Baguette is a command-line tool and web interface for controlling iOS simulators without opening Xcode or Simulator.app. Developers and agents use it to boot devices, stream screens, send touch and hardware input, inspect accessibility data and logs, and capture screenshots or recordings. The catalogue includes skills, instructions, and a plugin for operating Baguette.
Borrowing it
Nothing to install: this file belongs to tddworks/baguette. 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/tddworks/baguette/main/AGENTS.mdgit clone --depth 1 https://github.com/tddworks/baguetteWrote 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/tddworks/baguette/agents-md)<a href="https://agentmods.dev/instructions/tddworks/baguette/agents-md"><img src="https://agentmods.dev/badge/instructions/tddworks/baguette/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/tddworks/baguette/agents-md"><img src="https://agentmods.dev/badge/instructions/tddworks/baguette/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 | $0.02891 | $0.02891 |
| Opus 5.5 | $0.01156 | $0.01156 |
| Sonnet 5.5 | $0.00578 | $0.00578 |
| Haiku 4.5 | $0.00289 | $0.00289 |
Grade A, and why
baguette 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 7d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for every coding agent working in this repository (Claude Code reads this file too). It holds the rules that apply to every task; everything else is one link away, loaded only when relevant.
TDD is non-negotiable (read this first)
You MUST write a failing test before writing any production code. This rule overrides every other instinct, including "the change is small", "it's just a one-liner", "I'll add the test after". If you catch yourself opening a file under Sources/Baguette/ before a test under Tests/BaguetteTests/ exists and fails, stop and reverse course.
Pre-implementation gate — before editing anything in Sources/ (Domain value type, Domain abstraction, Infrastructure adapter, App-layer command), you must have done all of the following in order:
- Stated the user-facing behaviour in one sentence using domain language, shaped
should <outcome> [when <situation>]. Good: "should land a tap on the simulator as a finger down, hold and up", "should describe no UI when no app is frontmost". Bad: "IndigoHIDInput calls sendMouse twice" — an interaction, not a behaviour. - Written a
@TestinTests/BaguetteTests/<Context>/<Suite>.swiftthat asserts the expected outcome. The step-1 sentence is the test name, verbatim — no method/type names or mechanism verbs (returns,fires,calls); pair each happy path with itswhen …twin; rename old ones on touch. Prefer state assertions (#expect(filter.argv == [...]),#expect(node.frame == ...)) over interaction assertions. For@Mockableabstractions, use the auto-generatedMockXxx(given(input).tap(...).willReturn(true)); plain test doubles backed by Mockable are the canonical mocking style — never mock the value type itself. - Run the test and observed it fail —
swift test --filter "<SuiteName>"for the fastest loop. A compile error counts as red only when the failing symbol is the one the test names (KeyboardKey.from(wireCode:)doesn't exist yet); a generic build error somewhere else doesn't. - Reported the red result back to the user (one line is fine: "test
should map a letter key onto HID page 7fails:KeyboardKey.from is not a member").
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.
- 7d ago Changed · +1 lines · +5 tokens per session 9500613fb12f
- 25d ago Changed · +40 tokens per session b56f00b90c86
- 1mo ago Changed · -37 lines · -692 tokens per session 7f5085706fc6
- 2mo ago First seen · 136 lines · 3,538 tokens per session scan A 6f03c578430e
baguette AGENTS.md is an instructions file published in the GitHub repository tddworks/baguette (2,269 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,891 tokens to every session, about $0.0116 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 2026-08-30.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
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.