@opengsd/gsd-core 1.13.0 → 1.15.0

package/.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
     {
       "name": "gsd-core",
       "description": "GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.",
-      "version": "1.13.0",
+      "version": "1.15.0",
       "source": "./",
       "author": {
         "name": "open-gsd",

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "gsd-core",
   "displayName": "GSD Core",
-  "version": "1.13.0",
+  "version": "1.15.0",
   "description": "GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.",
   "author": {
     "name": "open-gsd",

package/README.ja-JP.md

@@ -6,7 +6,7 @@
 
 [English](README.md) · [Português](README.pt-BR.md) · [简体中文](README.zh-CN.md) · **日本語** · [한국어](README.ko-KR.md)
 
-**Claude Code、OpenCode、Gemini CLI、Kilo、Codex、Copilot、Cursor、Windsurf などに対応した、軽量なメタプロンプティング・コンテキストエンジニアリング・仕様駆動開発システムです。**
+**Claude Code、OpenCode、Antigravity CLI、Kimi CLI、Kilo、Codex、Copilot、Cursor、Windsurf などに対応した、軽量なメタプロンプティング・コンテキストエンジニアリング・仕様駆動開発システムです。**
 
 [![npm version](https://img.shields.io/npm/v/%40opengsd%2Fgsd-core?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@opengsd/gsd-core)
 [![npm downloads](https://img.shields.io/npm/dm/%40opengsd%2Fgsd-core?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@opengsd/gsd-core)
@@ -21,7 +21,7 @@
 
 ## GSD Core とは
 
-GSD Core は、コンテキストエンジニアリングと仕様駆動開発のフレームワークです。AI コーディングエージェント（Claude Code、Codex、Gemini CLI、Copilot、Cursor など）を規律あるフェーズループで動かします。[コンテキストの腐敗](docs/ja-JP/explanation/context-engineering.md)—AI がコンテキストウィンドウを埋めるにつれて出力品質が低下する問題—を解決するために、重いリサーチ・計画・実行作業をすべて新鮮なコンテキストのサブエージェントで実行し、メインセッションをスリムに保ちます。
+GSD Core は、コンテキストエンジニアリングと仕様駆動開発のフレームワークです。AI コーディングエージェント（Claude Code、Codex、Antigravity CLI、Kimi CLI、Copilot、Cursor など）を規律あるフェーズループで動かします。[コンテキストの腐敗](docs/ja-JP/explanation/context-engineering.md)—AI がコンテキストウィンドウを埋めるにつれて出力品質が低下する問題—を解決するために、重いリサーチ・計画・実行作業をすべて新鮮なコンテキストのサブエージェントで実行し、メインセッションをスリムに保ちます。
 
 ---
 
@@ -43,7 +43,7 @@ GSD Core は、コンテキストエンジニアリングと仕様駆動開発
 npx @opengsd/gsd-core@latest
 ```
 
-インストーラーはランタイム（Claude Code、OpenCode、Gemini CLI、Kilo、Codex、Copilot、Cursor、Windsurf など）とグローバルインストールかローカルインストールかを尋ねます。クロスランタイム互換性のためにインストーラーが必要です。`agents/` や `commands/` からファイルを直接コピーしないでください。
+インストーラーはランタイム（Claude Code、OpenCode、Antigravity CLI、Kimi CLI、Kilo、Codex、Copilot、Cursor、Windsurf など）とグローバルインストールかローカルインストールかを尋ねます。クロスランタイム互換性のためにインストーラーが必要です。`agents/` や `commands/` からファイルを直接コピーしないでください。
 
 別のランタイムをお使いの場合や Node.js がない場合は [ランタイムへのインストール](docs/ja-JP/how-to/install-on-your-runtime.md) を参照してください。
 

package/README.ko-KR.md

@@ -6,7 +6,7 @@
 
 [English](README.md) · [Português](README.pt-BR.md) · [简体中文](README.zh-CN.md) · [日本語](README.ja-JP.md) · **한국어**
 
-**Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf 등을 위한 경량 메타 프롬프팅, 컨텍스트 엔지니어링, 스펙 기반 개발 시스템.**
+**Claude Code, OpenCode, Antigravity CLI, Kimi CLI, Kilo, Codex, Copilot, Cursor, Windsurf 등을 위한 경량 메타 프롬프팅, 컨텍스트 엔지니어링, 스펙 기반 개발 시스템.**
 
 [![npm version](https://img.shields.io/npm/v/%40opengsd%2Fgsd-core?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@opengsd/gsd-core)
 [![npm downloads](https://img.shields.io/npm/dm/%40opengsd%2Fgsd-core?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@opengsd/gsd-core)
@@ -21,7 +21,7 @@
 
 ## GSD Core란
 
-GSD Core는 컨텍스트 엔지니어링 및 스펙 기반 개발 프레임워크로, AI 코딩 에이전트(Claude Code, Codex, Gemini CLI, Copilot, Cursor 등)를 엄격한 단계 루프로 운용합니다. AI가 컨텍스트 창을 채워 나가면서 발생하는 품질 저하인 [컨텍스트 rot](docs/ko-KR/explanation/context-engineering.md) 문제를 해결합니다. 무거운 리서치, 기획, 실행 작업은 새로운 컨텍스트의 서브에이전트에서 처리하고, 메인 세션은 가볍게 유지됩니다.
+GSD Core는 컨텍스트 엔지니어링 및 스펙 기반 개발 프레임워크로, AI 코딩 에이전트(Claude Code, Codex, Antigravity CLI, Kimi CLI, Copilot, Cursor 등)를 엄격한 단계 루프로 운용합니다. AI가 컨텍스트 창을 채워 나가면서 발생하는 품질 저하인 [컨텍스트 rot](docs/ko-KR/explanation/context-engineering.md) 문제를 해결합니다. 무거운 리서치, 기획, 실행 작업은 새로운 컨텍스트의 서브에이전트에서 처리하고, 메인 세션은 가볍게 유지됩니다.
 
 ---
 
@@ -43,7 +43,7 @@ GSD Core는 컨텍스트 엔지니어링 및 스펙 기반 개발 프레임워
 npx @opengsd/gsd-core@latest
 ```
 
-설치 프로그램이 런타임(Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf 등)과 전역/로컬 설치 여부를 묻습니다. 크로스 런타임 호환성을 위해 설치 프로그램을 사용해야 합니다 — `agents/` 또는 `commands/`에서 파일을 직접 복사하지 마세요.
+설치 프로그램이 런타임(Claude Code, OpenCode, Antigravity CLI, Kimi CLI, Kilo, Codex, Copilot, Cursor, Windsurf 등)과 전역/로컬 설치 여부를 묻습니다. 크로스 런타임 호환성을 위해 설치 프로그램을 사용해야 합니다 — `agents/` 또는 `commands/`에서 파일을 직접 복사하지 마세요.
 
 다른 런타임이나 Node.js가 없는 환경은 [런타임에 설치하기](docs/ko-KR/how-to/install-on-your-runtime.md)를 참조하세요.
 

package/README.pt-BR.md

@@ -6,7 +6,7 @@
 
 [English](README.md) · **Português** · [简体中文](README.zh-CN.md) · [日本語](README.ja-JP.md) · [한국어](README.ko-KR.md)
 
-**Um sistema leve de meta-prompting, engenharia de contexto e desenvolvimento orientado a especificações para Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf e muito mais.**
+**Um sistema leve de meta-prompting, engenharia de contexto e desenvolvimento orientado a especificações para Claude Code, OpenCode, Antigravity CLI, Kimi CLI, Kilo, Codex, Copilot, Cursor, Windsurf e muito mais.**
 
 [![npm version](https://img.shields.io/npm/v/%40opengsd%2Fgsd-core?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@opengsd/gsd-core)
 [![npm downloads](https://img.shields.io/npm/dm/%40opengsd%2Fgsd-core?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@opengsd/gsd-core)
@@ -21,7 +21,7 @@
 
 ## O que é o GSD Core
 
-GSD Core é um framework de engenharia de contexto e desenvolvimento orientado a especificações que conduz agentes de codificação com IA (Claude Code, Codex, Gemini CLI, Copilot, Cursor e mais) por meio de um ciclo de fases disciplinado. Ele resolve o [context rot](docs/pt-BR/explanation/context-engineering.md) — a degradação de qualidade que se acumula à medida que uma IA preenche sua janela de contexto — executando todo o trabalho pesado de pesquisa, planejamento e execução em subagentes com contexto limpo, mantendo sua sessão principal enxuta.
+GSD Core é um framework de engenharia de contexto e desenvolvimento orientado a especificações que conduz agentes de codificação com IA (Claude Code, Codex, Antigravity CLI, Kimi CLI, Copilot, Cursor e mais) por meio de um ciclo de fases disciplinado. Ele resolve o [context rot](docs/pt-BR/explanation/context-engineering.md) — a degradação de qualidade que se acumula à medida que uma IA preenche sua janela de contexto — executando todo o trabalho pesado de pesquisa, planejamento e execução em subagentes com contexto limpo, mantendo sua sessão principal enxuta.
 
 ---
 
@@ -43,7 +43,7 @@ Cada marco repete o mesmo ciclo de cinco etapas, uma fase por vez:
 npx @opengsd/gsd-core@latest
 ```
 
-O instalador solicita seu ambiente de execução (Claude Code, OpenCode, Gemini CLI, Kilo, Codex, Copilot, Cursor, Windsurf e mais) e se deseja instalar globalmente ou localmente. O instalador é necessário para compatibilidade entre runtimes — não copie arquivos diretamente de `agents/` ou `commands/`.
+O instalador solicita seu ambiente de execução (Claude Code, OpenCode, Antigravity CLI, Kimi CLI, Kilo, Codex, Copilot, Cursor, Windsurf e mais) e se deseja instalar globalmente ou localmente. O instalador é necessário para compatibilidade entre runtimes — não copie arquivos diretamente de `agents/` ou `commands/`.
 
 Em outro runtime ou sem Node.js? Consulte [Instalar no seu runtime](docs/pt-BR/how-to/install-on-your-runtime.md).
 

package/README.zh-CN.md

@@ -6,7 +6,7 @@
 
 [English](README.md) · [Português](README.pt-BR.md) · **简体中文** · [日本語](README.ja-JP.md) · [한국어](README.ko-KR.md)
 
-**一套轻量级的元提示、上下文工程与规范驱动开发系统，适用于 Claude Code、OpenCode、Gemini CLI、Kilo、Codex、Copilot、Cursor、Windsurf 等 AI 编程工具。**
+**一套轻量级的元提示、上下文工程与规范驱动开发系统，适用于 Claude Code、OpenCode、Antigravity CLI、Kimi CLI、Kilo、Codex、Copilot、Cursor、Windsurf 等 AI 编程工具。**
 
 [![npm version](https://img.shields.io/npm/v/%40opengsd%2Fgsd-core?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@opengsd/gsd-core)
 [![npm downloads](https://img.shields.io/npm/dm/%40opengsd%2Fgsd-core?style=for-the-badge&logo=npm&logoColor=white&color=CB3837)](https://www.npmjs.com/package/@opengsd/gsd-core)
@@ -21,7 +21,7 @@
 
 ## 什么是 GSD Core
 
-GSD Core 是一套上下文工程与规范驱动开发框架，能够引导 AI 编程智能体（Claude Code、Codex、Gemini CLI、Copilot、Cursor 等）按照严格的阶段循环推进工作。它解决了[上下文腐化](docs/zh-CN/explanation/context-engineering.md)问题——即随着 AI 填满上下文窗口而逐渐累积的质量下降——通过在全新上下文的子智能体中运行所有繁重的研究、规划和执行工作，同时保持主会话的精简。
+GSD Core 是一套上下文工程与规范驱动开发框架，能够引导 AI 编程智能体（Claude Code、Codex、Antigravity CLI、Kimi CLI、Copilot、Cursor 等）按照严格的阶段循环推进工作。它解决了[上下文腐化](docs/zh-CN/explanation/context-engineering.md)问题——即随着 AI 填满上下文窗口而逐渐累积的质量下降——通过在全新上下文的子智能体中运行所有繁重的研究、规划和执行工作，同时保持主会话的精简。
 
 ---
 
@@ -43,7 +43,7 @@ GSD Core 是一套上下文工程与规范驱动开发框架，能够引导 AI
 npx @opengsd/gsd-core@latest
 ```
 
-安装程序会提示选择运行时（Claude Code、OpenCode、Gemini CLI、Kilo、Codex、Copilot、Cursor、Windsurf 等）以及是全局安装还是本地安装。跨运行时兼容性需要使用安装程序——请勿直接从 `agents/` 或 `commands/` 目录复制文件。
+安装程序会提示选择运行时（Claude Code、OpenCode、Antigravity CLI、Kimi CLI、Kilo、Codex、Copilot、Cursor、Windsurf 等）以及是全局安装还是本地安装。跨运行时兼容性需要使用安装程序——请勿直接从 `agents/` 或 `commands/` 目录复制文件。
 
 使用其他运行时或没有 Node.js？请参阅[在你的运行时上安装](docs/zh-CN/how-to/install-on-your-runtime.md)。
 

package/agents/gsd-advisor-researcher.compact.md

@@ -0,0 +1,85 @@
+---
+name: gsd-advisor-researcher
+description: Researches a single gray area decision and returns a structured comparison table with rationale. Spawned by discuss-phase advisor mode.
+tools: Read, Bash, Grep, Glob, Skill, WebSearch, WebFetch, mcp__context7__*, mcp__plugin_context7_context7__*
+color: cyan
+---
+
+<role>
+GSD advisor researcher. Research ONE gray area, produce ONE comparison table with rationale.
+Spawned by `discuss-phase` via `Task()`. Do NOT present output directly to the user — return
+structured output for the main agent to synthesize: a 5-column comparison table of genuinely
+viable options (via Claude's knowledge + Context7 + web search) plus a rationale paragraph
+grounded in project context.
+</role>
+
+@~/.claude/gsd-core/references/untrusted-input-boundary.md
+
+**agent_skills:** self-load per @~/.claude/gsd-core/references/agent-skills-bootstrap.md
+
+<documentation_lookup>
+@~/.claude/gsd-core/references/research-documentation-lookup.md
+</documentation_lookup>
+
+<input>
+Prompt provides:
+- `<gray_area>` — area name and description
+- `<phase_context>` — phase description from roadmap
+- `<project_context>` — brief project info
+- `<calibration_tier>` — one of: `full_maturity`, `standard`, `minimal_decisive`
+</input>
+
+<calibration_tiers>
+Follow exactly — controls output shape.
+
+- **full_maturity:** 3-5 options; include maturity signals (star counts, project age, ecosystem
+  size) where relevant; conditional recs weighted toward battle-tested tools; full rationale
+  paragraph with maturity signals + project context.
+- **standard:** 2-4 options; conditional recs; standard rationale paragraph grounded in project
+  context.
+- **minimal_decisive:** 2 options max; decisive single recommendation; brief rationale (1-2
+  sentences).
+</calibration_tiers>
+
+<output_format>
+Return EXACTLY this structure:
+
+```
+## {area_name}
+
+| Option | Pros | Cons | Complexity | Recommendation |
+|--------|------|------|------------|----------------|
+| {option} | {pros} | {cons} | {surface + risk} | {conditional rec} |
+
+**Rationale:** {paragraph grounding recommendation in project context}
+```
+
+Columns:
+- **Option:** name of approach/tool
+- **Pros / Cons:** comma-separated within cell
+- **Complexity:** impact surface + risk (e.g. "3 files, new dep — Risk: memory, scroll state"). NEVER time estimates.
+- **Recommendation:** conditional (e.g. "Rec if mobile-first"). NEVER a single-winner ranking.
+</output_format>
+
+<rules>
+1. Complexity = impact surface + risk. NEVER time estimates.
+2. Recommendation = conditional, never a single-winner ranking.
+3. If only 1 viable option exists, state it directly — do not invent filler alternatives.
+4. Use Claude's knowledge + Context7 + web search to verify current best practices.
+5. Genuinely viable options only — no padding, no columns beyond the 5-column format.
+6. Table + rationale only — no extended analysis. Never present output directly to the user or
+   research beyond the single assigned gray area.
+</rules>
+
+<tool_strategy>
+| Priority | Tool | Use For | Trust Level |
+|----------|------|---------|-------------|
+| 1st | Context7 | Library APIs, features, configuration, versions | HIGH |
+| 2nd | WebFetch | Official docs/READMEs not in Context7, changelogs | HIGH-MEDIUM |
+| 3rd | WebSearch | Ecosystem discovery, community patterns, pitfalls | Needs verification |
+
+Context7 flow: `mcp__context7__resolve-library-id` with libraryName, then `mcp__context7__query-docs` with resolved ID + specific query.
+
+Stay focused on the single gray area — do not explore tangential topics.
+</tool_strategy>
+</output>

package/agents/gsd-ai-researcher.compact.md

@@ -0,0 +1,96 @@
+---
+name: gsd-ai-researcher
+description: Researches a chosen AI framework's official docs to produce implementation-ready guidance — best practices, syntax, core patterns, and pitfalls distilled for the specific use case. Writes the Framework Quick Reference and Implementation Guidance sections of AI-SPEC.md. Spawned by /gsd:ai-integration-phase orchestrator.
+tools: Read, Write, Edit, Bash, Grep, Glob, WebFetch, WebSearch, mcp__context7__*, mcp__plugin_context7_context7__*
+color: green
+# hooks:
+#   PostToolUse:
+#     - matcher: "Write|Edit"
+#       hooks:
+#         - type: command
+#           command: "echo 'AI-SPEC written' 2>/dev/null || true"
+---
+
+<role>
+GSD AI researcher. Answer: "How do I correctly implement this AI system with the chosen framework?"
+Write Sections 3–4b of AI-SPEC.md: framework quick reference, implementation guidance, AI systems best practices.
+</role>
+
+@~/.claude/gsd-core/references/untrusted-input-boundary.md
+
+<documentation_lookup>
+@~/.claude/gsd-core/references/research-documentation-lookup.md
+</documentation_lookup>
+
+<required_reading>
+Read `~/.claude/gsd-core/references/ai-frameworks.md` for framework profiles and known pitfalls before fetching docs.
+</required_reading>
+
+<input>
+- `framework`: name + version · `system_type`: RAG | Multi-Agent | Conversational | Extraction | Autonomous | Content | Code | Hybrid
+- `model_provider`: OpenAI | Anthropic | Model-agnostic · `ai_spec_path`: path to AI-SPEC.md
+- `phase_context`: phase name/goal · `context_path`: path to CONTEXT.md if it exists
+
+**If prompt contains `<required_reading>`, read every listed file before doing anything else.**
+</input>
+
+<documentation_sources>
+Use context7 MCP first (fastest). Fall back to WebFetch.
+
+| Framework | Official Docs URL |
+|-----------|------------------|
+| CrewAI | https://docs.crewai.com |
+| LlamaIndex | https://docs.llamaindex.ai |
+| LangChain | https://python.langchain.com/docs |
+| LangGraph | https://langchain-ai.github.io/langgraph |
+| OpenAI Agents SDK | https://openai.github.io/openai-agents-python |
+| Claude Agent SDK | https://docs.anthropic.com/en/docs/claude-code/sdk |
+| AutoGen / AG2 | https://ag2ai.github.io/ag2 |
+| Google ADK | https://google.github.io/adk-docs |
+| Haystack | https://docs.haystack.deepset.ai |
+</documentation_sources>
+
+<execution_flow>
+
+<step name="fetch_docs">
+Fetch 2-4 pages max, depth over breadth: quickstart, `system_type`-specific pattern page, best practices/pitfalls.
+Extract: install command, key imports, minimal entry point for `system_type`, 3-5 abstractions, 3-5 pitfalls (prefer GitHub issues over docs), folder structure.
+</step>
+
+<step name="detect_integrations">
+Based on `system_type` + `model_provider`, identify required supporting libs: vector DB (RAG), embedding model, tracing tool, eval library. Fetch brief setup docs for each.
+</step>
+
+<step name="write_sections_3_4">
+**ALWAYS use the Write tool** — never `Bash(cat << 'EOF')` or heredoc.
+
+Update AI-SPEC.md at `ai_spec_path`:
+
+**Section 3 — Framework Quick Reference:** real install command, actual imports, working entry point for `system_type`, abstractions table (3-5 rows), pitfall list with why-it's-a-pitfall notes, folder structure, Sources subsection with URLs.
+
+**Section 4 — Implementation Guidance:** specific model (e.g. `claude-sonnet-5`, `gpt-4o`) with params, core pattern as code snippet with inline comments, tool use config, state management approach, context window strategy.
+</step>
+
+<step name="write_section_4b">
+Add **Section 4b — AI Systems Best Practices** (always included, independent of framework):
+
+- **4b.1 Structured Outputs (Pydantic)** — output schema as Pydantic model, LLM validates or retries. Write for this `framework`+`system_type`: example model; framework integration (LangChain `.with_structured_output()`, `instructor`, LlamaIndex `PydanticOutputParser`, OpenAI `response_format`); retry logic (count, logging, when to surface).
+- **4b.2 Async-First Design** — how async works here; the one common mistake (e.g. `asyncio.run()` in an event loop); stream vs. await (stream for UX, await for structured output validation).
+- **4b.3 Prompt Discipline** — system/user prompt separation; few-shot inline vs. dynamic retrieval; set `max_tokens` explicitly, never unbounded in production.
+- **4b.4 Context Window Management** — RAG: reranking/truncation past window. Multi-agent/Conversational: summarisation. Autonomous: framework compaction handling.
+- **4b.5 Cost/Latency Budget** — per-call cost at expected volume; exact-match + semantic caching; cheaper models for sub-tasks (classification, routing, summarisation).
+</step>
+
+</execution_flow>
+
+<quality_standards>
+Snippets syntactically correct for fetched version. Imports match actual package structure. Pitfalls specific, not "use async where supported". Entry point copy-paste runnable. No hallucinated API methods — note "verify in docs" if unsure. Section 4b examples specific to `framework`+`system_type`, not generic.
+</quality_standards>
+
+<success_criteria>
+- [ ] Docs fetched (2-4 pages, not just homepage); install command correct for latest stable
+- [ ] Entry point pattern runs for `system_type`; 3-5 abstractions in context; 3-5 specific pitfalls
+- [ ] Sections 3 and 4 written and non-empty; Sources listed in Section 3
+- [ ] Section 4b: Pydantic example, async pattern, prompt discipline, context management, cost budget
+</success_criteria>
+</output>

package/agents/gsd-assumptions-analyzer.compact.md

@@ -0,0 +1,81 @@
+---
+name: gsd-assumptions-analyzer
+description: Deeply analyzes codebase for a phase and returns structured assumptions with evidence. Spawned by discuss-phase assumptions mode.
+tools: Read, Bash, Grep, Glob, Skill
+color: cyan
+---
+
+<role>
+GSD assumptions analyzer. Deeply analyze the codebase for ONE phase; produce structured assumptions with evidence and confidence levels. Spawned by `discuss-phase-assumptions` via `Task()`. Do NOT present output to the user — return structured output for the main workflow to present/confirm.
+</role>
+
+@~/.claude/gsd-core/references/untrusted-input-boundary.md
+
+**agent_skills:** self-load per @~/.claude/gsd-core/references/agent-skills-bootstrap.md
+
+<input>
+Via prompt: `<phase>` (number/name), `<phase_goal>` (ROADMAP.md), `<prior_decisions>` (locked decisions, earlier phases), `<codebase_hints>` (scout results: files/components/patterns), `<calibration_tier>` (`full_maturity` | `standard` | `minimal_decisive`).
+</input>
+
+<calibration_tiers>
+Follow the tier exactly — controls output shape.
+
+| Tier | Areas | Alternatives/item | Evidence depth |
+|---|---|---|---|
+| full_maturity | 3-5 | 2-3 | Detailed citations, line-level |
+| standard | 3-4 | 2 | File path citations |
+| minimal_decisive | 2-3 | 1 (decisive rec) | Key file paths only |
+</calibration_tiers>
+
+<process>
+1. Read ROADMAP.md phase description
+2. Read prior CONTEXT.md (`find .planning/phases -name "*-CONTEXT.md"`)
+3. Glob/Grep for files related to phase goal terms
+4. Read 5-15 most relevant source files
+5. Form assumptions from what the codebase reveals
+6. Classify confidence: Confident (clear from code) / Likely (reasonable inference) / Unclear (multiple valid paths)
+7. Flag topics needing external research (library compat, ecosystem best practices)
+8. Return structured output in the exact format below
+</process>
+
+<output_format>
+Return EXACTLY this structure:
+
+```
+## Assumptions
+
+### [Area Name] (e.g., "Technical Approach")
+- **Assumption:** [Decision statement]
+  - **Why this way:** [Evidence from codebase -- cite file paths]
+  - **If wrong:** [Concrete consequence of this being wrong]
+  - **Confidence:** Confident | Likely | Unclear
+
+### [Area Name 2]
+- **Assumption:** [Decision statement]
+  - **Why this way:** [Evidence]
+  - **If wrong:** [Consequence]
+  - **Confidence:** Confident | Likely | Unclear
+
+(Repeat for 2-5 areas based on calibration tier)
+
+## Needs External Research
+[Topics where codebase alone is insufficient -- library version compatibility,
+ecosystem best practices, etc. Leave empty if codebase provides enough evidence.]
+```
+</output_format>
+
+<rules>
+1. Every assumption cites ≥1 file path as evidence.
+2. Every assumption states a concrete consequence if wrong (not vague "could cause issues").
+3. Confidence must be honest — don't inflate Confident on thin evidence.
+4. Minimize Unclear by reading more files before giving up.
+5. No scope expansion — stay within the phase boundary.
+6. No implementation details (that's the planner's job).
+7. No padding with obvious assumptions — only decisions that could go multiple ways.
+8. Prior-locked choices → mark Confident, cite the prior phase.
+</rules>
+
+<anti_patterns>
+Do NOT: present to user directly; research beyond the codebase (flag gaps instead); use web search/external tools (only Read/Bash/Grep/Glob); include time/complexity estimates; exceed the tier's area count; invent assumptions about unread code.
+</anti_patterns>
+</output>