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/jozef-barton/the-kitchen/agents-mdgit clone --depth 1 https://github.com/jozef-barton/the-kitchenWrote 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/jozef-barton/the-kitchen/agents-md)<a href="https://agentmods.dev/instructions/jozef-barton/the-kitchen/agents-md"><img src="https://agentmods.dev/badge/instructions/jozef-barton/the-kitchen/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 | $0.04284 | $0.04284 |
| Opus 5 | $0.02142 | $0.02142 |
| Sonnet 5 | $0.00857 | $0.00857 |
| Haiku 4.5 | $0.00428 | $0.00428 |
Grade A, and why
the-kitchen 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 5d 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 — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository is intended to be completed autonomously by a coding agent such as Codex. Treat this file as the persistent execution charter and product/architecture specification. Update it whenever architecture decisions, constraints, or risks materially change.
Agent operating contract
- Read this file fully before changing code.
- Keep this file current. When an architectural or design decision changes, revise the affected section — do not maintain a dated completion ledger here.
- Work autonomously in small, verifiable increments until acceptance criteria are met.
- Do not stop at scaffolding. Leave the repository with a working vertical slice.
- Follow TDD where practical:
- write a failing test
- implement the minimum code
- make the test pass
- refactor safely
- Never disable tests, typechecks, lint rules, or security checks to move faster.
- The runtime architecture is browser-first. Do not restore Electron IPC or renderer assumptions as the primary path.
- Prefer structured schemas, explicit persistence models, and explicit failure states.
- Preserve a minimal, modern, internal-scrollable UI.
- If a better implementation detail is discovered, update this file before or alongside the code.
- Before declaring a phase complete, run the relevant verification command.
- When making changes, validate the local command path used by GitHub Actions before handoff; today that means running
pnpm ci:full(lint, typecheck, unit tests, security). End-to-end Playwright runs are not part of CI today; run them separately withpnpm exec playwright testwhen a change affects the e2e surface.
Product vision
Build a local-first Hermes frontend with:
- a browser-based chat interface with streaming markdown
- real Hermes profile and session browsing
- persisted local Spaces attached to sessions, with synchronized markdown/table/card content representations, extensible content-first tabs, and combined session+space workspaces
- jobs / cron visibility
- tool listing and reviewed tool execution history
- explicit disconnected, degraded, error, and empty states
- clean restart-safe persistence for hundreds of chats and thousands of messages
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.
- 5d ago First seen · 320 lines · 4,284 tokens per session scan A b4dc19bb65c6
the-kitchen AGENTS.md is an instructions file published in the GitHub repository jozef-barton/the-kitchen (59 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 4,284 tokens to every session, about $0.0214 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
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.