@mmerterden/multi-agent-pipeline 20.2.1 → 20.3.0

package/pipeline/skills/skills-index.md

@@ -3,25 +3,23 @@
 > Auto-generated by `pipeline/scripts/build-skills-index.mjs`  -  do not hand-edit.
 > Regenerate with `node pipeline/scripts/build-skills-index.mjs`.
 
-**219 skills** across 2 groups.
+**218 skills** across 2 groups.
 
 | Group | Name | Platform | Description |
 |-------|------|----------|-------------|
-| external | `accessibility-compliance-accessibility-audit` |  -  | You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct audits, i |
-| external | `agent-introspection-debugging` |  -  | Structured self-debugging for an agent that is stuck, looping, or failing repeatedly. Replaces blind re-prompting with capture -> diagnose - |
-| external | `agentflow` |  -  | Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code |
+| external | `accessibility-compliance-accessibility-audit` |  -  | WCAG 2.2 AA audit process for web, iOS and Android: scope, automated scans, screen-reader and keyboard checks, severity, report, retest. Use |
+| external | `agent-introspection-debugging` |  -  | Structured self-debugging for an agent that is stuck, looping, or failing repeatedly. Replaces blind re-prompting with capture, diagnose, co |
 | external | `alarmkit` |  -  | Implement AlarmKit alarms and countdown timers for iOS and iPadOS with Lock Screen, Dynamic Island, StandBy, and paired Apple Watch system U |
 | external | `android-architecture` |  -  | Design and implement Clean Architecture with multi-module structure on Android. Covers domain/data/presentation layers, Hilt dependency inje |
 | external | `android-build-quality-gates` |  -  | Encode Android module and quality rules as build-failing Gradle tasks: layer-dependency checks, coverage floors, a Compose-stability gate, l |
 | external | `android-datastore` |  -  | Typed Jetpack DataStore as the modern SharedPreferences replacement: Preferences and typed stores, serializer-layer encryption, and migratio |
 | external | `android-design-tokens-codegen` |  -  | A single-source JSON to typed-Kotlin codegen pipeline for design tokens, UI-test ids, analytics events and deeplink manifests, run as Gradle |
-| external | `android-jetpack-compose-expert` |  -  | Expert guidance for building modern Android UIs with Jetpack Compose, covering state management, navigation, performance, and Material Desig |
-| external | `android-mvi-viewmodel` |  -  | A reusable generic BaseViewModel<State, Intent, Event> for MVI Compose apps: StateFlow state, one-shot events over a rendezvous Channel, a s |
+| external | `android-jetpack-compose-expert` |  -  | Compose runtime expertise: state ownership, recomposition and stability, side-effect APIs, lazy lists, modifier order, Modifier.Node. Use wh |
+| external | `android-mvi-viewmodel` |  -  | A reusable generic BaseViewModel typed on State, Intent and Event for MVI Compose apps: StateFlow state, one-shot events over a rendezvous C |
 | external | `android-performance` |  -  | Optimize Android app performance with Baseline Profiles for startup, Compose stability annotations (@Stable, @Immutable, strong skipping), r |
 | external | `android-security` |  -  | Secure Android apps with ProGuard/R8 obfuscation, OkHttp certificate pinning, BiometricPrompt authentication, EncryptedSharedPreferences, Pl |
-| external | `android-ui-verification` |  -  | Automated end-to-end UI testing and verification on an Android Emulator using ADB. Use when an Android build needs driving on an emulator to |
-| external | `api-patterns` |  -  | API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination. Use when choosing be |
-| external | `api-security-best-practices` |  -  | Implement secure API design patterns including authentication, authorization, input validation, rate limiting, and protection against common |
+| external | `api-patterns` |  -  | Choosing an API style (REST, GraphQL, gRPC, webhooks, events) and the contracts every style needs: versioning, cursor pagination, idempotenc |
+| external | `api-security-best-practices` |  -  | API security against the OWASP API Top 10: object-level authorization, token handling, input validation, rate limits, secrets. Use when buil |
 | external | `app-clips` |  -  | Build iOS App Clips with invocation URLs, App Clip Codes, NFC, QR codes, Safari banners, Maps, Messages, target setup, App Store Connect exp |
 | external | `app-intents` |  -  | Implement App Intents for Siri, Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence on iOS. Covers AppIntent actions, AppE |
 | external | `app-store-changelog` |  -  | Generate user-facing App Store release notes from git history since the last tag. Use when release notes have to be written from the commits |
@@ -29,21 +27,20 @@
 | external | `app-store-review` |  -  | Prepare for App Store review and prevent rejections. Covers App Store review guidelines, app rejection reasons, PrivacyInfo.xcprivacy privac |
 | core | `apple-archive-compliance` |  -  | Apple App Store Review compliance  -  wraps the multi-agent-toolkit-mcp `ios_app_store_audit` tool (18-rule deep scan) with ITMS error code  |
 | external | `apple-on-device-ai` |  -  | Integrate on-device AI using Foundation Models framework, Core ML, and open-source LLM runtimes on Apple Silicon. Covers Foundation Models ( |
-| external | `architecture` |  -  | Architectural decision-making framework. Requirements analysis, trade-off evaluation, ADR documentation. Use when making architecture decisi |
+| external | `architecture` |  -  | Stack-neutral architecture decisions: quality drivers, options with a trade-off matrix, reversibility, ADRs, fitness checks. Use when making |
 | external | `authentication` |  -  | Implement iOS authentication flows with AuthenticationServices and LocalAuthentication. Use when building Sign in with Apple, passkey/WebAut |
 | external | `avkit` |  -  | Create media playback experiences using AVKit. Use when adding video players with AVPlayerViewController, enabling Picture-in-Picture, routi |
 | external | `background-processing` |  -  | Schedule and execute background work on iOS using BGTaskScheduler. Use when registering BGAppRefreshTask for short background fetches, BGPro |
-| external | `backlog` |  -  | The engineering backlog registry for deferred-but-approved work in this codebase. Every job the user defers ('defer it', 'add it to the list |
+| external | `backlog` |  -  | The engineering backlog registry for deferred-but-approved work: each deferred job lands here with its spec, origin and unblock condition. U |
 | external | `callkit-voip` |  -  | Implement VoIP calling with CallKit and PushKit. Use when building incoming/outgoing call flows, registering for VoIP push notifications, co |
 | external | `ci-cd-pipelines` |  -  | CI/CD pipelines: GitHub Actions workflows, Docker multi-stage builds, environment management, secret management, deployment strategies. Use  |
-| external | `clean-code` |  -  | This skill embodies the principles of \"Clean Code\" by Robert C. Martin (Uncle Bob). Use it to transform \"code that works\" into \"code th |
-| external | `closed-loop-delivery` |  -  | Use when a coding task must be completed against explicit acceptance criteria with minimal user re-intervention across implementation, revie |
+| external | `clean-code` |  -  | Readability checks for code in any language: names, function focus, control flow, side effects, errors, comments, duplication. Use when writ |
 | external | `cloudkit-sync` |  -  | Implement, review, or improve CloudKit and iCloud sync in iOS/macOS apps. Use when working with CKContainer, CKRecord, CKQuery, CKSubscripti |
 | external | `compose-components` |  -  | Build Material 3 UI components and custom composables with Jetpack Compose. Covers TopAppBar, Scaffold, BottomSheet, SnackbarHost, slot-base |
-| external | `compose-navigation` |  -  | Implement type-safe navigation in Jetpack Compose using Navigation 2.8+ with @Serializable routes, NavHost, composable<Route>, nested naviga |
+| external | `compose-navigation` |  -  | Implement type-safe navigation in Jetpack Compose using Navigation 2.8+ with @Serializable routes, NavHost, typed composable routes, nested  |
 | external | `compose-testing` |  -  | Test Jetpack Compose UI with createComposeRule, semantic matchers (onNodeWithText, onNodeWithTag, onNodeWithContentDescription), actions (pe |
 | external | `contacts-framework` |  -  | Read, create, update, and pick contacts using the Contacts and ContactsUI frameworks. Use when fetching contact data, saving new contacts, w |
-| external | `context-compression` |  -  | When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is aggressive com |
+| external | `context-compression` |  -  | Keeping long LLM agent sessions on track: what a summary must preserve, incremental structured summaries, state in files, compact versus res |
 | external | `core-bluetooth` |  -  | Build direct Bluetooth Low Energy workflows with Core Bluetooth. Use when implementing BLE central or peripheral GATT communication, scannin |
 | external | `core-data` |  -  | Build, review, or improve Core Data persistence in apps that have not adopted SwiftData. Use when working with NSManagedObject subclasses, N |
 | external | `core-motion` |  -  | Access Core Motion accelerometer, gyroscope, magnetometer, device-motion, pedometer, activity-recognition, altitude, headphone motion, batch |
@@ -54,50 +51,49 @@
 | external | `css-modern` |  -  | Modern CSS: container queries, nesting, @layer, Grid/Flexbox patterns, custom properties, animations, and transitions. Use when writing or r |
 | external | `database-patterns` |  -  | Database patterns: SQL best practices (PostgreSQL), indexing, query optimization, migrations, schema design, ORMs (SQLAlchemy, Prisma, Drizz |
 | external | `debugging-instruments` |  -  | Debug iOS apps and profile performance using LLDB, Memory Graph Debugger, and Instruments. Use when diagnosing crashes, memory leaks, retain |
-| external | `debugging-strategies` |  -  | Transform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical approa |
+| external | `debugging-strategies` |  -  | Language-neutral debugging method: reproduce, minimise, falsifiable hypotheses, git bisect, instrumentation, production traces, concurrency  |
 | external | `device-integrity` |  -  | Verify device legitimacy and app integrity using DeviceCheck (DCDevice per-device bits) and App Attest (DCAppAttestService key generation, a |
-| external | `docker-expert` |  -  | You are an advanced Docker containerization expert with comprehensive, practical knowledge of container optimization, security hardening, mu |
+| external | `docker-expert` |  -  | Dockerfiles and images: multi-stage builds, BuildKit cache and secret mounts, slim or distroless bases, non-root, healthchecks, scanning, mu |
 | external | `energykit` |  -  | Query grid electricity forecasts and submit load events using EnergyKit to help users optimize home electricity usage. Use when building sma |
 | external | `eventkit-calendar` |  -  | Create, read, and manage calendar events and reminders using EventKit and EventKitUI. Use when adding events to the user's calendar, creatin |
 | external | `evidence-github` |  -  | Search GitHub for facts an analysis can cite - a known issue in a dependency, the PR that fixed it, what a release actually changed, prior a |
 | external | `evidence-registry` |  -  | Check a package's real version, deprecation status and release notes on npm, PyPI, Maven Central or Swift Package Index. Use when a spec or  |
-| external | `fastapi-pro` |  -  | Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async p |
+| external | `fastapi-pro` |  -  | FastAPI with Pydantic v2: lifespan, settings, Annotated dependencies, async SQLAlchemy 2.0 sessions, error handlers, background work, httpx  |
 | external | `firebase` |  -  | You're a developer who has shipped dozens of Firebase projects. You've seen the easy path lead to security breaches, runaway costs, and impo |
-| external | `github-actions-templates` |  -  | Production-ready GitHub Actions workflow patterns for testing, building, and deploying applications. Use when a GitHub Actions workflow has  |
+| external | `github-actions-templates` |  -  | Authoring GitHub Actions workflows: triggers, matrices, caching, concurrency, least-privilege permissions, SHA pinning, OIDC, reusable workf |
 | core | `google-play-compliance` |  -  | Google Play Store publication compliance  -  bundletool + aapt2 + apksigner orchestration + 21-rule policy catalog with Play Console error c |
 | external | `gradle-kotlin-dsl` |  -  | Configure Android builds with Gradle Kotlin DSL, version catalogs (libs.versions.toml), convention plugins (build-logic module), common conf |
 | external | `healthkit` |  -  | Read, write, and query Apple Health data using HealthKit. Covers HKHealthStore authorization, sample queries, statistics queries, statistics |
-| external | `hig-components-content` |  -  | Apple Human Interface Guidelines for content display components. Use when designing or reviewing how content is displayed on an Apple platfo |
-| external | `hig-components-layout` |  -  | Apple Human Interface Guidelines for layout and navigation components. Use when designing or reviewing layout and navigation on an Apple pla |
-| external | `hig-components-status` |  -  | Apple HIG guidance for status and progress UI components including progress indicators, status bars, and activity rings. Use when designing  |
-| external | `hig-components-system` |  -  | 'Apple HIG guidance for system experience components: widgets, live activities, notifications, complications, home screen quick actions, top |
-| external | `hig-foundations` |  -  | Apple Human Interface Guidelines design foundations. Use when a design decision turns on Apple's foundations: layout, typography, colour, mo |
-| external | `hig-inputs` |  -  | Apple Human Interface Guidelines for input methods: touch gestures, keyboards, Apple Pencil, pointing devices, game controllers, Digital Cro |
-| external | `hig-patterns` |  -  | Apple Human Interface Guidelines interaction and UX patterns. Use when an interaction or UX pattern on an Apple platform needs designing or  |
-| external | `hig-platforms` |  -  | Apple Human Interface Guidelines for platform-specific design. Use when a design has to fit a specific Apple platform's conventions. |
-| external | `hig-technologies` |  -  | Apple Human Interface Guidelines for Apple technologies: Siri, Apple Pay, Wallet, HealthKit, CarPlay, iCloud, Maps, in-app purchase and Sign |
+| external | `hig-components-content` |  -  | Apple HIG for content views mapped to SwiftUI: lists, tables, grids, charts, images, text, web views, empty states. Use when choosing or rev |
+| external | `hig-components-layout` |  -  | Apple HIG for app structure mapped to SwiftUI: tab bars, split views, navigation stacks, toolbars, sheets, popovers, alerts, windows, iOS 26 |
+| external | `hig-components-status` |  -  | Apple HIG for status UI mapped to SwiftUI: progress views, gauges, placeholders, status bar, activity rings, success and failure feedback. U |
+| external | `hig-components-system` |  -  | Apple HIG for system surfaces: widgets, controls, Live Activities, Dynamic Island, notifications, complications, quick actions, App Shortcut |
+| external | `hig-foundations` |  -  | Apple HIG foundations mapped to SwiftUI: Dynamic Type, semantic color, contrast, safe areas, SF Symbols, materials and Liquid Glass, motion, |
+| external | `hig-inputs` |  -  | Apple HIG for input mapped to SwiftUI: touch gestures, keyboards, pointer, Apple Pencil, focus and game controllers, Digital Crown, eyes and |
+| external | `hig-patterns` |  -  | Apple HIG interaction patterns mapped to SwiftUI: modality, loading, empty and error states, feedback, undo, search, data entry, settings, s |
+| external | `hig-platforms` |  -  | Apple HIG per platform: iPhone, iPad, Mac, Watch, TV and Vision Pro conventions, and adapting one SwiftUI codebase across them. Use when a d |
+| external | `hig-technologies` |  -  | Apple HIG for system technologies: Sign in with Apple, passkeys, Apple Pay, Wallet, Siri and App Intents, HealthKit, HomeKit, iCloud, Maps,  |
 | external | `homekit-matter` |  -  | Control smart-home accessories and commission Matter devices using HomeKit and MatterSupport. Use when managing homes/rooms/accessories, cre |
 | external | `html-semantic` |  -  | Semantic HTML5: elements, forms with validation and accessibility, SEO best practices, structured data, Open Graph, Twitter Cards. Use when  |
 | external | `humanizer` |  -  | Remove AI-generated writing patterns from text. Makes output sound natural and human-written. Detects inflated language, filler phrases, AI  |
 | external | `ios-accessibility` |  -  | Implements, reviews, or improves accessibility in iOS/macOS apps with SwiftUI, UIKit, and AppKit. Use when adding VoiceOver, Voice Control,  |
 | external | `ios-coding-standard` |  -  | The iOS coding-standard rule registry: 99 stable-ID rules across readability, security, service layer, business rules, concurrency, testing, |
 | external | `ios-debugger-agent` |  -  | Debug the current iOS project on a booted simulator with XcodeBuildMCP. Use when an iOS bug has to be reproduced and diagnosed on a booted s |
-| external | `ios-developer` |  -  | Develop native iOS applications with Swift/SwiftUI. Masters iOS 18, SwiftUI, UIKit integration, Core Data, networking, and App Store optimiz |
 | external | `ios-localization` |  -  | Implement, review, or improve localization and internationalization in iOS/macOS apps  -  String Catalogs (.xcstrings), generated localizabl |
 | external | `ios-module-structure` |  -  | The ios-module-structure rule registry: stable-ID rules over where a declaration lives, what its file is called and what its folder must con |
 | external | `ios-networking` |  -  | Build, review, or improve networking code in iOS/macOS apps using URLSession with async/await, structured concurrency, and modern Swift patt |
 | external | `ios-security` |  -  | Secure iOS apps with Keychain Services, CryptoKit encryption, biometric authentication (Face ID, Touch ID), Secure Enclave key storage, LACo |
 | external | `ios-simulator` |  -  | Manages iOS Simulator devices and tests app behaviour with xcrun simctl: device lifecycle, app install and launch, push notification and loc |
-| external | `kotlin-coroutines-expert` |  -  | Expert patterns for Kotlin Coroutines and Flow, covering structured concurrency, error handling, and testing. Use when writing or reviewing  |
+| external | `kotlin-coroutines-expert` |  -  | Kotlin coroutines and Flow: scopes, structured concurrency, cancellation, exception handling, dispatcher injection, StateFlow versus SharedF |
 | external | `live-activities` |  -  | Implement, review, or improve Live Activities and Dynamic Island experiences in iOS apps using ActivityKit. Use when building real-time upda |
-| external | `localization-reuse-map` |  -  | Produce a per-screen localization-reuse map for one redesigned screen (iOS / Android / web): for each UI element it pairs the NEW localizati |
+| external | `localization-reuse-map` |  -  | Builds a per-screen localization-reuse map for one redesigned screen (iOS, Android, web): pairs each UI element's new key and values with th |
 | external | `macos-menubar-tuist-app` |  -  | Build, refactor, or review SwiftUI macOS menubar apps that use Tuist. Use when building, refactoring or reviewing a SwiftUI macOS menubar ap |
 | external | `macos-spm-app-packaging` |  -  | Scaffold, build, sign, and package SwiftPM macOS apps without Xcode projects. Use when a SwiftPM macOS app has to be built, signed or packag |
 | external | `mapkit-location` |  -  | Implement, review, or improve maps and location features in iOS/macOS apps using MapKit and CoreLocation. Use when working with Map views, a |
 | external | `metrickit-diagnostics` |  -  | Collect and analyze on-device performance metrics and crash diagnostics using MetricKit. Use when setting up MXMetricManager, handling MXMet |
-| external | `monorepo-architect` |  -  | Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient mu |
+| external | `monorepo-architect` |  -  | Monorepo structure: pnpm workspaces, Turborepo or Nx task graphs, affected-only CI, remote cache, package boundaries, Changesets, CODEOWNERS |
 | core | `multi-agent` |  -  | Task orchestrator: runs the full pipeline from a Jira ID or GitHub Issue URL  -  analysis → plan → TDD development → parallel review (Fable  |
-| core | `multi-agent-analysis` |  -  | Standalone feature-spec analysis. Two profiles picked at intake: global (23-section development handoff, 8 of them in Lite mode) or corporat |
+| core | `multi-agent-analysis` |  -  | Standalone feature-spec analysis. Two profiles picked at intake: global (23-section development handoff, evidence-trimmed) or corporate (IG/ |
 | core | `multi-agent-analysis-jira` |  -  | Turn a rendered analysis document into a Jira story tree: derive stories from the document's own rule ids, check coverage both ways, preview |
 | core | `multi-agent-analysis-resolve` |  -  | Resolve the Section 20 Risks and Open Questions of an analysis v3 document one row at a time: up to 3 source-labeled answer candidates per r |
 | core | `multi-agent-autopilot` |  -  | Launch any task in autopilot mode: skips every confirmation, runs end-to-end autonomously. Use when a task should run end to end with no con |
@@ -128,8 +124,9 @@
 | core | `multi-agent-prune-prompts` |  -  | Zero-base prompt review: measure the always-on instruction footprint, classify every rule block, propose keep/trial-removal/delete; applies  |
 | core | `multi-agent-purge` |  -  | ⚠️ Wipes every worktree, branch, log, and state file. Irreversible; asks for double confirmation. Use when every worktree, branch, log and s |
 | core | `multi-agent-refactor` |  -  | Analyse the project: extract adapted best-practices, hunt real bugs + improvement areas, check upstream drift of derived skills, research th |
+| core | `multi-agent-research` |  -  | Research an item's open gaps from the tracker, linked docs and the repo before anyone is asked; a script decides which closed. Use when a ru |
 | core | `multi-agent-resume` |  -  | Pick up unfinished work: a pipeline run that stopped mid-phase, or work already written on the current branch that never went through the pi |
-| core | `multi-agent-review` |  -  | Run parallel review on a branch diff or a Pull Request: 3 models on Claude Code (Fable + Opus + Sonnet), 3 models on Copilot CLI (GPT + Opus |
+| core | `multi-agent-review` |  -  | Run parallel review on a branch diff or a Pull Request: 3 models on Claude Code (Fable + Opus + Sonnet; Opus + Sonnet while the fable rung i |
 | core | `multi-agent-review-analysis` |  -  | Review a written analysis document instead of a diff: resolve it from a path, a Confluence page or a Jira issue, run the deterministic gates |
 | core | `multi-agent-review-issue` |  -  | Assess whether a GitHub issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / sta |
 | core | `multi-agent-review-jira` |  -  | Assess whether a Jira issue is ready for multi-agent development: fetch it, grade scope / acceptance criteria / repro / design / API / stack |
@@ -137,10 +134,12 @@
 | core | `multi-agent-route-on` |  -  | Enable policy-driven model routing: pick a strategy, a scope, and the rules that say which rung a call lands on. Use when asked to turn mode |
 | core | `multi-agent-route-status` |  -  | Report model routing: whether it is armed, which rule applies where, which rung the last dispatches took, and what this run has cost. Use wh |
 | core | `multi-agent-routines` |  -  | List your saved /multi-agent routines (from /multi-agent:save) with what each one does, rendered in outputLanguage. Use when asked which sav |
-| core | `multi-agent-save` |  -  | Save a recurring job as a reusable /multi-agent:<name> command. Reviews the conversation + your CLAUDE.md for candidate routines, you pick o |
+| core | `multi-agent-save` |  -  | Save a recurring job as a reusable /multi-agent:{name} command. Reviews the conversation + your CLAUDE.md for candidate routines, you pick o |
+| core | `multi-agent-scaffold` |  -  | Create a project skeleton with the enabled toolkit's scaffold skill and prove it builds, tests and lints before the first commit; no remote  |
 | core | `multi-agent-scan` |  -  | Skill security scan: walks local skill directories against a tiered pattern catalog. Use when local skill directories need checking for unsa |
 | core | `multi-agent-search` |  -  | Log search across every agent-log.md with smart ranking and filters. Optional --semantic flag queries the per-repo triage corpus. Use when s |
 | core | `multi-agent-security-review` |  -  | Run a standalone defensive, static security review of a diff, branch or repo: run-scoped threat model, reviewer-shaped findings joined to OW |
+| core | `multi-agent-serve` |  -  | Start the local contract server a client (the macOS toolbox, a web page) reads runs, commands, questions, issues and worktrees from, on 127. |
 | core | `multi-agent-setup` |  -  | First-run setup wizard: keychain token discovery, Git Identity onboarding, and pipeline preparation. Use when the pipeline is being set up f |
 | core | `multi-agent-stack` |  -  | Select the active stack(s) for this repo by enabling the matching marketplace plugin(s) in .claude/settings.json. Multi-select: pass several |
 | core | `multi-agent-status` |  -  | Show every multi-agent task's ID, phase, branch, and status. Use when asked what is running, or for an overview of every task. |
@@ -158,8 +157,8 @@
 | external | `musickit-audio` |  -  | Integrate Apple Music playback, catalog search, and Now Playing metadata using MusicKit and MediaPlayer. Use when adding music search, Apple |
 | external | `natural-language` |  -  | Tokenize, tag, and analyze natural language text using Apple's NaturalLanguage framework and translate between languages with the Translatio |
 | external | `nextjs-app-router` |  -  | Next.js 15+ App Router: Server/Client Components, Server Actions, data fetching, layouts, middleware, ISR/SSG/SSR, and routing patterns. Use |
-| external | `nodejs-backend-patterns` |  -  | Comprehensive guidance for building scalable, maintainable, and production-ready Node.js backend applications with modern frameworks, archit |
-| external | `observability-engineer` |  -  | Build production-ready monitoring, logging, and tracing systems. Implements comprehensive observability strategies, SLI/SLO management, and  |
+| external | `nodejs-backend-patterns` |  -  | Node.js 22/24 services in ESM: structure, validated config, error mapping, graceful shutdown, AsyncLocalStorage, streams, queues, node:test. |
+| external | `observability-engineer` |  -  | Observability with OpenTelemetry: traces, metrics and logs, semantic conventions, structured logging, RED and USE, SLOs and burn-rate alerts |
 | external | `passkit-wallet` |  -  | Integrate Apple Pay payments and Wallet passes using PassKit. Use when adding Apple Pay buttons, creating payment requests, handling payment |
 | external | `pdfkit` |  -  | Display and manipulate PDF documents using PDFKit. Use when embedding PDFView to show PDF files, creating or modifying PDFDocument instances |
 | external | `pencilkit-drawing` |  -  | Add Apple Pencil drawing with PKCanvasView, PKToolPicker, PKDrawing serialization/export, stroke inspection, and PencilKit/PaperKit handoffs |
@@ -185,11 +184,11 @@
 | external | `swift-architecture` |  -  | Select, implement, or migrate between app architecture patterns for Apple platform apps. Use when choosing between MV (Model-View with @Obse |
 | external | `swift-charts` |  -  | Implement, review, or improve data visualizations using Swift Charts. Use when building bar, line, area, point, pie, donut, or iOS 26 3D cha |
 | external | `swift-codable` |  -  | Implement Swift Codable models for JSON and property-list encoding and decoding with JSONDecoder, JSONEncoder, CodingKeys, and custom init(f |
-| external | `swift-concurrency` |  -  | Resolve Swift concurrency compiler errors, adopt approachable concurrency (SE-0466), and write data-race-safe async code. Use when fixing Se |
+| external | `swift-concurrency` |  -  | Swift concurrency language reference and migration: Sendable and actor-isolation diagnostics, approachable concurrency (SE-0466 default Main |
 | external | `swift-concurrency-expert` |  -  | Review and fix Swift concurrency issues such as actor isolation and Sendable violations. Use when a Swift concurrency problem needs diagnosi |
 | external | `swift-concurrency-pro` |  -  | Reviews Swift code for concurrency correctness, modern API usage, and common async/await pitfalls. Use when reading, writing, or reviewing S |
 | external | `swift-formatstyle` |  -  | Format values for display using the FormatStyle protocol and its concrete types. Use when formatting numbers (integers, floating-point, deci |
-| external | `swift-language` |  -  | Apply modern Swift language patterns and idioms for non-concurrency, non-SwiftUI code. Covers if/switch expressions (Swift 5.9+), typed thro |
+| external | `swift-language` |  -  | Modern Swift language patterns for code outside concurrency and SwiftUI: if/switch expressions, typed throws, result builders, property wrap |
 | external | `swift-security` |  -  | Use when working with iOS/macOS Keychain Services (SecItem queries, kSecClass, OSStatus errors), biometric authentication (LAContext, Face I |
 | external | `swift-testing` |  -  | Writes and migrates Swift Testing framework tests with @Test, @Suite, #expect, #require, confirmation, traits, withKnownIssue, Attachment.re |
 | external | `swift-testing-pro` |  -  | Writes, reviews, and improves Swift Testing code using modern APIs and best practices. Use when reading, writing, or reviewing projects that |
@@ -202,8 +201,8 @@
 | external | `swiftui-layout-components` |  -  | Build SwiftUI layouts using stacks, grids, lists, scroll views, forms, and controls. Covers VStack/HStack/ZStack, LazyVGrid/LazyHGrid, List  |
 | external | `swiftui-liquid-glass` |  -  | Implement, review, or improve SwiftUI Liquid Glass effects for iOS 26+. Covers glassEffect modifier, GlassEffectContainer, glass button styl |
 | external | `swiftui-navigation` |  -  | Implement SwiftUI navigation patterns including NavigationStack, NavigationSplitView, sheet presentation, tab-based navigation, and deep lin |
-| external | `swiftui-patterns` |  -  | Builds SwiftUI views with modern MV architecture, state management, and view composition patterns. Covers @Observable ownership rules, @Stat |
-| external | `swiftui-performance` |  -  | Audit and improve SwiftUI runtime performance. Use when diagnosing slow rendering, janky scrolling, high CPU, memory usage, excessive view u |
+| external | `swiftui-patterns` |  -  | Builds SwiftUI views with MV architecture: @Observable ownership, @State/@Bindable/@Environment wiring, view decomposition, custom ViewModif |
+| external | `swiftui-performance` |  -  | Audit and improve SwiftUI runtime performance: slow rendering, janky scrolling, high CPU or memory, excessive view updates, layout thrash, b |
 | external | `swiftui-performance-audit` |  -  | Audit SwiftUI performance issues from code review and profiling evidence. Use when a SwiftUI view is slow and the cause has to be found from |
 | external | `swiftui-pro` |  -  | Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. Use when reading, writing, or revi |
 | external | `swiftui-ui-patterns` |  -  | Apply proven SwiftUI UI patterns for navigation, sheets, async state, and reusable screens. Use when a SwiftUI screen needs a proven pattern |

package/docs/token-budget-history.md

@@ -1,24 +0,0 @@
-# Token budget history
-
-Every ceiling change in `pipeline/schemas/token-budget.json`, with the reason
-that was written at the time. It lives here rather than inside the schema for a
-plain reason: it had grown to 23,769 characters, larger than four of the eight
-documents it governs, inside a file whose job is to hold eight numbers.
-
-It is kept rather than dropped because the reasons are the audit trail - they
-are what separates a considered raise from threshold-chasing, and reading them
-end to end is what made the pattern visible: almost every entry says "the
-smallest step that clears it", which sets the ceiling to the measurement and is
-why six of the eight phases ended up at 99-100% of their own limit.
-
-As of v17.1.0 the rules changed. `warn` is no longer stored at all - the gate
-computes it per phase from that phase's own git history. `max` stays a committed
-constant, and a ceiling that sits more than 25% above the measurement now FAILS
-as stale, so reclaimed space is banked instead of being left as room to drift
-back into. The ceiling can still be raised; it can no longer be raised for free.
-
----
-
-Token estimate = ceil(chars / 4). Per-phase budget rule: warn = current+10% (rounded to nearest 50), max = current+25%. Gives ~6 edit cycles of headroom before warn trips  -  intentionally quiet under normal maintenance, loud when a phase grows unusually. Only the active phase is loaded (lazy). Recalibrated at v10.0.0 after the validator/consistency/simplifier/lesson gate contracts landed in phases 1-4. Recalibrated again at v10.9.0 after the verify-by-test (Phase 4 Step 3.7), update-check (Phase 0 Step 0.6), immutable-test (Phase 3 GREEN) and redTests re-entry contracts landed  -  Step 3.7 prose was compressed to a pointer into refs/features/verify-by-test.md before the recalibration. Total bumped 50000 -> 51000 at v12.5.0 after the worktree residue/traversal-prune contract (Phase 0 + Phase 5 heal) and the Reflexion causal-diagnosis contract (Phase 4 lesson memory) landed; the prose was compressed first (161 tokens reclaimed) and every per-phase max still passes  -  only the aggregate needed room. Recalibrated again at v13.6.0 after the install-relative path correction: an instruction that names `pipeline/scripts/x` resolves only from a repo checkout, and a run happens in the user's worktree, so 157 references across these docs moved to `$HOME/.claude/...` at +5 bytes each  -  196 tokens of pure correctness cost. Same discipline as before: prose was compressed FIRST (149 tokens reclaimed, by pointing Phase 1's Figma tier table at the Phase 0 probe that already resolved it and Phase 4's Codex constraints at the always-loaded AGENTS.md block), and only then were the budgets moved. Five warn lines had been permanently amber, which makes the amber tier useless as a signal, so every warn was reset to the documented current+10% and the four maxes that the new warn would have collided with were reset to current+25%. Aggregate 51000 -> 51500. Total bumped 51500 -> 52200 at v14.0.0 after Phase 4 Review entered the four --dev mode phase sets and the criteria-resolution contract (Step 1.78) landed. Same discipline as every prior bump: prose was compressed FIRST, 820 tokens reclaimed, before the number moved. Two of those compressions are structural rather than cosmetic - the hardcoded SwiftUI interaction list in Step 1.5 and the SwiftUI convention paragraph in Step 2.8 were transcriptions of rules that now live in a scoped registry, so keeping them here would have re-created the drift this release exists to remove, and the third moved the Step 1.78 full contract into refs/features/skill-conformance.md leaving a pointer. What remains is contract text that cannot be inferred: the manifest's four consumer-visible parts, the conformance checklist the reviewers must return, and the fail-closed semantics. Every per-phase max still passes (phase-4 12405/14750); only the aggregate needed room. Total bumped 52200 -> 52700 at v14.1.0 after two more contracts landed: stack skill routing (Phase 3 pre-flight step 9) and worktree finalize (Phase 6 step 9). Compression came first, as always, and twice: 224 tokens out of Phase 3 by pointing its criteria-ledger and routing steps at their feature files instead of restating them, and 190 out of Phase 6 by moving the finalize contract into refs/features/worktree-finalize.md and leaving the invocation plus the exit-3 semantics. Both new contracts follow the pattern the earlier ones set: the phase doc carries the call and the decision, the feature file carries the reasoning, and the feature files are outside this budget because it loops only the eight phase-N-* keys. Every per-phase max still passes (phase-3 7677/8950, phase-6 5223/6150 and both under warn); only the aggregate needed room. Total bumped 52700 -> 52750 for the Phase 0 Step 3 branch-persistence correction: the step wrote the legacy `projects[].branches` while the TTL filter two sections below read `global.recentBranches`, and both spots named a `{name, lastUsed}` shape the schema rejects (`branch` required, `additionalProperties: false`), so the recent-branch picker option could never populate and a literal implementation would have failed prefs validation. Naming the right target, the right key and the legacy field to avoid costs 41 tokens over the one line it replaces. Compression came first and was applied three times to the replacement text itself, from 120 tokens down to 66, by moving the rationale out of the phase doc entirely: the reasoning now lives where it is enforced, in the migrate-prefs carry-forward comment and the smoke-pref-migration f7 block, leaving the phase doc with only the instruction. 50 was the smallest step that clears it; phase-0-init sits at 10893/12400, far under its own max, so this is purely an aggregate ceiling. v15.0.0: total 52750 -> 53100, the stack-skill tables in phase-1/2/4 now carry plugin-namespaced names (ai-<stack>-toolkit:<skill>) - functional prefixes, ~170 tokens. v15.10.0: total 53350 -> 53950 for the memory-recall + context-offload contracts (Phase 1 two-block durable-knowledge injection and its telemetry, Phase 3 build-log offload pipe, Phase 4 ranked prior art, offload pipe and recall telemetry). Compression came first and twice, taking the new prose from 1168 tokens to 580: the reasoning behind the two blocks lives in multi-agent-refs/prompt-assembly.md and the reasoning behind the offload filter lives in the offload-ref.sh header, both outside this budget, so the phase docs carry only the call, the pref that gates it and the one fact an agent cannot infer - that the evidence gate still reads the whole build log, so offloading changes what is read, never what counts as a verified pass. Every per-phase max still passes (phase-3 7985/8950, phase-4 12997/14750); phase-3 and phase-4 crossed their warn lines and are left amber on purpose, because that is the signal that those two docs are the next ones needing structural compression rather than another bump. v15.13.0: total 53950 -> 54050 for the prefs-to-flag bridges. Five settings had shipped declared-but-inert: contextOffload.minLines and .tailLines (fixed in 15.11.0), learningsLedger.maxBriefEntries, and testGap.scanTree and .promoteSeverity - the last two declared in the schema AND implemented as flags in the scanner, with nothing in between reading the pref and passing the flag. Wiring three of them costs the phase docs 94 tokens, which is the wiring itself and not prose: two `--max` substitutions and a three-line GAP_FLAGS block. Compression came first and twice, as always: the rationale that would have sat in phase-5 now lives in the header of smoke-prefs-consumed.sh, the gate that makes this class fail a build instead of shipping, and a `--severity-promote` table row was dropped because the invocation above it now shows the flag and names the pref that triggers it, which the row did not. 100 was the smallest step that clears it. Every per-phase max still passes; phase-3 and phase-4 remain amber on purpose. v15.14.0: total 54050 -> 54400 for the supported-version gate. Phase 0 Step 0.6 stopped being purely advisory: a release can now publish an npm dist-tag `required` that names the oldest runnable version, and below it the run halts instead of nagging. What the phase doc has to carry is the part an agent cannot infer - the third stdout field, that the halt is identical in autopilot, and that the run must NOT continue on the freshly updated install because its docs were already loaded from the old version. Compression came first, as always, and took the new prose from 469 tokens to 337: the rationale for the floor, the exemption list, the fail-open rules and the `npm dist-tag add` recipe all moved to multi-agent-refs/rules.md "Supported Version Gate" (loaded by 25 commands, outside this budget) and to the header of require-supported-version.sh, leaving the phase doc with the call, the decision table and the halt. 350 was the smallest step that clears it. Every per-phase max still passes (phase-0-init 11230/12400); phase-3 and phase-4 remain amber on purpose. v15.17.0: total 54400 -> 54900 for the Phase 1 analysis-document step. Phase 2 and Phase 3 pre-flights had BLOCKED on `analysis/<feature>-<platform>.md` since v9.0.0 while nothing produced it, so a full run either aborted at Phase 2 or the model ignored its own BLOCKING contract; Step 4 is the producer. What the phase doc carries is only what cannot be inferred: the when-table (taskType x Figma reference), the four refs in load order, the two artefacts, and that the doc validator fails closed. Compression came first and took the step from 745 tokens to 497: the history of why the gap existed moved to the CHANGELOG, the per-ref one-line descriptions moved into the refs' own headers, and the autopilot carve-out collapsed to one clause. The 17.4k-token analysis engine itself is NOT in this budget - it moved out of commands/ into multi-agent-refs/analysis/{locked,evidence,synthesis,render}.md, loaded on demand, which also took analysis/SKILL.md from 18081 to 5974 tokens and retired its lint grace entry. 500 was the smallest step that clears it; phase-1-analysis sits at 4338/4600 and is amber on purpose, like phase-3 and phase-4. v15.18.0: total 54900 -> 55250 for analysis mode. Three phase docs gained a mode branch that cannot be inferred: Phase 3 reviews a document instead of a diff (validator, the one question reviewers answer, the open-question walk), and Phase 6 publishes instead of committing. Compression came first and was applied twice to the new prose and once to old: the Phase 4 branch went from 320 tokens to 180 and the Phase 6 branch from 190 to 120 by pointing at multi-agent-refs/analysis/{resolve,render}.md, which now hold the walks themselves, and the front-matter parse contract stopped being spelled out in both pre-flights. The analysis engine keeps leaving this budget rather than entering it: intake joined locked/evidence/synthesis/render/resolve in multi-agent-refs/analysis/, which is what let analysis/SKILL.md drop under the 6000 hard cap after its grace entry was retired. 350 was the smallest step that clears it; phase-4 and phase-6 are amber on purpose, as phase-1 and phase-3 already were. v15.20.0: total 55250 -> 55500 for the TDD bridge. Phase 3 pre-flight read the analysis doc's concept table and even said test method names come from it, while nothing read Section 15 - so the RED step invented tests and the analysis test matrix never reached development. Phase 3 step 5b now loads it into state.dev.testPlan[] and Phase 4 step 1.45 cross-checks every planned row against a real test, which is what turns "analysis quality is output quality" from a slogan into a finding. Compression came first on both blocks, 300 tokens down to 175, by dropping the enumerated failure modes to one line each and the rationale to one clause; the reasoning lives in the CHANGELOG. 250 was the smallest step that clears it. v15.21.0: total 55500 -> 55800 for the post-analysis confirmation. Phase 2 gained Step 0.9, the last human checkpoint before Phase 3: derived values are shown for confirmation and only Section 20 rows are asked, through the resolve engine that already exists in refs. It belongs here rather than Phase 4 because Phase 3 runs after development, where an answer arrives too late to change anything. Compression came first and twice, 430 tokens down to 250, by collapsing the derived-vs-asked explanation to one sentence each and moving the walk itself to multi-agent-refs/analysis/resolve.md, which Phase 4 and analysis-resolve already mount. 300 was the smallest step that clears it. v15.22.0: total 55800 -> 55900 for the analyst-toolkit hooks. Phase 1 Step 4 now names the two prefs that decide whether a document is produced at all and how deep it goes (forceFull, mode) - the first of those had shipped declared-but-inert and smoke-prefs-consumed caught it - and Phase 3 triage gained one clause: a finding that blames a third-party library asks evidence-github whether it is already open upstream, which turns it into a deferred item with a citation instead of Phase 3 rework on code that is not ours. Compression came first and three times, taking the new prose from 220 tokens to 110, and the Phase 1d evidence contract itself never entered this budget - it lives in multi-agent-refs/analysis/evidence.md beside the phases it belongs to. 100 was the smallest step that clears it, leaving 34 tokens of headroom. phase-4 stays amber and the debt named at v15.10.0 stands: it is the doc that needs structural compression rather than another bump, and the two candidates are the inline triage JSON shape and the 3.4 telemetry block, both of which restate something already authoritative elsewhere. v16.0.0: total 55900 -> 56350 for the depth picker. `--dev` and the four dev-* commands are gone; depth is Phase 0 Step 7.5, which costs phase-0-init a step it did not have. Compression came first and three times, taking the step from 530 tokens to 300: the question wording, the per-taskType recommendation and the mode tables all live in phases/modes.md (outside this budget), so the phase doc carries only what an agent cannot infer - that the step runs after Step 7 and why, who is exempt, that ASK_CHOICE_DEFAULT must be passed explicitly because ask-choice.sh takes the FIRST option on a non-TTY, and that Short flips the Phase 1/2 tiles late rather than pre-marking them. The phase-4 telemetry block named as compression debt at v15.22.0 was collapsed to an emit() helper (-27) and the four dev-* mode files left the tree entirely, but neither offsets a genuinely new phase step. 450 was the smallest step that clears it, leaving 119 tokens of headroom. phase-4 remains amber and its other named candidate, the inline triage JSON shape, was left alone on purpose: it is the prompt the triage agent is handed, not a restatement for readers. v16.2.0: total 56350 -> 56600 for the spec-freshness and reuse-tag contracts. Phase 3 step 3 had compared `state.run.lastAnalysisDigest` since it was written, against a key nothing ever set and that the state schema did not declare, so the staleness branch was unreachable and every run reported fresh by default. Phase 1 now persists the digest and a `base_commit` anchor, and step 3 gained the repo-drift half the digest cannot see: a reused document keeps a matching digest precisely because its evidence inputs did not change, while the code underneath it moved. The second contract is the Section 14 tag reaching development: Phase 2 carries it onto the todo as `sourceTag` and Phase 3 treats it as an instruction, which is what stops a Reuse row from being re-implemented. Compression came first and took the four additions from 380 tokens to 214, by moving every rationale clause out of the phase docs: why the commit anchor exists rather than a digest recomputation lives in this note and the CHANGELOG, and the schema descriptions carry the field semantics. The baseline had 9 tokens of headroom, so no addition of any size could have fit without a bump. 250 was the smallest step that clears it, leaving 45 tokens. phase-3 and phase-4 remain amber. v16.13.0: total 57600 -> 57700 for the code-graph injection and the fable-rung switch. Phase 1 gained Step 2.6 (query the graph, hand Explore a ranked starting set), Phase 7 gained the post-branch graph refresh, and Phase 0 Step 0 gained one line: a prefs switch that resolves every preferredModel: fable persona to opus for the run, which also collapses the Phase 4 Claude Code panel from three reviewers to two. Compression came first and mostly structurally: of roughly 1,630 tokens of new contract text, 1,310 never entered this budget at all - the whole code-graph contract lives in multi-agent-refs/features/code-graph.md (604) and the fable switch's scope table, per-host effects and cost-accounting consequence live in features/model-fallback.md (+707), leaving the phase docs with the call, the pref that gates it and the one fact an agent cannot infer. Phase 4 was compressed on top of that: its TLDR restated the reviewer matrix 270 lines below it, so 36 tokens came back and the doc nets +6 despite carrying two new clauses. One of those clauses is a correction rather than a feature - the consensus rule still said reviewerCount is 2 on Claude Code, which stopped being true when the third reviewer landed in 16.12.0, and the cross-CLI smoke never caught it because it reads the matrix line instead. 100 was the smallest step that clears it, leaving 54 tokens. phase-3 and phase-4 remain amber. v16.17.0: total 57700 -> 57850 for the platform-parity cross-check. Phase 4 gained Step 1.8: when dev-context carries a counterpart app repo, the review compares the change against the other platform on four axes. Compression came first and structurally, as always - of roughly 1,610 tokens of new contract text, 1,490 never entered this budget at all, because the four axes, the file cap, the graph-query recipe, the read-only prohibitions and the rule that an extractor miss may not be reported as an absence all live in multi-agent-refs/platform-parity.md. The step itself was then cut from ~200 tokens to 120 by deleting everything the ref already owns, leaving the trigger, the pointer and the two facts an agent must not infer: the counterpart repo is read-only, and parity findings are never blocking. The baseline had 13 tokens of headroom, so no addition of any size could have fit without a bump. 150 was the smallest step that clears it, leaving 35 tokens. phase-3 and phase-4 remain amber, and phase-4's structural-compression debt still stands. v16.20.0: phase-4-review max 14750 -> 15150 and total 58250 -> 60250 for the cross-round review delta, the scope self-check handoff and the circuit-breaker wiring. Compression came first and structurally: of roughly 3,900 tokens of new contract text, 2,700 never entered this budget at all - the previous-round-findings block, the scope-self-check block, the Step 3.8 state merge, telemetry and picker wording live in multi-agent-refs/features/review-delta.md, and the scope-check record rules and consumers in features/scope-check.md - so the phase docs carry the call, the pref that gates it and the exit table. The Phase 3 stability rule and the trigger-3 write were cut twice more before the bump; phase-3 stays under its max (8692/8950). Phase 4 is the first per-phase max raised since v10.9.0: the doc gained three steps that cannot be inferred (a per-round triage file, a prefix block that changes what reviewers report, and a halt condition), and its structural-compression debt (the inline triage JSON shape, named at v15.10.0) still stands and is the next candidate. 15150 and 60250 were the smallest steps that clear it, leaving 25 and 45 tokens. v16.23.0: phase-0-init max 12400 -> 12500 and total 60250 -> 60500 for the widget-registration call and the accounting gate. Phase 0 gained the `tiles` call and the exit-3 rule, Phase 7 gained the run report; together they are contract an agent cannot infer - which call registers this host's widget, and that a completion is refused without recorded spend. Compression came first and twice, taking the new prose from 472 tokens to 255: the per-host call list moved into tracker-contract.md "The card is not the widget" and the record-then-rerun recovery into "Accounting is a gate", both outside this budget, leaving the phase docs with the call and the one fact that cannot be looked up. 100 and 250 were the smallest steps that clear it, leaving 74 and 40 tokens. phase-3 and phase-4 remain amber. v16.24.0: total 60500 -> 60750 for visual evidence. Four phase docs gained one instruction each that cannot be inferred: Phase 0 keeps the issue's own images as the pre-fix evidence, Phase 3 captures the fixed state (there and not Phase 5, because every autopilot entry and every local workspace drops Phase 5), Phase 5 hosts the flow recording when it runs, and Phase 6 blocks on a required artefact that is neither attached nor explained. Compression came first and twice, 42 tokens back, and the contract itself never entered this budget: the trigger matrix, the three video tiers, the size-degradation ladder and both render shapes live in multi-agent-refs/features/visual-evidence.md. phase-0-init cleared its own max without a bump. 250 was the smallest step that clears the aggregate. phase-3 and phase-4 remain amber. v17.0.0: phase-0-init max 13000 -> 13100 and total 62400 -> 62500 for the evidence-verdict writer. Phase 0 Step 7.7 probed with `--platform "$PLATFORM"`, a variable no phase document ever assigned, and it was gated on `visualEvidence.required`, which no phase document ever wrote - five readers, zero writers - so the step, Phase 3's capture and Phase 6's blocker were all unreachable and the pipeline reported nothing wrong. The step now writes the verdict and derives the platform from the stack, skipping the probe with a recorded reason when there is no device platform rather than passing the empty string the probe refuses with exit 2. Compression came first and three times, 30 tokens back from the Step 7.7 index rule that restated Step 7.5 verbatim and 55 from the new block itself; the reasoning never entered this budget, because who writes the verdict and how the platform is derived live in features/visual-evidence.md sections 1a and 1b. phase-3-dev max 9250 -> 9300 in the same change: it reads the platform back from state and re-decides the provisional verdict before capturing, which is the half of the fix that makes Phase 3 honest rather than merely reachable. Compressed three times first, 29 tokens back, by pointing its Phase-5 rationale and its tier mapping at visual-evidence.md sections 3 and 4.3 where both already live. 100, 50 and 150 were the smallest steps that clear it, leaving 24, 15 and 26 tokens. phase-3 and phase-4 remain amber. v17.1.0: total 62550 -> 62600 for the Figma/toolkit MCP distinction and web as an evidence platform. Three phase docs said "MCP forbidden" without qualifying it, while the gate that enforces it (smoke-no-mcp-in-dev-phases.sh) has always matched `figma` and nothing else - so the prose banned the screenshot, xcodebuild and UI-test tools that Phase 3 Steps 3.4 and 3.55 actually call, which is one way a run reaches Phase 7 with no evidence. Phase 0 gained one `web` arm in the platform derivation, now that run-ui-tests.sh has a web arm to derive it for. Compression came first and three times, taking the new prose from 175 tokens to 30: the reasoning moved to rules.md, whose own seven-row Figma phase matrix was deleted in the same pass because it duplicated rules/figma-pipeline.md "Phase access matrix" two paragraphs below this file's own instruction not to duplicate that rule file - 74 tokens back there, which is why phase-3-dev cleared its max without a bump (9298/9300). 50 was the smallest step that clears the aggregate, leaving 37 tokens. phase-3 and phase-4 remain amber. v17.1.0 (2): total 62600 -> 62700 for the plan reaching the task widget. Phase 2 computed tasks[], their order and their dependsOn[] edges, stored them, and used them to drive Phase 3's ready-task picker - and none of it was visible on the surface the user actually watches; the card had drawn sub-phases for releases, the widget never had. Phase 2 gains one call. Compression came first and twice: the tasks[]-to-todos[] jq blob left the phase doc for plan-todos.sh `set`, which now accepts a planning-output document directly (-28, and it removes a mapping two files defined, of which this was the untested copy), and the new step's own prose was cut from 116 tokens to 61. The parsing of the plan itself never entered this budget - it lives in phase-tracker.sh `plan`, which owns the sub-phase structure it writes. 100 was the smallest step that clears it, leaving 75 tokens. phase-3 and phase-4 remain amber. v17.5.0: phase-0-init max 13100 -> 13150 for the deferred widget registration, the dev-context step and two more exit-gate assertions. Compression came first and seven times, 492 tokens reclaimed before the number moved: the TLDR restated the step headings under it, the exit-gate list restated the script's own header comment, and the clarifier cost note, the branch-collision probe rationale, the fetch-fail host explanation, the multi-repo write-state race and the baseline unknown-vs-green warning all restate something already authoritative in agents/task-clarifier.md, phases/operations.md or phase0-exit-gate.mjs. The three additions are contract an agent cannot infer: that only Phase 0 is registered at Step -1 and the rest at 7.5 with `tiles --new`, that the dev-context picker runs between project and branch and writes siblings[] even when empty, and that a one-option AskUserQuestion is refused by the host along with every question batched with it. The reasoning for the last one never entered this budget - it lives in picker-contract.md "Two options or it is not a question". 50 was the smallest step that clears it, leaving 28 tokens; the aggregate needed no bump and sits at 62698/62700. phase-3 and phase-4 remain amber. v17.5.0 (2): phase-0-init max 13150 -> 13300 and total 62700 -> 62900 for the workspace question. Phase 0 gained Step 5b: where the branch lives was decided by a flag and by a command name, never by a question, so a user who saw a run improvise "Worktree / Lokal" once took it for a shipped picker and concluded /multi-agent:local was redundant - while it was the only way to reach local mode at all. Compression came first and three times, 156 tokens reclaimed before the number moved and the step itself cut from 426 tokens to 181: the ask-choice index rule in Step 7.5 restated modes.md "Pipeline depth" in full, and the question wording, the two options and what local costs now live in modes.md "Local Mode", outside this budget. What the phase doc carries is what an agent cannot infer - that it runs after Step 4 and before Step 6b and 7.5, who is exempt, and that autopilot resolves it to a worktree rather than skipping it, because an unattended commit in the user's own checkout is what worktrees exist to prevent. The state field is the other half: localMode alone cannot say whether anyone decided, since false is both a chosen worktree and one nothing asked about, and phase0-exit-gate.mjs now refuses to close Phase 0 without workspaceSource. 150 and 200 were the smallest steps that clear it, leaving 32 and 56 tokens. phase-3 and phase-4 remain amber. v17.5.0 (3): phase-0-init max 13300 -> 13400 and total 62900 -> 63000 for base-branch evidence. Step 3 asked one question with a list it could not vouch for: `git fetch origin` ran, its exit code was discarded, and `git branch -r` printed the remote-tracking cache either way, so a restricted network produced a weeks-old local list presented as the remote's answer. And the answer was usually derivable - an issue carrying a target version, or linking a separate issue that represents the release, already names the branch on a repo whose release branches encode the version - and nothing derived it. Rule 5 now captures the exit code and rule 5b hands the list plus the issue's version fields and links to base-branch-candidates.mjs. Compression came first and six times, 1,118 characters reclaimed across this step before the number moved: the one-row picker rule and the not-skippable rule both restated picker-contract.md, the autopilot resolution order and the whole rationale for admitting version-carrying branches moved into features/base-branch-evidence.md, and the fetch-fail persistence block was four sentences for one instruction. The feature's own reasoning never entered this budget at all - the evidence sources, the learned convention, the picker contract, the autopilot fencing and the state shape are ~1,900 tokens living in that ref. What the phase doc carries is the call and the two facts an agent cannot infer: that the fetch exit code decides whether the list may be called remote, and that the branch filter needs a version alternative because a word list that discards is the prefix table this replaces. 100 was the smallest step that clears both, leaving 51 and 61 tokens. phase-3 and phase-4 remain amber. v17.6.0: phase-3-dev max 9300 -> 9450 and total 63000 -> 63150 for package-manager resolution. The node-shaped arms typed `npm` into two command lines, so a repo on pnpm, yarn or bun failed in Phase 3 with a worktree and a branch already created - or, worse, npm resolved against a lock file it does not own and the run continued on a tree the repo's own tooling would never have produced. Both arms now call package-manager.mjs, which prints the line to run. A resolver invocation is inherently longer than the four characters it replaces, and phase-3-dev had 2 tokens of headroom (9298/9300), so no addition of any size could have fit without a bump. Compression came first and twice, taking the new prose from 430 characters to 160 and trimming the build arm's tail by 140: the resolution order, the two-lock-file rule, the per-manager command shapes, the exit-3 contract and the eval-safety argument all live in features/package-manager.md, outside this budget. What the phase doc carries is the call and the one fact an agent cannot infer - that exit 3 means the repo declares no such script, so the step is skipped and said, never substituted. phase-4-review was compressed rather than raised in the same pass: its Gate 3 comment named npm as though it were the only node test command, and the corrected line is 64 characters SHORTER than the one it replaces, so the doc nets -64 while becoming true (15150/15150). 150 was the smallest step that clears phase-3-dev, leaving 51 tokens; 150 clears the aggregate, leaving 133. phase-3 and phase-4 remain amber.
-
-Recalibrated at v19.0.0 for the six-phase contract. Eight documents became six: `phase-1-analysis` + `phase-2-planning` merged into `phase-1-plan` (10000), `phase-3-dev` absorbed the Stage 1 verify gates that `phase-4-review` used to run a second time and became `phase-2-dev` (10650), the rest of review plus the whole of the old test phase became `phase-3-review` (17200), and commit and report kept their contents at their new numbers (6500, 5550). `phase-0-init` is untouched at 13400 - it was the reason analysis folded into planning rather than into init, because init plus analysis would have needed roughly 18000 and the two-sided rule refuses a ceiling that far above the measurement. Every ceiling here was measured after the merge rather than summed from the two documents that fed it: summing would have banked the duplicated build prose the merge deleted. Total 63150 -> 63300, which is the aggregate the six measurements actually need, not the old eight-phase total carried forward.

package/pipeline/skills/shared/external/agentflow/SKILL.md

@@ -1,199 +0,0 @@
----
-name: agentflow
-description: "Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution. Use when development should be driven from a Kanban board rather than from a single prompt."
-risk: safe
-source: community
-date_added: "2026-04-02"
----
-
-# AgentFlow
-
-## Overview
-
-AgentFlow turns your existing Kanban board into a fully autonomous AI development pipeline. Instead of building custom orchestration infrastructure, it treats your project management tool (Asana, GitHub Projects, Linear) as a distributed state machine  -  tasks move through stages, AI agents read and write state via comments, and humans intervene through the same UI they already use.
-
-The result is complete pipeline observability from your phone, free crash recovery (state lives in your PM tool, not in memory), and human override at any point by dragging a card.
-
-## When to Use This Skill
-
-- Use when you need to orchestrate multiple Claude Code workers across a full development lifecycle (build, review, test, integrate)
-- Use when you want deterministic quality gates (tsc/eslint/tests) before AI review on AI-generated code
-- Use when you want full pipeline visibility from your Kanban board or phone
-- Use when running a solo or team project that needs autonomous task dispatch with cost tracking
-- Use when you need crash-proof orchestration that survives session restarts
-
-## Core Concepts
-
-### 7-Stage Kanban Pipeline
-
-Tasks flow through: Backlog, Research, Build, Review, Test, Integrate, Done. Each stage has specific gates. The Kanban board IS the orchestration layer  -  no separate database, no message queue, no custom infrastructure.
-
-### Stateless Orchestrator
-
-A crontab-driven one-shot sweep runs every 15 minutes. No daemon, no session dependency. If it crashes, the next sweep picks up where it left off because all state lives in your PM tool.
-
-### Deterministic Before Probabilistic
-
-Hard gates (tsc + eslint + tests) run before any AI review, catching roughly 60% of issues at near-zero cost. AI review comes after, as a second layer.
-
-### Adversarial Review
-
-A different AI agent reviews code and must list 3 things wrong before deciding to pass. This prevents rubber-stamp approvals.
-
-### Transitive Priority Dispatch
-
-Tasks that unblock the most downstream work get built first, automatically computing the critical path.
-
-## Skills / Commands
-
-### `/spec-to-board`
-Decomposes a SPEC.md into atomic tasks on your Kanban board with dependencies mapped.
-
-### `/sdlc-orchestrate`
-Dispatches tasks to workers based on transitive priority and conflict detection. Runs as a crontab sweep.
-
-### `/sdlc-worker --slot <N>`
-Runs a worker in a terminal slot that picks up tasks, builds code, and creates PRs. Run 3-4 workers in parallel.
-
-### `/sdlc-health`
-Real-time pipeline status dashboard showing current stage, assigned agent, retry count, and accumulated cost for every task.
-
-### `/sdlc-stop`
-Graceful shutdown: active workers finish their current task, unstarted tasks return to Backlog.
-
-## Step-by-Step Guide
-
-### 1. Write Your Spec
-
-Create a `SPEC.md` for your project describing what you want to build.
-
-### 2. Decompose Into Tasks
-
-```
-claude -p "/spec-to-board"
-```
-
-This reads your SPEC.md, decomposes it into atomic tasks, maps dependencies, and creates them on your Kanban board.
-
-### 3. Start Workers
-
-Open 3-4 terminal windows, each as a worker slot:
-
-```bash
-# Terminal 2  -  Builder
-claude -p "/sdlc-worker --slot T2"
-
-# Terminal 3  -  Builder
-claude -p "/sdlc-worker --slot T3"
-
-# Terminal 4  -  Reviewer
-claude -p "/sdlc-worker --slot T4"
-
-# Terminal 5  -  Tester
-claude -p "/sdlc-worker --slot T5"
-```
-
-### 4. Start the Orchestrator
-
-```bash
-# Add to crontab (runs every 15 minutes)
-crontab -e
-# Add: */15 * * * * ~/.claude/sdlc/agentflow-cron.sh >> /tmp/agentflow-orchestrate.log 2>&1
-```
-
-### 5. Monitor and Intervene
-
-Open your Kanban board on your phone. Watch tasks flow through the pipeline. Drag any card to "Needs Human" to intervene. Run `/sdlc-health` for a terminal dashboard.
-
-### 6. Stop the Pipeline
-
-```
-claude -p "/sdlc-stop"
-```
-
-## Quality Gates
-
-Each stage enforces specific gates before promotion:
-
-- **Build to Review**: `tsc` + `eslint` + `npm test` must all pass (deterministic)
-- **Review to Test**: Adversarial reviewer must list 3 issues before passing
-- **Test to Integrate**: 80% coverage threshold on new files
-- **Integrate to Done**: Full test suite on main after merge; auto-reverts on failure
-
-## Cost Tracking
-
-Per-task cost tracking with stage ceilings (Sonnet defaults):
-
-- Research: ~$0.10
-- Build: ~$0.40
-- Review: ~$0.10
-- Test: ~$0.05
-- Integrate: ~$0.03
-
-Automatic guardrails: warning at $3/$8, hard stop at $10/$20 (Sonnet/Opus) with human escalation.
-
-## Safety and Recovery
-
-- **Auto-revert**: Integration failures trigger `git revert` (new commit, never force-push)
-- **Blocked tasks**: After 2 failed attempts, tasks escalate to human review
-- **Dead agent detection**: Heartbeat every 5 min, reassign after 10 min timeout
-- **Graceful shutdown**: `/sdlc-stop` drains workers, returns unstarted tasks to backlog
-- **Scope creep detection**: PR diff files compared against predicted files list
-- **Spec drift detection**: SHA-256 hash comparison catches requirement changes mid-sprint
-
-## Installation
-
-```bash
-# Clone the repo
-git clone https://github.com/UrRhb/agentflow.git
-
-# Copy skills and prompts to your Claude Code config
-cp -r agentflow/skills/* ~/.claude/skills/
-cp -r agentflow/prompts/* ~/.claude/sdlc/prompts/
-cp agentflow/conventions.md ~/.claude/sdlc/conventions.md
-```
-
-Or install as a Claude Code plugin:
-
-```bash
-/plugin marketplace add UrRhb/agentflow
-/plugin install agentflow
-```
-
-## Best Practices
-
-- Do: Write a clear SPEC.md before running `/spec-to-board`
-- Do: Start with 3-4 workers for a typical project
-- Do: Monitor from your Kanban board and drag cards to "Needs Human" when needed
-- Do: Review LEARNINGS.md periodically  -  it captures common failure patterns
-- Don't: Skip the deterministic quality gates  -  they catch most issues cheaply
-- Don't: Force-push to main  -  AgentFlow uses `git revert` for safety
-- Don't: Run more workers than your project's parallelism supports
-
-## Troubleshooting
-
-### Problem: Worker appears stuck or dead
-**Symptoms:** Task card hasn't moved in 15+ minutes, no new comments
-**Solution:** The orchestrator detects dead agents via heartbeat and reassigns after 10 minutes. If the issue persists, run `/sdlc-health` to check status and manually drag the card back to Backlog.
-
-### Problem: Cost guardrail triggered
-**Symptoms:** Task moved to "Needs Human" with COST:CRITICAL tag
-**Solution:** Review the task's comment thread for accumulated context. Decide whether to increase the budget, simplify the task, or split it into smaller pieces.
-
-### Problem: Integration test failure after merge
-**Symptoms:** Task auto-reverted from main
-**Solution:** The auto-revert preserves main stability. Check the task's retry context in comments, which carries what was tried and what failed. The next worker assigned will use this context.
-
-## Related Skills
-
-- `@brainstorming` - Use before AgentFlow to design your SPEC.md
-- `@writing-plans` - Complements spec writing for task decomposition
-- `@test-driven-development` - Works well with AgentFlow's quality gates
-- `@subagent-driven-development` - Alternative approach to multi-agent coordination
-
-## Additional Resources
-
-- [AgentFlow Repository](https://github.com/UrRhb/agentflow)
-- [Architecture Documentation](https://github.com/UrRhb/agentflow/blob/main/docs/architecture.md)
-- [Gap Registry (45 failure modes)](https://github.com/UrRhb/agentflow/blob/main/docs/gap-registry.md)
-- [Getting Started Guide](https://github.com/UrRhb/agentflow/blob/main/docs/getting-started.md)

package/pipeline/skills/shared/external/android-ui-verification/SKILL.md

@@ -1,66 +0,0 @@
----
-name: android-ui-verification
-description: "Automated end-to-end UI testing and verification on an Android Emulator using ADB. Use when an Android build needs driving on an emulator to verify its UI end to end."
-risk: safe
-source: community
-date_added: "2026-02-28"
----
-
-# Android UI Verification Skill
-
-This skill provides a systematic approach to testing React Native applications on an Android emulator using ADB commands. It allows for autonomous interaction, state verification, and visual regression checking.
-
-## When to Use
-- Verifying UI changes in React Native or Native Android apps.
-- Autonomous debugging of layout issues or interaction bugs.
-- Ensuring feature functionality when manual testing is too slow.
-- Capturing automated screenshots for PR documentation.
-
-## 🛠 Prerequisites
-- Android Emulator running.
-- `adb` installed and in PATH.
-- Application in debug mode for logcat access.
-
-## 🚀 Workflow
-
-### 1. Device Calibration
-Before interacting, always verify the screen resolution to ensure tap coordinates are accurate.
-```bash
-adb shell wm size
-```
-*Note: Layouts are often scaled. Use the physical size returned as the base for coordinate calculations.*
-
-### 2. UI Inspection (State Discovery)
-Use the `uiautomator` dump to find the exact bounds of UI elements (buttons, inputs).
-```bash
-adb shell uiautomator dump /sdcard/view.xml && adb pull /sdcard/view.xml ./artifacts/view.xml
-```
-Search the `view.xml` for `text`, `content-desc`, or `resource-id`. The `bounds` attribute `[x1,y1][x2,y2]` defines the clickable area.
-
-### 3. Interaction Commands
-- **Tap**: `adb shell input tap <x> <y>` (Use the center of the element bounds).
-- **Swipe**: `adb shell input swipe <x1> <y1> <x2> <y2> <duration_ms>` (Used for scrolling).
-- **Text Input**: `adb shell input text "<message>"` (Note: Limited support for special characters).
-- **Key Events**: `adb shell input keyevent <code_id>` (e.g., 66 for Enter).
-
-### 4. Verification & Reporting
-#### Visual Verification
-Capture a screenshot after interaction to confirm UI changes.
-```bash
-adb shell screencap -p /sdcard/screen.png && adb pull /sdcard/screen.png ./artifacts/test_result.png
-```
-
-#### Analytical Verification
-Monitor the JS console logs in real-time to detect errors or log successes.
-```bash
-adb logcat -d | grep "ReactNativeJS" | tail -n 20
-```
-
-#### Cleanup
-Always store generated files in the `artifacts/` folder to satisfy project organization rules.
-
-## 💡 Best Practices
-- **Wait for Animations**: Always add a short sleep (e.g., 1-2s) between interaction and verification.
-- **Center Taps**: Calculate the arithmetic mean of `[x1,y1][x2,y2]` for the most reliable tap target.
-- **Log Markers**: Use distinct log messages in the code (e.g., `✅ Action Successful`) to make `grep` verification easy.
-- **Fail Fast**: If a `uiautomator dump` fails or doesn't find the expected text, stop and troubleshoot rather than blind-tapping.