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/uxname/litestack/agents-mdgit clone --depth 1 https://github.com/uxname/LiteStackWhat 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 | $0.02269 | $0.02269 |
| Opus 5 | $0.01135 | $0.01135 |
| Sonnet 5 | $0.00454 | $0.00454 |
| Haiku 4.5 | $0.00227 | $0.00227 |
Grade A, and why
LiteStack 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — LiteStack (meta-project)
LiteStack is a full-stack boilerplate, not a runnable product. It bundles two real projects as git submodules and adds a thin coordination layer:
backend/— the backend project (liteend-go, its own repo). All server code.frontend/— the frontend project (litefront, its own repo). All browser code.- LiteStack (this repo) — owns no application code. It only coordinates: which project to touch, how the two connect, and how to commit across them.
This file is the entry point, not the whole manual. Read the file that matches your task — don't read them all.
Three boxes — put each change in the right one
| You are changing… | Go to | Why |
|---|---|---|
| API, database, business logic, background jobs, server-side GraphQL | backend/ |
it owns all server behaviour |
| UI, pages, routing, client state, styling, GraphQL the browser sends | frontend/ |
it owns everything in the browser |
| How the two fit together, this guide, cross-project skills, submodule pointers | LiteStack root | the meta-project only coordinates |
Rule of thumb: never put application code in the meta-project. Writing a resolver, a component or a migration means you are in the wrong folder — go into a submodule.
🔴 Start here
1. Read the retrospectives — learn from past mistakes
Before touching code, read every docs/retro/*.md. These record what went wrong in past
sessions, each ending in a one-line rule. Reading them first is how you avoid
repeating a mistake this project already paid for.
Do it in a separate thread so it doesn't bloat your working context. Spawn a subagent with this instruction:
Read every file in
docs/retro/*.md(skipREADME.mdandTEMPLATE.md). Return ONLY a deduplicated, compact list of the Rule — do this next time lines, grouped by area (backend / frontend / meta / cross). No file dumps, no narrative — just the rules.
Apply the returned rules to the work you are about to do. If docs/retro/ has no retro
files yet, there is nothing to read — continue.
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 · 146 lines · 2,269 tokens per session scan A 2f1d2bf81248
LiteStack AGENTS.md is an instructions file published in the GitHub repository uxname/LiteStack (2 stars, last pushed 10d ago), licensed MIT. It adds 2,269 tokens to every session, about $0.0113 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.