Borrowing it
Nothing to install: this file belongs to baijum/ukulele-companion. 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/baijum/ukulele-companion/main/.cursor/skills/large-feature-harness/SKILL.mdgit clone --depth 1 https://github.com/baijum/ukulele-companionWrote 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/baijum/ukulele-companion/large-feature-harness)<a href="https://agentmods.dev/skills/baijum/ukulele-companion/large-feature-harness"><img src="https://agentmods.dev/badge/skills/baijum/ukulele-companion/large-feature-harness/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/baijum/ukulele-companion/large-feature-harness"><img src="https://agentmods.dev/badge/skills/baijum/ukulele-companion/large-feature-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.01191 |
| Opus 5 | $0.00036 | $0.00596 |
| Sonnet 5 | $0.00014 | $0.00238 |
| Haiku 4.5 | $0.00007 | $0.00119 |
Grade A, and why
large-feature-harness 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 12d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Large Feature Harness (Planner-Generator-Evaluator)
A three-phase workflow for tasks too large for a single agent pass. Based on Anthropic's harness design pattern — separates planning, generation, and evaluation so each phase has focused context and the evaluator cannot be influenced by the generator's reasoning.
When to Use
- Feature spanning 3+ screens or ViewModels
- Refactors touching 10+ files
- New feature areas requiring both Android and iOS implementation
- Multi-hour autonomous coding sessions
For single-file changes or small bug fixes, skip this and work directly.
Phase 1: Plan
Produce a structured specification before writing any code.
-
Gather context. Read the relevant existing code, AGENTS.md, and any applicable
.cursor/rules/*.mdcfiles. Use the architecture map (docs/architecture-map.md) to understand navigation and ViewModel mappings. -
Write a plan document. Create
docs/plans/<feature-name>.mdwith:# Feature: <name> ## Goal One paragraph describing the user-visible outcome. ## Screens / Components - [ ] <ScreenName> — backed by <ViewModel>, what it does - [ ] ... ## Shared Domain Changes - [ ] <class/function> in shared/src/commonMain/... ## Data Model Changes - [ ] <enum/data class> changes ## Acceptance Criteria - [ ] Criterion 1 (testable) - [ ] Criterion 2 (testable) - [ ] ... ## Sprint Order 1. Sprint 1: <scope> — what "done" looks like 2. Sprint 2: <scope> — what "done" looks like 3. ... -
Review with user. Present the plan and get confirmation before proceeding.
Phase 2: Generate (Sprint Loop)
Implement one sprint at a time. Each sprint produces a buildable, testable increment.
For each sprint:
- Read the plan to understand the current sprint scope.
- Implement the code changes for this sprint only.
- Run automated checks after implementation:
./gradlew assembleDebug # Android builds ./gradlew testDebugUnitTest # Unit tests pass ./gradlew :shared:jvmTest # Shared tests pass - Update the plan — check off completed items, note any deviations.
- Commit the sprint with message:
Add: <feature> — sprint N (<scope>).
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.
- 12d ago First seen · 148 lines · 71 tokens per session scan A 0d1a4eea97fd
large-feature-harness is a skill published in the GitHub repository baijum/ukulele-companion (14 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,191 once invoked, about $0.0004 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
sceneview-ios
Build 3D and AR apps on Apple platforms (iOS, macOS, visionOS) with SceneViewSwift — the SwiftUI wrapper around RealityKit. Use whenever the user asks for "3D in SwiftUI", "AR with ARKit in SwiftUI", a model viewer for iOS, or any Apple-platform 3D/AR app where the dependency is the SceneViewSwift Swift Package from…
sceneview-web
Build 3D and WebXR (AR/VR) experiences in the browser with SceneView for Web — Filament.js (WebGL2/WASM) wrapped in a Kotlin/JS DSL and a plain-JavaScript API on window.sceneview. Use whenever the user asks for "3D in the browser", "a web model viewer", "WebXR AR/VR", or any browser 3D/AR app where the dependency is…
sceneview
Build 3D and AR apps with the SceneView SDK in Jetpack Compose, SwiftUI (iOS/macOS/visionOS via SceneViewSwift), Web (Filament.js), Flutter and React Native. Use whenever the user asks for "3D in Compose", "AR with ARCore in Compose", a model viewer, or any cross-platform 3D/AR app where the dependency is…
to-plan
Use when one ready GitHub issue or an in-chat task needs a repository-aware implementation plan for a later implementation workflow.
compose-ui-testing-patterns
Use when writing or reviewing Jetpack Compose UI tests, screenshot tests, previews, semantics assertions, fake image loading, keyboard input, focus assertions, interaction state (hover/pressed/focused), or tests for plain state-driven UI composables.
compose-animations
Use when writing or reviewing Jetpack Compose motion: visibility enter/exit, animating one property toward a target, color or size transitions, multiple properties from one state, switching composable content, or choosing between AnimatedVisibility, animateAsState, rememberTransition, AnimatedContent, and Crossfade.