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/.claude/skills/baguette-implement-feature/SKILL.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/skills/tddworks/baguette/baguette-implement-feature)<a href="https://agentmods.dev/skills/tddworks/baguette/baguette-implement-feature"><img src="https://agentmods.dev/badge/skills/tddworks/baguette/baguette-implement-feature/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/skills/tddworks/baguette/baguette-implement-feature"><img src="https://agentmods.dev/badge/skills/tddworks/baguette/baguette-implement-feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 335 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 439 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00192 | $0.05758 |
| Opus 5 | $0.00096 | $0.02879 |
| Sonnet 5 | $0.00038 | $0.01152 |
| Haiku 4.5 | $0.00019 | $0.00576 |
Grade A, and why
app-implement-feature 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 10d 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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Implement a feature in baguette
baguette is a CLI + WebSocket server, not a SwiftUI app. There is no
ViewModel layer, no async actors in the input path — gestures are
synchronous Bool-returning calls into the @Mockable Input
abstraction whose only concrete adapter is IndigoHIDInput. The frontend
is hand-written vanilla JS IIFEs (no bundler) that talk to the server
via one WebSocket per stream.
Naming abstractions: every @Mockable protocol in this codebase is
a domain noun for the role it plays — Input, Screen,
Accessibility, LogStream, DeviceHost, Subprocess, Chromes,
Simulators. The pattern-label suffixes "Port" / "Service" /
"Manager" never appear. If you reach for XxxPort, the abstraction
isn't named yet — keep going until the noun describes what the thing
is in the domain.
Repository is allowed — but only for aggregate CRUD, and only
named as the collection noun. A protocol that is genuinely a DDD
collection-like interface for an aggregate root (load / save / delete
by identity) takes the plural of the aggregate — Simulators,
Chromes, Books, Orders — not BookRepository / OrderRepo. The
suffix Repository is still banned; the role (aggregate persistence)
is the legitimate case the plural-noun convention already covers.
If your protocol isn't aggregate persistence (it's an adapter, an
event source, a process boundary, …), the repository carve-out
doesn't apply — pick a role-noun like Subprocess / LogStream
instead.
Read CLAUDE.md — the "TDD is non-negotiable" gate,
the naming rule, and the orchestrator-vs-collaborator split for adapters
that wrap 3rd-party I/O are authoritative there. This skill describes
the process of adding features that fit those rules.
Workflow
┌──────────────────────────────────────────────────────────────┐
│ 0. ARCHITECTURE DESIGN (user approval required) │
│ wire shape · domain types · adapter split · risks │
├──────────────────────────────────────────────────────────────┤
│ 1. DOMAIN TDD │
│ value types · pure static factories · @Mockable │
│ abstractions · rich-domain methods │
├──────────────────────────────────────────────────────────────┤
│ 2. INFRASTRUCTURE TDD │
│ concrete adapter impl. If the adapter wraps 3rd-party I/O │
│ and the call is conversational, introduce a domain-named │
│ `@Mockable` collaborator (`Subprocess`) and split the │
│ orchestrator from the thin `HostXxx` impl. │
├──────────────────────────────────────────────────────────────┤
│ 3. WIRING │
│ register on GestureRegistry (gestures only) · CLI │
│ subcommand · WS route · browser IIFE (when user-facing) │
├──────────────────────────────────────────────────────────────┤
│ 4. DOCS + CHANGELOG (mandatory before reporting "done") │
│ create or update `docs/features/<feature>.md` · │
│ update `CHANGELOG.md` Unreleased section · │
│ update `skills/baguette/` references when CLI / wire │
│ surface changed │
└──────────────────────────────────────────────────────────────┘
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 442 lines · 192 tokens per session scan A ba2cf64b0f77
app-implement-feature is a skill published in the GitHub repository tddworks/baguette (1,749 stars, last pushed yesterday), licensed Apache-2.0. It adds 192 tokens to every session and 5,758 once invoked, about $0.0010 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 skills, from other repositories
swift-architecture-skill
Swift iOS architecture guidance and playbooks for MVVM, MVI, TCA, Clean Architecture, VIPER, MVP, Coordinator, and Reactive patterns. Use when designing, implementing, refactoring, or reviewing the architecture of a SwiftUI or UIKit feature, module, or codebase.
swiftui-view-refactor
Refactor a SwiftUI view file for consistent property ordering, MV patterns, view model handling, and Observation usage; split an oversized body via same-file computed view properties or MARK-organized extensions. Use when asked to clean up a SwiftUI view's layout, reorder its properties, or standardize…
watchos-development
Use when building or reviewing a watchOS app or WatchKit extension — app structure and independent-app configuration, Watch Connectivity / companion-app sync, complications and Smart Stack widgets, controls or Live Activities on watch, background refresh and networking limits, watchOS-specific SwiftUI design…
cmp-upgrade
Migrate an existing Kotlin/Compose Multiplatform (CMP/KMP) project to the next PROVEN-GREEN dependency version set. Use this when the user wants to upgrade Kotlin, KSP, Compose Multiplatform, Room, AGP, Koin, or Ktor versions in a KMP project, bump their KMP dependencies, or asks "upgrade kotlin/compose/KMP versions"…
xcode-build-fixer
Apply approved Xcode build optimization changes following best practices, then re-benchmark to verify improvement. Use when a developer has an approved optimization plan from xcode-build-orchestrator, wants to apply specific build fixes, needs help implementing build setting changes, script phase guards, source-level…
xcode-build-orchestrator
Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval, delegating approved fixes to xcode-build-fixer, and re-benchmarking after changes. Use when a developer wants an end-to-end build optimization workflow, asks to speed…