Borrowing it
Nothing to install: this file belongs to alex-alecu/garden-desk. 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/alex-alecu/garden-desk/main/AGENTS.mdgit clone --depth 1 https://github.com/alex-alecu/garden-deskWrote 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/alex-alecu/garden-desk/agents-md)<a href="https://agentmods.dev/instructions/alex-alecu/garden-desk/agents-md"><img src="https://agentmods.dev/badge/instructions/alex-alecu/garden-desk/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/alex-alecu/garden-desk/agents-md"><img src="https://agentmods.dev/badge/instructions/alex-alecu/garden-desk/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 | $0.02445 | $0.02445 |
| Opus 5 | $0.01222 | $0.01222 |
| Sonnet 5 | $0.00489 | $0.00489 |
| Haiku 4.5 | $0.00245 | $0.00245 |
Grade A, and why
garden-desk 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 yesterday.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the control document for agents working in this repository. It is authoritative, followed by accepted ADRs, docs/IMPLEMENTATION_PLAN.md, and docs/DEVELOPMENT_WORKFLOW.md.
Top Priority: Minimum Work
This rule applies to Codex and all other agents. It controls all later repository documents, skills, and general completion rules. Only an explicit owner request can increase the work or verification scope.
- Make the smallest correct change for the requested outcome. Keep required security, privacy, authority, and active product contracts complete.
- Do not add adjacent refactors, speculative abstractions, defensive branches, options, fallbacks, compatibility layers, documentation, or cleanup.
- Default to zero new tests. A bug gets one reproducing test. A new boundary or business rule gets at most one focused test.
- Run only the smallest check that proves the changed behavior. Do not run the full unit suite, repository gate, milestone gate, real model, or physical microVM only for more confidence.
- A general skill, completion checklist, review request, commit, push, or pull request does not increase the scope. If a later instruction conflicts with this rule, use the smaller change and smaller verification set.
- Ask the owner before you add scope, tests, or verification beyond this rule.
A real run is any command or script that loads a real model or starts a physical microVM. This includes a focused real-model reproduction, pnpm test:m3:macos, pnpm test:m3:windows, pnpm test:gate --milestone 3, and wrappers that start them. First use source inspection, existing evidence, and focused deterministic tests. If a real run is still necessary, state the unresolved question, why cheaper evidence cannot answer it, the exact command or workload, and the number of planned invocations. Then ask the owner. A direct owner request for that workload is approval. Approval covers only the named commands and invocation count. A retry needs new approval.
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.
- yesterday Changed · +13 tokens per session b362053ab740
- 5d ago Changed · +13 lines · +376 tokens per session e89bcbd481c9
- 9d ago First seen · 76 lines · 2,056 tokens per session scan A 99ca2e2e74a5
garden-desk AGENTS.md is an instructions file published in the GitHub repository alex-alecu/garden-desk (6 stars, last pushed today), licensed Apache-2.0. It adds 2,445 tokens to every session, about $0.0122 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
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.