Borrowing it
Nothing to install: this file belongs to smaramwbc/statewave-grounded-shop-assistant. 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/smaramwbc/statewave-grounded-shop-assistant/main/AGENTS.mdgit clone --depth 1 https://github.com/smaramwbc/statewave-grounded-shop-assistantWrote 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/smaramwbc/statewave-grounded-shop-assistant/agents-md)<a href="https://agentmods.dev/instructions/smaramwbc/statewave-grounded-shop-assistant/agents-md"><img src="https://agentmods.dev/badge/instructions/smaramwbc/statewave-grounded-shop-assistant/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/smaramwbc/statewave-grounded-shop-assistant/agents-md"><img src="https://agentmods.dev/badge/instructions/smaramwbc/statewave-grounded-shop-assistant/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 | $0.01050 | $0.01050 |
| Opus 5 | $0.00525 | $0.00525 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
statewave-grounded-shop-assistant 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 9d 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — guide for contributors and coding agents
A short orientation for humans and AI coding agents (GitHub Copilot, Claude, Cursor, …) working in statewave-grounded-shop-assistant — a runnable Statewave use case in TypeScript: a grounded product advisor and support assistant for a fictional store, plus an internal Ops Assistant that tracks and closes content gaps.
Setup, build, test
Node 18+ (CI runs 18, 20 and 22). No API key is required.
npm ci
npm run build # tsc -b across server + packages
npm test # tsx --test across packages/*/test and server/test
npm run seed # ingest the catalog + service content
npm run dev # storefront, ops console and APIs on http://localhost:4000
GET /healthz reports completionMode, which is the quickest way to tell
whether you are on the offline responder or a real LLM gateway.
Layout
server/src/routes/—chat.ts(shopper-facing) andops.ts(internal console).server/src/middleware/— ops auth and rate limiting.packages/chat-core/— prompt assembly, shared types, and the completion backends (offline.ts,openrouter.ts,litellm.ts).packages/statewave-core/— the store/retrieval layer.packages/chat-widget/— the embeddable widget (built vianpm run build:widget).public/— storefront (index.html) and ops console (ops.html).
Conventions
- The demo must stay clone-and-run with no API key. The offline
rule-based responder is the default path, and CI asserts it by booting the
server with an empty environment and checking
"completionMode":"offline-rule-based". Don't make a provider key a precondition for the demo working. - Answers stay grounded. Every shopper-facing answer is backed by retrieved evidence and cited. When evidence is missing the assistant says so and logs a gap — it must never fill the hole by guessing.
- Any OpenAI-compatible gateway should work. Keep provider wording generic; don't hard-code an assumption that one specific vendor is required.
- Ops routes are protected by
OPS_API_KEY. If it is unset the server leaves/api/ops/*open and logs a loud warning on boot. Keep that warning loud, and keep the routes closed by default wherever this is deployed beyond localhost. npm run buildmust stay clean. The demo executes throughtsx, so type errors won't stopnpm run dev— CI runstsc -bto catch them; run it locally before pushing.- Keep claims accurate and modest. This is a demonstration use case; don't describe it as a production deployment.
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.
- 9d ago First seen · 82 lines · 1,050 tokens per session scan A 847c91a70dea
statewave-grounded-shop-assistant AGENTS.md is an instructions file published in the GitHub repository smaramwbc/statewave-grounded-shop-assistant (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,050 tokens to every session, about $0.0052 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.