Borrowing it
Nothing to install: this file belongs to aranlucas/ai-shopping-mcp. 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/aranlucas/ai-shopping-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/aranlucas/ai-shopping-mcpWrote 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/aranlucas/ai-shopping-mcp/agents-md)<a href="https://agentmods.dev/instructions/aranlucas/ai-shopping-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/aranlucas/ai-shopping-mcp/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/aranlucas/ai-shopping-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/aranlucas/ai-shopping-mcp/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 | $0.00545 | $0.00545 |
| Opus 5.5 | $0.00218 | $0.00218 |
| Sonnet 5.5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
ai-shopping-mcp 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
After making changes, run pnpm lint and fix all errors.
The views use @shadcn/lint in .oxlintrc.json. Use component variants and
badge tones for appearance; keep className for layout. The config documents
the spacing, carousel gutter, and skeleton rounding contracts. Shared UI
implementations in views/shared/ui/ own their styles and retain their existing
lint exclusion. Tailwind utility checks come from the shared Oxforge Tailwind preset in .oxlintrc.json.
Scripts: native first
Before adding a script file (scripts/, bin/, tools/, root *.sh|*.py|*.mjs) or a package script that runs one, take the first rung that works:
- A flag or subcommand of a tool the repo already uses (
<tool> --help). - Declarative config for that tool (
cloudflare.config.ts,vite.views.config.ts,drizzle.config.ts,oxfmt.config.ts,pnpm-workspace.yaml,vitest.config.ts). - A maintained plugin for that tool.
- A one-line package.json script that calls a native command.
- A test in the existing runner (Vitest), for anything that asserts.
- A custom script, only for behavior specific to this repo. Its first comment names the native rung it couldn't use and why. It has a test in the existing runner, and the PR that adds it quotes that comment.
Code: libraries first
Before hand-writing general-purpose code, use a well-maintained library: actively released, widely adopted, typed, and a fit for this stack. Reach for one already in the dependencies first. Write custom code for domain logic and for the glue no library covers. A PR that adds a dependency says why it was picked; a PR that hand-writes something a library covers names the library and why it didn't fit.
- Runtime validation → zod.
- Typed Kroger HTTP clients → openapi-fetch with the generated API types.
- D1 queries and schema definitions → drizzle-orm.
Tests worth maintaining
- Before adding a test, identify the specific behavior, a credible mistake it should catch, and an independently justified expected result.
- Prefer small, fast, reliable tests whose failures identify the broken behavior. Use integration/E2E tests for interactions isolated tests cannot establish.
- Do not reproduce implementation logic in assertions or mocks.
- Protect contracts, not incidental internal structure.
- Distinguish temporary development scaffolding from checks worth maintaining.
- Never delete or weaken a failing test just to make the suite pass.
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 Changed · +9 lines · +106 tokens per session 91fea4764236
- 19d ago Changed · +19 lines · +328 tokens per session d64c667ede5b
- 26d ago Changed · +6 tokens per session 34472ce1c965
- 1mo ago Changed · +7 lines ec1877200550
- 2mo ago Changed · -341 lines e3b0c44298fc
- 2mo ago First seen · 342 lines · 5,059 tokens per session scan A d4a3f1360ed6
ai-shopping-mcp AGENTS.md is an instructions file published in the GitHub repository aranlucas/ai-shopping-mcp (1 stars, last pushed 3d ago), licensed MIT. It adds 545 tokens to every session, about $0.0022 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.
ai-shopping-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ai-shopping-mcp AGENTS.mdaranlucas/ai-shopping-mcp | Instructions file | 1 | 3d ago | MIT | A | 545 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,649 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |