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.
npx agentmods add instructions/jakejarvis/domainstack.io/agents-mdgit clone --depth 1 https://github.com/jakejarvis/domainstack.ioWhat 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 | $0.04784 | $0.04784 |
| Opus 5 | $0.02392 | $0.02392 |
| Sonnet 5 | $0.00957 | $0.00957 |
| Haiku 4.5 | $0.00478 | $0.00478 |
Grade A, and why
domainstack.io 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.
How it starts
The opening of the file, as written. The whole thing — 554 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Pre-Commit Checklist
CRITICAL: Before declaring victory on any task and before committing to git, the following four commands must pass with NO WARNINGS:
pnpm lint— Must pass with zero warningspnpm fmt:check— Must pass with zero warningspnpm check-types— Must pass with zero warningspnpm test— Must pass with zero warnings
Do not proceed with commits until all four checks are clean.
Commands
Development
pnpm dev— Start Next.js dev server at http://localhost:3000pnpm build— Compile production bundlepnpm check-types— Runtsc --noEmitfor type diagnostics
Linting & Formatting
pnpm lint— Run oxlint lintpnpm fmt— Apply oxfmt formatting
Testing
pnpm test— Run all tests oncepnpm test path/to/file.test.ts— Run a single test filepnpm test -t "test name"— Run tests matching a patternpnpm test:coverage— Run tests with coverage report
Database
pnpm db:generate— Generate Drizzle migrationspnpm db:push— Push schema to databasepnpm db:migrate— Apply migrationspnpm db:studio— Open Drizzle Studio
Code Style
General
- TypeScript only,
strictenabled - 2-space indentation (oxfmt enforces)
- Prefer small, pure modules
- Node.js >= 24 required
Naming Conventions
- Files/folders: kebab-case (
user-settings.ts) - React components: PascalCase exports (
UserSettings) - Helpers/hooks: camelCase named exports (
useUserSettings)
Imports
- Use
@/...path aliases for app-specific imports - Import shared UI components from
@domainstack/ui/*(e.g.,@domainstack/ui/button) - oxfmt auto-organizes imports on save
- Client components must start with
"use client"
Types
- Shared domain types in
@domainstack/typespackage - Enum const arrays (primitives) in
@domainstack/constants(Drizzle pgEnums derive from these) - Do NOT use Zod for simple enums or internal database types
- Import types from
@domainstack/types
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.
- 2d ago First seen · 554 lines · 4,784 tokens per session scan A 16113fa3ff9a
domainstack.io AGENTS.md is an instructions file published in the GitHub repository jakejarvis/domainstack.io (285 stars, last pushed 2d ago), licensed MIT. It adds 4,784 tokens to every session, about $0.0239 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.
Other instructions, from other repositories
20i-MCP CLAUDE.md
Instructions for Cbrown35/20i-MCP, covering claude.md, project overview, development commands, build & development and testing & analysis.
core CLAUDE.md
Claude Code instructions for module-federation/core, covering claude task parallelization & development guidelines, core principles, maximum parallelization strategy, universal parallel task patterns and for any codebase task.
Codex-Skills AGENTS.md
Instructions for TheGoat395/Codex-Skills, covering repository operating notes, required checks, evidence rules and change hygiene.
souls-directory CLAUDE.md
Instructions for thedaviddias/souls-directory, covering claude.md — project context for ai assistants, project overview, tech stack, critical rules and database is convex.
nextarter-tailwind AGENTS.md
AGENTS.md instructions for agustinusnathaniel/nextarter-tailwind, covering next.js: always read docs before coding, ai agent guidance: nextarter-tailwind, 1. mental model for agents, implementation delegation and tooling strategy.
agentgram CLAUDE.md
Instructions for agentgram/agentgram, covering claude.md — agentgram development guide, project overview, tech stack, monorepo structure and core architecture patterns.