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/joachimchauvet/modernstack-saas/agents-mdgit clone --depth 1 https://github.com/joachimchauvet/modernstack-saasWrote 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.
[](https://agentmods.dev/instructions/joachimchauvet/modernstack-saas/agents-md)<a href="https://agentmods.dev/instructions/joachimchauvet/modernstack-saas/agents-md"><img src="https://agentmods.dev/badge/instructions/joachimchauvet/modernstack-saas/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00745 | $0.00745 |
| Opus 5 | $0.00373 | $0.00373 |
| Sonnet 5 | $0.00149 | $0.00149 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
modernstack-saas 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 6d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Guidelines
Core Technologies
- Frontend: SvelteKit ^2.30 with Svelte 5.
- Backend: Convex (database, serverless functions, real-time).
- Styling: Tailwind CSS v4 with shadcn-svelte components.
- Package Manager: pnpm.
Key Conventions
- Package Management: IMPORTANT: Always use
pnpmfor all package management operations (pnpm install,pnpm add, etc.). YOU MUST NOT usenpmoryarn. - Backend Development: All backend logic is in the
convex/directory. - File-based Routing: Use SvelteKit's file-based routing system in
src/routes/. - Shared Code: Place reusable code in
src/lib/. - Use
git mvinstead of creating a new file and deleting the old one or justmvif moving existing files that have been committed already. - Do not commit changes on your own. Humans will do that after approval.
- Before making edits in files involving Svelte 5 or Convex, make sure you read the svelte/overview.md and convex.md documentation or you have it in your context.
- Most of the time,
pnpm devandpnpm convex devwill be running in another terminal already. No need to run those commands yourself.
Svelte Best Practices
High-Level Principles
- Write concise, technical, and accurate Svelte 5/SvelteKit code.
- Leverage SSR and SSG.
- Prioritize performance and minimal JavaScript.
- Use descriptive variable names and follow official conventions.
Code Style and Structure
- Prefer functional and declarative patterns.
- Avoid code duplication through iteration and modularization.
- Structure files logically: component logic, markup, styles, helpers, types.
TypeScript Usage
- Use TypeScript for all code.
- Prefer interfaces over types.
- Avoid enums; use
as constobjects. - Enable strict mode.
- Don't use Any as type. That's not precise or clear enough.
Available Documentation
Refer to the following documents for detailed information on specific topics. These are your primary source of truth for the project. Always double-check when in doubt.
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.
- 6d ago First seen · 59 lines · 745 tokens per session scan A 2ef352eb67e6
modernstack-saas AGENTS.md is an instructions file published in the GitHub repository joachimchauvet/modernstack-saas (133 stars, last pushed 1mo ago), licensed MIT. It adds 745 tokens to every session, about $0.0037 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
svelteflare AGENTS.md
Instructions for pinebasedev/svelteflare, covering agent rules for this project, theme fidelity (non-negotiable), talking to the user and deep-dive skills.
nextjs-expo-saas-starter CLAUDE.md
Instructions for brainbytes-dev/nextjs-expo-saas-starter, covering claude.md, project overview, monorepo structure, commands and database (from root or packages/db).
tanstack-start-template AGENTS.md
AGENTS.md instructions for dyeoman2/tanstack-start-template, covering tanstack start agent guide, core philosophy, architecture, golden rules and key patterns.
Vue CLAUDE.md
Claude Code instructions for pierreb-devkit/Vue, covering devkit vue stack - claude code setup, 🔓 public oss repo — no downstream references, quick start, architecture and casl abilities & organizations.
Vue copilot-instructions.md
Copilot instructions for pierreb-devkit/Vue, covering devkit vue - copilot instructions, preflight, canonical commands, available prompts and always-on guardrails.
Vue AGENTS.md
AGENTS.md instructions for pierreb-devkit/Vue, covering devkit vue stack - agent guide, mission, codex prompt routing and workflow rules.