ourgroceries-mcp: Instructions file for Codex

AGENTS.md

ourgroceries-mcp AGENTS.md is an instructions file for Codex, OpenCode from sargue/ourgroceries-mcp. It costs 1,435 tokens per session, scanned A, original, from a forked repository, MIT.

Repository instructions for `ourgroceries-mcp`, a TypeScript MCP server that connects coding tools to the OurGroceries service. They describe the code layout, data model, coding conventions, and development commands.

In plain words
What is it for?
Use them when installing dependencies, building, testing, linting, or modifying the server, command-line tool, authentication, configuration, or OurGroceries client.
Why use it?
They give an agent the project-specific rules needed to change the repository consistently and run its checks correctly.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is sargue/ourgroceries-mcp's own configuration. It tells Codex and OpenCode how to work on ourgroceries-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ourgroceries-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sargue/ourgroceries-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.

Copy the file
curl -O https://raw.githubusercontent.com/sargue/ourgroceries-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/sargue/ourgroceries-mcp

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for ourgroceries-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sargue/ourgroceries-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/sargue/ourgroceries-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/sargue/ourgroceries-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sargue/ourgroceries-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.

agentmods 80×15 button for ourgroceries-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/sargue/ourgroceries-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sargue/ourgroceries-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,435 This file is loaded in full into every session.
When invoked 1,435 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01435 $0.01435
Opus 5 $0.00718 $0.00718
Sonnet 5 $0.00287 $0.00287
Haiku 4.5 $0.00144 $0.00144

Measured 9d ago against content hash a4fbc5678e27, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ourgroceries-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 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.

AGENTS.md · 82 lines

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.

Repository Guidelines

Project Structure & Module Organization

This is a TypeScript MCP server package. Source files live in src/ and compile to build/, which is ignored by Git and included in the published npm package. Key modules are:

  • src/index.ts: MCP server, tool definitions, and tool-to-client dispatch.
  • src/cli.ts: ourgroceries-mcp command, login/logout workflow, JSON CLI commands, and no-arg server startup.
  • src/client.ts: OurGroceries HTTP client and request envelope construction.
  • src/auth.ts: OurGroceries sign-in and team ID extraction.
  • src/config.ts: credential config path, load, and save helpers.
  • src/version.ts: package version loading for the MCP server and CLI.

Tests live in tests/ and compile to build-test/, which is ignored by Git.

Build, Test, and Development Commands

  • npm install: install dependencies from package-lock.json.
  • npm ci: install the exact locked dependency set for verification or CI.
  • npm run build: run tsc and emit ESM output plus declarations into build/.
  • npm test: compile tests with tsconfig.test.json and run Node's built-in test runner.
  • npm run lint: run ESLint.
  • npm run format:check: verify Prettier formatting.
  • npm run check: run build, lint, format check, and tests.
  • npm run watch: run TypeScript in watch mode during local development.
  • node build/cli.js login: authenticate and write local credentials after building.
  • node build/cli.js logout: remove saved local credentials after building.
  • node build/cli.js get-lists: print visible shopping-list summaries without item arrays.
  • node build/cli.js get-categories: print item categories extracted from the hidden category list.
  • node build/cli.js get-settings: print account settings and list schema version.
  • node build/cli.js get-active-items --list-id LIST_ID: print active items for a shopping list.
  • node build/cli.js get-crossed-off-items --list-id LIST_ID [--search TEXT] [--crossed-off-after DATE] [--crossed-off-before DATE] [--sort-by crossedOffAt|name] [--asc|--desc] [--limit N] [--offset N]: print filtered crossed-off item history.
  • node build/cli.js resolve-item-to-add --query TEXT [--list-id LIST_ID] [--limit N]: resolve natural-language or partial item text against the master catalog and shopping history, including likely target-list suggestions when no list ID is provided.
  • node build/cli.js add-item --list-id LIST_ID --value VALUE [--note NOTE]: add an item and print JSON success.
  • node build/cli.js remove-item --list-id LIST_ID --item-id ITEM_ID: remove an item and print JSON success.
  • node build/cli.js update-item --list-id LIST_ID --item-id ITEM_ID --new-value VALUE [--category-id CATEGORY_ID] [--note NOTE] [--star 0|1]: update an item and print JSON success.
  • node build/cli.js cross-off-item --list-id LIST_ID --item-id ITEM_ID: cross off an item and print JSON success.
  • node build/cli.js uncross-item --list-id LIST_ID --item-id ITEM_ID: uncross an item and print JSON success.
  • node build/cli.js: after building and configuring credentials, start the MCP server over stdio.

Read the full file on GitHub · 82 lines

Changes

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.

  1. 9d ago First seen · 82 lines · 1,435 tokens per session scan A a4fbc5678e27

Subscribe to this mod's changes

ourgroceries-mcp AGENTS.md is an instructions file published in the GitHub repository sargue/ourgroceries-mcp (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,435 tokens to every session, about $0.0072 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

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).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens