diff --git a/commands/gsd/research-project.md b/commands/gsd/research-project.md
new file mode 100644
index 000000000..19ed96f96
--- /dev/null
+++ b/commands/gsd/research-project.md
@@ -0,0 +1,147 @@
+---
+description: Research domain ecosystem before creating roadmap
+allowed-tools:
+  - Task
+  - Read
+  - Write
+  - Bash
+  - Glob
+  - Grep
+  - AskUserQuestion
+---
+
+<!--
+DESIGN NOTE: Pre-Roadmap Research
+
+This command runs AFTER new-project and BEFORE create-roadmap.
+It spawns batched subagents to research domain ecosystems in parallel.
+Subagents write directly to .planning/research/ to preserve main context.
+
+Flow: new-project → research-project (optional) → create-roadmap
+-->
+
+<objective>
+Research domain ecosystem via batched subagents before roadmap creation.
+
+Spawns 3-4 subagents in parallel to research:
+- Ecosystem (libraries, frameworks, tools)
+- Architecture (patterns, project structure)
+- Pitfalls (common mistakes, what NOT to do)
+- Standards (best practices, conventions)
+
+Each subagent writes directly to `.planning/research/` preserving main context.
+</objective>
+
+<execution_context>
+@~/.claude/get-shit-done/workflows/research-project.md
+@~/.claude/get-shit-done/templates/project-research.md
+@~/.claude/get-shit-done/references/research-subagent-prompts.md
+</execution_context>
+
+<context>
+**Load project vision:**
+@.planning/PROJECT.md
+
+**Check for existing research:**
+!`ls .planning/research/ 2>/dev/null || echo "NO_RESEARCH_DIR"`
+</context>
+
+<process>
+
+<step name="validate">
+Check prerequisites:
+
+```bash
+# Verify .planning/ exists
+[ -d .planning ] || { echo "No .planning/ directory. Run /gsd:new-project first."; exit 1; }
+
+# Verify PROJECT.md exists
+[ -f .planning/PROJECT.md ] || { echo "No PROJECT.md. Run /gsd:new-project first."; exit 1; }
+
+# Check for existing research
+[ -d .planning/research ] && echo "RESEARCH_EXISTS" || echo "NO_RESEARCH"
+```
+
+If RESEARCH_EXISTS:
+```
+Research already exists at .planning/research/
+
+What would you like to do?
+1. View existing research
+2. Re-run research (overwrites existing)
+3. Skip to create-roadmap
+```
+
+Wait for user decision.
+</step>
+
+<step name="detect_domain">
+Parse PROJECT.md to identify the domain and research scope.
+
+Look for:
+- Technologies mentioned (Three.js, WebGL, audio, etc.)
+- Problem domain (3D, games, real-time, etc.)
+- Technical constraints that suggest specific ecosystems
+
+If domain unclear, use AskUserQuestion:
+- header: "Domain"
+- question: "What domain should we research?"
+- options:
+  - "3D/Graphics" - Three.js, WebGL, shaders
+  - "Games/Interactive" - Physics, collision, procedural
+  - "Audio/Music" - Web Audio, synthesis, DSP
+  - (other relevant options based on PROJECT.md)
+</step>
+
+<step name="research">
+Follow research-project.md workflow:
+
+1. Create `.planning/research/` directory
+2. Spawn first batch of subagents (ecosystem + architecture)
+3. Wait for completion
+4. Spawn second batch (pitfalls + standards)
+5. Wait for completion
+6. Verify all outputs exist
+</step>
+
+<step name="summarize">
+After all subagents complete:
+
+```
+Research complete:
+- .planning/research/ecosystem.md
+- .planning/research/architecture.md
+- .planning/research/pitfalls.md
+- .planning/research/standards.md
+
+Key findings:
+- [Top ecosystem recommendation]
+- [Key architecture pattern]
+- [Critical pitfall to avoid]
+
+What's next?
+1. Create roadmap (/gsd:create-roadmap) - Incorporates research
+2. Review research files
+3. Done for now
+```
+
+If user selects "Create roadmap" → invoke `/gsd:create-roadmap`
+</step>
+
+</process>
+
+<output>
+- `.planning/research/ecosystem.md`
+- `.planning/research/architecture.md`
+- `.planning/research/pitfalls.md`
+- `.planning/research/standards.md`
+</output>
+
+<success_criteria>
+- [ ] PROJECT.md exists (prerequisite checked)
+- [ ] Domain detected or user clarified
+- [ ] Subagents spawned in batches of 3-4 max
+- [ ] All subagents wrote files directly to .planning/research/
+- [ ] All 4 research files exist
+- [ ] User knows next steps (create-roadmap)
+</success_criteria>
diff --git a/get-shit-done/templates/project-research.md b/get-shit-done/templates/project-research.md
new file mode 100644
index 000000000..7f8625692
--- /dev/null
+++ b/get-shit-done/templates/project-research.md
@@ -0,0 +1,181 @@
+# Project Research Template
+
+Template for `.planning/research/{category}.md` - project-level domain research written by subagents.
+
+---
+
+## File Template
+
+```markdown
+# {Category}: {Domain}
+
+**Category:** {ecosystem | architecture | pitfalls | standards}
+**Domain:** {domain from PROJECT.md}
+**Researched:** {date}
+**Confidence:** {high | medium | low}
+
+## Research Summary
+
+{2-3 sentence overview of what was found and why it matters for this project}
+
+## Findings
+
+### {Finding 1 Title}
+
+{What was discovered}
+
+**Source:** {URL or documentation reference}
+**Confidence:** {high | medium | low}
+**Relevance:** {Why this matters for the project}
+
+### {Finding 2 Title}
+
+{What was discovered}
+
+**Source:** {URL or documentation reference}
+**Confidence:** {high | medium | low}
+**Relevance:** {Why this matters for the project}
+
+{... additional findings ...}
+
+## Recommendations
+
+### Use
+
+- **{Library/Pattern/Tool}** - {One line why}
+- **{Library/Pattern/Tool}** - {One line why}
+
+### Avoid
+
+- **{Thing to avoid}** - {One line why}
+- **{Thing to avoid}** - {One line why}
+
+### Defer Decision
+
+- **{Topic}** - {Why more info needed}
+
+## Sources
+
+| Source | Type | Confidence | Last Verified |
+|--------|------|------------|---------------|
+| {URL or reference} | {official docs / blog / github / forum} | {high/medium/low} | {date} |
+| {URL or reference} | {type} | {confidence} | {date} |
+
+## Open Questions
+
+- {Question that couldn't be resolved}
+- {Question that needs more context}
+- {Question for roadmap planning to consider}
+
+---
+*Generated by research-project subagent*
+*Category: {category}*
+```
+
+---
+
+<category_guides>
+
+## Category-Specific Guidance
+
+### ecosystem.md
+
+**Purpose:** Map the library/framework landscape for this domain
+
+**Key questions to answer:**
+- What are the go-to libraries for this problem?
+- Which frameworks are actively maintained?
+- What's the "standard stack" experts use?
+- What NOT to hand-roll (existing solutions exist)?
+
+**Structure emphasis:**
+- Compare 2-4 main options
+- Clear "use X when..." guidance
+- Version currency (is it maintained?)
+- Integration considerations
+
+### architecture.md
+
+**Purpose:** Document standard project structure and patterns
+
+**Key questions to answer:**
+- How do experts organize code for this domain?
+- What patterns prevent common problems?
+- What component boundaries make sense?
+- How does data flow in typical implementations?
+
+**Structure emphasis:**
+- Directory structure recommendations
+- Component organization patterns
+- State management approaches
+- Integration patterns with related systems
+
+### pitfalls.md
+
+**Purpose:** Catalog what NOT to do and why
+
+**Key questions to answer:**
+- What mistakes do beginners commonly make?
+- What causes performance problems?
+- What architectural choices cause regret?
+- What seems like a good idea but isn't?
+
+**Structure emphasis:**
+- Clear problem → consequence → solution
+- Real examples of failures
+- Detection (how to know if you're doing this)
+- Prevention (how to avoid)
+
+### standards.md
+
+**Purpose:** Document best practices and quality expectations
+
+**Key questions to answer:**
+- What does "production quality" mean for this domain?
+- What testing approaches work?
+- What performance benchmarks matter?
+- What accessibility/security considerations apply?
+
+**Structure emphasis:**
+- Measurable quality criteria
+- Testing strategies that work
+- Performance targets
+- Common standards/conventions
+
+</category_guides>
+
+<difference_from_phase_research>
+## How This Differs from Phase-Level Research
+
+**project-research.md (this template):**
+- Written BEFORE roadmap exists
+- Informs phase structure and scope
+- Ecosystem-level landscape view
+- Answers "what tools/patterns should we use?"
+
+**research.md (phase-level):**
+- Written AFTER roadmap exists
+- Informs specific phase implementation
+- Implementation-level detail
+- Answers "how do we implement this phase?"
+
+Project research is strategic (shapes the roadmap).
+Phase research is tactical (shapes the implementation).
+</difference_from_phase_research>
+
+<quality_bar>
+## Quality Expectations
+
+A well-written research file:
+- Has specific, actionable recommendations (not "it depends")
+- Cites sources with confidence levels
+- Distinguishes verified facts from educated guesses
+- Surfaces open questions honestly
+- Can be read in 2-3 minutes and inform a decision
+
+**Avoid:**
+- Generic advice that applies to anything
+- Recommendations without reasoning
+- Outdated information (pre-2024 unless fundamental)
+- Confidence without verification
+</quality_bar>
diff --git a/get-shit-done/workflows/research-project.md b/get-shit-done/workflows/research-project.md
new file mode 100644
index 000000000..1a5164758
--- /dev/null
+++ b/get-shit-done/workflows/research-project.md
@@ -0,0 +1,173 @@
+<purpose>
+Orchestrate batched subagent research for domain ecosystems before roadmap creation.
+
+Subagents write directly to `.planning/research/` to preserve main context.
+Maximum 4 parallel subagents, recommended batch size 3.
+</purpose>
+
+<process>
+
+<step name="setup">
+Create research directory:
+
+```bash
+mkdir -p .planning/research
+```
+
+Parse PROJECT.md to extract:
+- Domain keywords (technology mentions, problem space)
+- Constraints that affect ecosystem choices
+- Any mentioned preferences or requirements
+</step>
+
+<step name="define_research_categories">
+Standard research categories:
+
+1. **ecosystem.md** - Libraries, frameworks, tools for this domain
+2. **architecture.md** - Patterns, project structure, component organization
+3. **pitfalls.md** - Common mistakes, what NOT to do, performance traps
+4. **standards.md** - Best practices, conventions, quality expectations
+
+Each subagent researches ONE category and writes directly to `.planning/research/{category}.md`
+</step>
+
+<step name="batch_execution">
+## Batched Subagent Spawning
+
+**Batch 1: Foundation research** (spawn in parallel)
+
+Spawn using Task tool with `subagent_type="general-purpose"`:
+
+```
+Subagent 1: ecosystem.md
+Subagent 2: architecture.md
+```
+
+**Wait for Batch 1 completion.**
+
+**Batch 2: Risk & quality research** (spawn in parallel)
+
+```
+Subagent 3: pitfalls.md
+Subagent 4: standards.md
+```
+
+**Wait for Batch 2 completion.**
+
+**Subagent prompt structure:**
+
+Use prompts from `~/.claude/get-shit-done/references/research-subagent-prompts.md`
+
+Each subagent receives:
+- Domain context from PROJECT.md
+- Category assignment (ecosystem, architecture, etc.)
+- Output format from templates/project-research.md
+- Instruction to write directly to `.planning/research/{category}.md`
+</step>
+
+<step name="verify_outputs">
+After all batches complete:
+
+```bash
+# Check all files exist
+ls -la .planning/research/
+
+# Verify each file has content
+for f in ecosystem architecture pitfalls standards; do
+  [ -s ".planning/research/${f}.md" ] && echo "✓ ${f}.md" || echo "✗ ${f}.md MISSING"
+done
+```
+
+**If any file missing:**
+- Log which subagent failed
+- Optionally retry that specific subagent
+- Continue with available research (partial is better than none)
+</step>
+
+<step name="aggregate">
+Read key findings from each research file for summary:
+
+```bash
+# Extract first few lines of each for summary
+for f in .planning/research/*.md; do
+  echo "=== $(basename $f) ==="
+  head -20 "$f"
+  echo ""
+done
+```
+
+Extract for user summary:
+- Top library/framework recommendation from ecosystem.md
+- Primary architecture pattern from architecture.md
+- Most critical pitfall from pitfalls.md
+- Key quality standard from standards.md
+</step>
+
+</process>
+
+<batching_rules>
+## Batching Configuration
+
+**Maximum parallel subagents:** 4 (API safety limit)
+**Recommended batch size:** 3 (reliable)
+
+**Batch ordering rationale:**
+- Batch 1 (ecosystem + architecture): Foundation knowledge that informs everything
+- Batch 2 (pitfalls + standards): Risk and quality that build on foundation
+
+**Between batches:**
+- Verify all subagents in batch completed
+- Check for failures, note for retry if needed
+- Proceed to next batch
+</batching_rules>
+
+<subagent_template>
+## Task Tool Invocation Pattern
+
+For each subagent, use:
+
+```
+Task tool parameters:
+- subagent_type: "general-purpose"
+- description: "Research {category} for {domain}"
+- prompt: [filled template from research-subagent-prompts.md]
+```
+
+**Prompt template (simplified):**
+
+```
+Research and write {category}.md for {domain} domain.
+
+## Context
+{Paste relevant sections from PROJECT.md}
+
+## Your Assignment
+File: .planning/research/{category}.md
+Category: {category}
+Purpose: {category-specific purpose}
+
+## Research Requirements
+Use WebSearch to find current information. Verify:
+- Libraries are actively maintained (commits in last 12 months)
+- Patterns are current best practice (not deprecated)
+- Examples are from 2024-2025 sources where possible
+
+## Output
+Write directly to .planning/research/{category}.md using the template structure:
+- research_summary
+- findings (specific discoveries with sources)
+- recommendations (actionable guidance)
+- sources (where info came from, confidence level)
+- open_questions (what couldn't be resolved)
+
+Quality bar: Someone reading this should be able to make informed decisions about the roadmap.
+```
+</subagent_template>
+
+<success_criteria>
+Research workflow complete when:
+- [ ] All 4 research files exist in .planning/research/
+- [ ] Each file has substantive content (not empty/error)
+- [ ] Key findings extracted for summary
+- [ ] Main agent context preserved (minimal usage)
+</success_criteria>