-changing feature and fix work
  • typescript-lsp for type-aware TypeScript symbol exploration

Read the full file on GitHub · 203 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. 3d ago First seen · 203 lines · 1,314 tokens per session scan A a93e6426c400

Subscribe to this mod's changes

dx-toolkit AGENTS.md is an instructions file published in the GitHub repository youdotcom-oss/dx-toolkit (25 stars, last pushed 13d ago), licensed MIT. It adds 1,314 tokens to every session, about $0.0066 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.