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/henkas/orderfood/agents-mdgit clone --depth 1 https://github.com/henkas/orderfoodWrote 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/henkas/orderfood/agents-md)<a href="https://agentmods.dev/instructions/henkas/orderfood/agents-md"><img src="https://agentmods.dev/badge/instructions/henkas/orderfood/agents-md.svg" alt="Measured on agentmods" 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 | $0.00586 | $0.00586 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
orderfood 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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
This repository is currently documentation-first. The checked-in files live under docs/superpowers/:
docs/superpowers/specs/holds approved design specs.docs/superpowers/plans/holds implementation plans and task breakdowns.
The spec defines the intended monorepo layout once scaffolded:
packages/shared/for normalized types and errorspackages/ubereats-client/andpackages/thuisbezorgd-client/for platform clientspackages/mcp-server/for MCP tool handlerstools/api-capture/for mitmproxy capture and parsing utilitiesdocs/api-reference/for generated endpoint notes
Build, Test, and Development Commands
No runnable workspace files are checked in yet, so there is nothing to build or test from this snapshot alone. The implementation plan expects a pnpm workspace with these root commands after bootstrap:
pnpm installinstalls shared dev dependencies.pnpm buildbuilds all workspace packages.pnpm testruns all Vitest suites.pnpm typecheckruns strict TypeScript checks.
Use pnpm --version first; the plan expects pnpm 8+.
Coding Style & Naming Conventions
Follow the conventions defined in the design and plan docs:
- TypeScript uses ESM,
NodeNext, andstrict: true. - Prefer small focused modules such as
client.ts,auth.ts,mappers.ts, andtypes.ts. - Keep shared domain models in
packages/shared/src/. - Use kebab-case for package directories and lowercase filenames.
- Use clear exported type names such as
Restaurant,Cart, andPlatformClient.
Testing Guidelines
Vitest is the planned test framework. Place tests beside each package in a tests/ directory and name files *.test.ts, for example packages/shared/tests/errors.test.ts.
Add unit tests for new parsing, mapping, and error-handling code. Run pnpm test and pnpm typecheck before opening a PR.
Commit & Pull Request Guidelines
Local .git history is not present in this workspace snapshot, so no repository-specific history can be inspected. Use the commit style already shown in the implementation plan, for example chore: bootstrap pnpm workspace.
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.
- 4d ago First seen · 54 lines · 586 tokens per session scan A 63cac63b2297
orderfood AGENTS.md is an instructions file published in the GitHub repository henkas/orderfood (2 stars, last pushed 2mo ago), licensed MIT. It adds 586 tokens to every session, about $0.0029 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
storagesdk AGENTS.md
Instructions for storagesdk/storagesdk, covering agents.md, what this is, locked design decisions, working principles and gates.
protocol-launcher AGENTS.md
Instructions for zhensherlock/protocol-launcher, covering agents.md - protocol launcher, repo shape, commands that matter, protocol library and docs.
protocol-launcher CLAUDE.md
Instructions for zhensherlock/protocol-launcher, covering claude.md - protocol launcher and claude-specific behavior.
spectral CLAUDE.md
Instructions for spectral-mcp/spectral, covering spectral — project specification, style preferences, development environment, what this project is and project structure.
mitmproxy-mcp CLAUDE.md
Claude Code instructions for mplogas/mitmproxy-mcp, covering claude.md, project, architecture, safety model and build and run.
avasfood-mcp AGENTS.md
AGENTS.md instructions for Rayyan011/avasfood-mcp, covering avas food agent instructions, ordering discipline, budgeting and privacy.