Borrowing it
Nothing to install: this file belongs to uxname/LiteStack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/uxname/LiteStack/main/AGENTS.mdgit clone --depth 1 https://github.com/uxname/LiteStackWrote 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/uxname/litestack/agents-md)<a href="https://agentmods.dev/instructions/uxname/litestack/agents-md"><img src="https://agentmods.dev/badge/instructions/uxname/litestack/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/uxname/litestack/agents-md"><img src="https://agentmods.dev/badge/instructions/uxname/litestack/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01225 | $0.01225 |
| Opus 5.5 | $0.00490 | $0.00490 |
| Sonnet 5.5 | $0.00245 | $0.00245 |
| Haiku 4.5 | $0.00122 | $0.00122 |
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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — LiteStack (meta-repo)
LiteStack is a full-stack boilerplate: two projects as git submodules — backend/
(liteend-go) and frontend/ (litefront), each its own repo — plus this thin layer that
only coordinates them. The product's requirements live here in docs/src (docc), and
a clickable prototype, protokit/, is a third submodule until a product removes it;
both are tied to the code by docc: tags
(ADR-0011).
Application code always lives in a submodule: a resolver, a component or a migration at
this root means you are in the wrong folder.
Every task
- Lessons first. If
docs/retro/holds dated files, read their "Rule" lines before touching code (how). - Go to the box that owns the change (table below) and read that sub-project's
AGENTS.md; it routes on to its.agents/*.md. Inside a sub-project, its rules win over this file. - Write to the standard. Code, tests, log lines and commit messages follow .agents/CODING_STANDARDS.md. Everything committed is English, whatever language the chat is in.
- A structural decision gets an ADR the same session, before the code lands — criteria in docs/adr/README.md. Before changing an area, read the ADRs that cover it.
- Done means the gate is green by exit status, never by the tail of its output:
task checkinbackend/,npm run checkinfrontend/, the hook in lefthook.yml here. There is no CI (ADR-0001): the hooks are the only gate, so every commit and push runs them in full —--no-verifyskips the whole guarantee.
Where to go
| Your task | Go to |
|---|---|
| API, database, business logic, jobs, server-side GraphQL | backend/AGENTS.md |
| UI, routing, client state, styling, GraphQL the browser sends | frontend/AGENTS.md |
| What the product must do: read or change a requirement — every edit reaches the prototype and the code tagged with it | docs/src, the docc skill; the rules in .agents/CROSS-PROJECT.md → "Requirements" |
| The prototype: a screen or a path on the simulated server | protokit/, the protokit skill; removing it: .agents/OPERATING-MODE.md |
| A feature on both sides | requirement first, then the prototype (while there is one), then backend — the full-stack-feature skill |
A back ↔ front seam (codegen, auth audience, CORS + WebSockets, requestId), or who owns a shared value |
.agents/CROSS-PROJECT.md |
| An env var both sides must agree on | docs/ENV-CONTRACT.md |
| Commit or push: template vs derived mode decides the remote | the commit skill; rules in .agents/OPERATING-MODE.md |
| Derive a real product from the template | .agents/DERIVE.md |
| A change to boundaries, protocols or components — the architecture model moves in the same change | docs/architecture/likec4/ (ADR-0003) |
| Deploy: local Docker, Dokploy, registry images | docs/DEPLOY.md |
| Observability: errors, logs, metrics, traces, product analytics, alerts — deploy the shared stack, connect a project, read its data | docs/observability/ |
| First-time setup of a clone, toolchain | README.md → "Getting started" |
| See what the frontend does at runtime (you have no browser) | frontend/.agents/OBSERVABILITY.md |
| Triage a failure from the logs | backend/docs/DEBUGGING.md, then the row above |
| Team process, or adding agent guidance or a skill | docs/TEAM.md |
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.
- 8d ago Changed · +6 lines · +207 tokens per session fd56ec9933d8
- 27d ago Changed · +1 lines · +49 tokens per session ab7dc8b947e7
- 29d ago Changed · -60 lines · -857 tokens per session b72d28f0a389
- 1mo ago Changed · -14 lines · -177 tokens per session fe8dda17da95
- 2mo ago Changed · +1 lines · +20 tokens per session d60946fa7068
- 2mo ago Changed · +1 lines · +12 tokens per session 4ae4273953ef
- 2mo ago Changed · +18 lines · +429 tokens per session a98f5cbb939e
- 2mo ago Changed · -36 lines · -727 tokens per session 0b4f6ed622cd
- 2mo 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 5d ago), licensed MIT. It adds 1,225 tokens to every session, about $0.0049 per session on Opus 5.5. 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.
LiteStack AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| LiteStack AGENTS.mduxname/LiteStack | Instructions file | 2 | 5d ago | MIT | A | 1,225 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |