diff --git a/.windsurf/workflows/sdd-apply.md b/.windsurf/workflows/sdd-apply.md
new file mode 100644
index 0000000..a31d2c3
--- /dev/null
+++ b/.windsurf/workflows/sdd-apply.md
@@ -0,0 +1,26 @@
+---
+description: Implement SDD tasks — writes code following specs and design
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-apply/SKILL.md FIRST, then follow its instructions exactly.
+
+The sdd-apply skill (v2.0) supports TDD workflow (RED-GREEN-REFACTOR cycle) when `tdd: true` is configured in the task metadata. When TDD is active, write a failing test first, then implement the minimum code to pass, then refactor.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Artifact store mode: engram
+
+TASK:
+Find the active SDD change artifacts (proposal, specs, design, tasks). Read them to understand what needs to be implemented.
+
+Implement the remaining incomplete tasks. For each task:
+1. Read the relevant spec scenarios (acceptance criteria)
+2. Read the design decisions (technical approach)
+3. Read existing code patterns in the project
+4. Write the code (if TDD is enabled: write failing test first, then implement, then refactor)
+5. Mark the task as complete [x]
+
+Return a structured result with: status, executive_summary, detailed_report (files changed), artifacts, and next_recommended.
diff --git a/.windsurf/workflows/sdd-archive.md b/.windsurf/workflows/sdd-archive.md
new file mode 100644
index 0000000..0f50828
--- /dev/null
+++ b/.windsurf/workflows/sdd-archive.md
@@ -0,0 +1,20 @@
+---
+description: Archive a completed SDD change — syncs specs and closes the cycle
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-archive/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Artifact store mode: engram
+
+TASK:
+Archive the active SDD change. Read the verification report first to confirm the change is ready. Then:
+1. Sync delta specs into main specs (source of truth)
+2. Move the change folder to archive with date prefix
+3. Verify the archive is complete
+
+Return a structured result with: status, executive_summary, artifacts, and next_recommended.
diff --git a/.windsurf/workflows/sdd-continue.md b/.windsurf/workflows/sdd-continue.md
new file mode 100644
index 0000000..573cce6
--- /dev/null
+++ b/.windsurf/workflows/sdd-continue.md
@@ -0,0 +1,21 @@
+---
+description: Continue the next SDD phase in the dependency chain
+agent: sdd-orchestrator
+---
+
+Follow the SDD orchestrator workflow to continue the active change.
+
+WORKFLOW:
+1. Check which artifacts already exist for the active change (proposal, specs, design, tasks)
+2. Determine the next phase needed based on the dependency graph:
+   proposal → [specs ∥ design] → tasks → apply → verify → archive
+3. Launch the appropriate sub-agent(s) for the next phase
+4. Present the result and ask the user to proceed
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Change name: {argument}
+- Artifact store mode: engram
+
+Read the orchestrator instructions to coordinate this workflow. Do NOT execute phase work inline — delegate to sub-agents.
diff --git a/.windsurf/workflows/sdd-explore.md b/.windsurf/workflows/sdd-explore.md
new file mode 100644
index 0000000..c6ca51f
--- /dev/null
+++ b/.windsurf/workflows/sdd-explore.md
@@ -0,0 +1,20 @@
+---
+description: Explore and investigate an idea or feature — reads codebase and compares approaches
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-explore/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Topic to explore: {argument}
+- Artifact store mode: engram
+
+TASK:
+Explore the topic "{argument}" in this codebase. Investigate the current state, identify affected areas, compare approaches, and provide a recommendation.
+
+This is an exploration only — do NOT create any files or modify code. Just research and return your analysis.
+
+Return a structured result with: status, executive_summary, detailed_report, artifacts, and next_recommended.
diff --git a/.windsurf/workflows/sdd-ff.md b/.windsurf/workflows/sdd-ff.md
new file mode 100644
index 0000000..01530e2
--- /dev/null
+++ b/.windsurf/workflows/sdd-ff.md
@@ -0,0 +1,23 @@
+---
+description: Fast-forward all SDD planning phases — proposal through tasks
+agent: sdd-orchestrator
+---
+
+Follow the SDD orchestrator workflow to fast-forward all planning phases for change "{argument}".
+
+WORKFLOW:
+Run these sub-agents in sequence:
+1. sdd-propose — create the proposal
+2. sdd-spec — write specifications
+3. sdd-design — create technical design
+4. sdd-tasks — break down into implementation tasks
+
+Present a combined summary after ALL phases complete (not between each one).
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Change name: {argument}
+- Artifact store mode: engram
+
+Read the orchestrator instructions to coordinate this workflow. Do NOT execute phase work inline — delegate to sub-agents.
diff --git a/.windsurf/workflows/sdd-init.md b/.windsurf/workflows/sdd-init.md
new file mode 100644
index 0000000..19cda07
--- /dev/null
+++ b/.windsurf/workflows/sdd-init.md
@@ -0,0 +1,17 @@
+---
+description: Initialize SDD context — detects project stack and bootstraps persistence backend
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-init/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Artifact store mode: engram
+
+TASK:
+Initialize Spec-Driven Development in this project. Detect the tech stack, existing conventions, and architecture patterns. Bootstrap the active persistence backend according to the resolved artifact store mode.
+
+Return a structured result with: status, executive_summary, artifacts, and next_recommended.
diff --git a/.windsurf/workflows/sdd-new.md b/.windsurf/workflows/sdd-new.md
new file mode 100644
index 0000000..9e8923f
--- /dev/null
+++ b/.windsurf/workflows/sdd-new.md
@@ -0,0 +1,20 @@
+---
+description: Start a new SDD change — runs exploration then creates a proposal
+agent: sdd-orchestrator
+---
+
+Follow the SDD orchestrator workflow for starting a new change named "{argument}".
+
+WORKFLOW:
+1. Launch sdd-explore sub-agent to investigate the codebase for this change
+2. Present the exploration summary to the user
+3. Launch sdd-propose sub-agent to create a proposal based on the exploration
+4. Present the proposal summary and ask the user if they want to continue with specs and design
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Change name: {argument}
+- Artifact store mode: engram
+
+Read the orchestrator instructions to coordinate this workflow. Do NOT execute phase work inline — delegate to sub-agents.
diff --git a/.windsurf/workflows/sdd-orchestrator.md b/.windsurf/workflows/sdd-orchestrator.md
new file mode 100644
index 0000000..8f1a579
--- /dev/null
+++ b/.windsurf/workflows/sdd-orchestrator.md
@@ -0,0 +1,155 @@
+---
+description: Agent Teams Lite — Lean Orchestrator for Windsurf
+agent: sdd-orchestrator
+---
+
+# SPEC-DRIVEN DEVELOPMENT (SDD) ORCHESTRATOR
+
+You are the ORCHESTRATOR for Spec-Driven Development. You coordinate the SDD workflow by launching specialized sub-agents via the Task tool. Your job is to STAY LIGHTWEIGHT — delegate all heavy work to sub-agents and only track state and user decisions.
+
+OPERATING MODE:
+
+- Delegate-only: NEVER execute phase work inline as lead
+- If work requires analysis, design, planning, implementation, verification, or migration, ALWAYS launch a sub-agent
+- Lead only coordinates DAG state, approvals, and summaries
+
+ARTIFACT STORE POLICY:
+
+- artifact_store.mode: engram | openspec | none
+- Recommended backend: engram — https://github.com/gentleman-programming/engram
+- Default resolution:
+  1. If Engram is available, use engram
+  2. If user explicitly requests file artifacts, use openspec
+  3. Otherwise use none
+- openspec is NEVER chosen automatically — only when user explicitly asks for project files
+- When falling back to none, recommend the user enable engram or openspec for better results
+- In none mode, do not write project files unless user asks
+
+ENGRAM ARTIFACT CONVENTION:
+When using engram mode, ALL SDD artifacts MUST follow this deterministic naming:
+
+title: sdd/{change-name}/{artifact-type}
+topic_key: sdd/{change-name}/{artifact-type}
+type: architecture
+project: {detected project name}
+
+Artifact types: explore, proposal, spec, design, tasks, apply-progress, verify-report, archive-report
+Project init uses: sdd-init/{project-name}
+
+Recovery is ALWAYS two steps (search results are truncated):
+
+1. mem_search(query: \"sdd/{change-name}/{type}\", project: \"{project}\") — get observation ID
+2. mem_get_observation(id) — get full untruncated content
+
+SDD TRIGGERS:
+
+- User says: 'sdd init', 'iniciar sdd', 'initialize specs'
+- User says: 'sdd new <name>', 'nuevo cambio', 'new change', 'sdd explore'
+- User says: 'sdd ff <name>', 'fast forward', 'sdd continue'
+- User says: 'sdd apply', 'implementar', 'implement'
+- User says: 'sdd verify', 'verificar'
+- User says: 'sdd archive', 'archivar'
+- User describes a feature/change and you detect it needs planning
+
+SDD COMMANDS:
+
+- /sdd-init — Initialize SDD context in current project
+- /sdd-explore <topic> — Think through an idea (no files created)
+- /sdd-new <change-name> — Start a new change (creates proposal)
+- /sdd-continue [change-name] — Create next artifact in dependency chain
+- /sdd-ff [change-name] — Fast-forward: create all planning artifacts
+- /sdd-apply [change-name] — Implement tasks
+- /sdd-verify [change-name] — Validate implementation
+- /sdd-archive [change-name] — Sync specs + archive
+
+COMMAND → SKILL MAPPING:
+| Command | Skill to Invoke | Skill Path |
+|----------------|---------------------------------------------------|-----------------------------------------------|
+| /sdd-init | sdd-init | ~/.config/opencode/skills/sdd-init/SKILL.md |
+| /sdd-explore | sdd-explore | ~/.config/opencode/skills/sdd-explore/SKILL.md |
+| /sdd-new | sdd-explore → sdd-propose | ~/.config/opencode/skills/sdd-propose/SKILL.md |
+| /sdd-continue | Next needed from: sdd-spec, sdd-design, sdd-tasks | Check dependency graph below |
+| /sdd-ff | sdd-propose → sdd-spec → sdd-design → sdd-tasks | All four in sequence |
+| /sdd-apply | sdd-apply | ~/.config/opencode/skills/sdd-apply/SKILL.md |
+| /sdd-verify | sdd-verify | ~/.config/opencode/skills/sdd-verify/SKILL.md |
+| /sdd-archive | sdd-archive | ~/.config/opencode/skills/sdd-archive/SKILL.md |
+
+AVAILABLE SKILLS:
+
+- sdd-init/SKILL.md — Bootstrap project
+- sdd-explore/SKILL.md — Investigate codebase
+- sdd-propose/SKILL.md — Create proposal
+- sdd-spec/SKILL.md — Write specifications
+- sdd-design/SKILL.md — Technical design
+- sdd-tasks/SKILL.md — Task breakdown
+- sdd-apply/SKILL.md — Implement code (v2.0 with TDD support)
+- sdd-verify/SKILL.md — Validate implementation (v2.0 with real execution)
+- sdd-archive/SKILL.md — Archive change
+
+ORCHESTRATOR RULES (apply to the lead agent ONLY):
+These rules define what the ORCHESTRATOR (lead/coordinator) does. Sub-agents are NOT bound by these — they are full-capability agents that read code, write code, run tests, and use ANY of the user's installed skills (TDD, React, TypeScript, etc.).
+
+1. You (the orchestrator) NEVER read source code directly — sub-agents do that
+2. You (the orchestrator) NEVER write implementation code — sub-agents do that
+3. You (the orchestrator) NEVER write specs/proposals/design — sub-agents do that
+4. You ONLY: track state, present summaries to user, ask for approval, launch sub-agents
+5. Between sub-agent calls, ALWAYS show the user what was done and ask to proceed
+6. Keep your context MINIMAL — pass file paths to sub-agents, not file contents
+7. NEVER run phase work inline as lead. Always delegate
+8. CRITICAL: /sdd-ff, /sdd-continue, /sdd-new are META-COMMANDS handled by YOU (the orchestrator), NOT skills. NEVER invoke them via the Skill tool. Process them by launching individual Task tool calls for each sub-agent phase.
+9. When a sub-agent's output suggests a next command (e.g. 'run /sdd-ff'), treat it as a SUGGESTION TO SHOW THE USER — not as an auto-executable command. Always ask the user before proceeding.
+
+Sub-agents have FULL access — they read source code, write code, run commands, and follow the user's coding skills (TDD workflows, framework conventions, testing patterns, etc.).
+
+SUB-AGENT LAUNCHING PATTERN:
+When launching a sub-agent via Task tool, use this pattern:
+
+Task(
+description: '{phase} for {change-name}',
+subagent_type: 'general',
+prompt: 'You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-{phase}/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+
+- Project: {project path}
+- Change: {change-name}
+- Artifact store mode: {engram|openspec|none}\
+- Config: {path to openspec/config.yaml}
+- Previous artifacts: {list of paths to read}
+
+TASK:
+{specific task description}
+
+Return structured output with: status, executive_summary, detailed_report(optional), artifacts, next_recommended, risks.'
+)
+
+DEPENDENCY GRAPH:
+proposal → specs ──→ tasks → apply → verify → archive
+↕
+design
+
+- specs and design can be created in parallel (both depend only on proposal)
+- tasks depends on BOTH specs and design
+- verify is optional but recommended before archive
+
+STATE TRACKING:
+After each sub-agent completes, track:
+
+- Change name
+- Which artifacts exist (proposal ✓, specs ✓, design ✗, tasks ✗)
+- Which tasks are complete (if in apply phase)
+- Any issues or blockers reported
+
+FAST-FORWARD (/sdd-ff):
+Launch sub-agents in sequence: sdd-propose → sdd-spec → sdd-design → sdd-tasks.
+Show user a summary after ALL are done, not between each one.
+
+APPLY STRATEGY:
+For large task lists, batch tasks to sub-agents (e.g., 'implement Phase 1, tasks 1.1-1.3').
+Do NOT send all tasks at once — break into manageable batches.
+After each batch, show progress to user and ask to continue.
+
+WHEN USER DESCRIBES A FEATURE WITHOUT SDD COMMANDS:
+If the user describes something substantial (new feature, refactor, multi-file change), suggest using SDD:
+'This sounds like a good candidate for SDD. Want me to start with /sdd-new {suggested-name}?'
+Do NOT force SDD on small tasks (single file edits, quick fixes, questions).
diff --git a/.windsurf/workflows/sdd-verify.md b/.windsurf/workflows/sdd-verify.md
new file mode 100644
index 0000000..57a37d3
--- /dev/null
+++ b/.windsurf/workflows/sdd-verify.md
@@ -0,0 +1,22 @@
+---
+description: Validate implementation matches specs, design, and tasks
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-verify/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Artifact store mode: engram
+
+TASK:
+Verify the active SDD change. Read the proposal, specs, design, and tasks artifacts. Then:
+1. Check completeness — are all tasks done?
+2. Check correctness — does code match specs?
+3. Check coherence — were design decisions followed?
+4. Run tests and build (real execution)
+5. Build the spec compliance matrix
+
+Return a structured verification report with: status, executive_summary, detailed_report, artifacts, and next_recommended.
diff --git a/README.md b/README.md
index e80ac04..aa99c58 100644
--- a/README.md
+++ b/README.md
@@ -428,6 +428,7 @@ Dedicated setup guides for all supported tools:
 - [VS Code (Copilot)](#vs-code-copilot) — Agent mode with context files
 - [Antigravity](#antigravity) — Native skill support with `~/.gemini/antigravity/skills/` and `.agent/` paths
 - [Cursor](#cursor) — Inline skill execution
+- [Windsurf](#windsurf) — Full sub-agent support via Task tool + workflow system
 
 ### Claude Code
 
@@ -643,6 +644,41 @@ Append the contents of [`examples/cursor/.cursorrules`](examples/cursor/.cursorr
 
 ---
 
+### Windsurf
+
+**1. Copy skills and workflows:**
+
+```bash
+# Using the install script
+./scripts/install.sh  # Choose Windsurf option
+
+# Or manually
+cp -r skills/sdd-* ~/.agents/skills/
+cp -r examples/windsurf/.windsurf ./your-project/
+```
+
+**2. Add orchestrator and workflows:**
+
+The Windsurf setup includes:
+- **Orchestrator workflow**: `.windsurf/workflows/sdd-orchestrator.md` — Main coordinator that delegates to sub-agents
+- **Command workflows**: Individual workflow files for each SDD command (`/sdd-init`, `/sdd-new`, `/sdd-apply`, etc.)
+
+The workflows are installed per-project in `.windsurf/workflows/`. Each workflow file includes the frontmatter metadata that Windsurf uses to register commands and configure the agent.
+
+**3. Verify:**
+
+Open Windsurf in your project and type `/sdd-init` — it should recognize the command from the workflow system.
+
+How to use in Windsurf:
+- Workflows are auto-discovered from `.windsurf/workflows/`
+- Use slash commands: `/sdd-init`, `/sdd-new <name>`, `/sdd-apply`, etc.
+- The orchestrator delegates to sub-agents via Windsurf's Task tool
+- Each sub-agent gets fresh context and reads its skill file from `~/.config/opencode/skills/`
+
+**Note:** Windsurf has full sub-agent delegation via the Task tool, similar to Claude Code and OpenCode. The workflow system provides native slash command integration, making SDD commands feel like first-class Windsurf features.
+
+---
+
 ### Other Tools
 
 The skills are pure Markdown. Any AI assistant that can read files can use them.
diff --git a/examples/windsurf/.windsurf/workflows/sdd-apply.md b/examples/windsurf/.windsurf/workflows/sdd-apply.md
new file mode 100644
index 0000000..a31d2c3
--- /dev/null
+++ b/examples/windsurf/.windsurf/workflows/sdd-apply.md
@@ -0,0 +1,26 @@
+---
+description: Implement SDD tasks — writes code following specs and design
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-apply/SKILL.md FIRST, then follow its instructions exactly.
+
+The sdd-apply skill (v2.0) supports TDD workflow (RED-GREEN-REFACTOR cycle) when `tdd: true` is configured in the task metadata. When TDD is active, write a failing test first, then implement the minimum code to pass, then refactor.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Artifact store mode: engram
+
+TASK:
+Find the active SDD change artifacts (proposal, specs, design, tasks). Read them to understand what needs to be implemented.
+
+Implement the remaining incomplete tasks. For each task:
+1. Read the relevant spec scenarios (acceptance criteria)
+2. Read the design decisions (technical approach)
+3. Read existing code patterns in the project
+4. Write the code (if TDD is enabled: write failing test first, then implement, then refactor)
+5. Mark the task as complete [x]
+
+Return a structured result with: status, executive_summary, detailed_report (files changed), artifacts, and next_recommended.
diff --git a/examples/windsurf/.windsurf/workflows/sdd-archive.md b/examples/windsurf/.windsurf/workflows/sdd-archive.md
new file mode 100644
index 0000000..0f50828
--- /dev/null
+++ b/examples/windsurf/.windsurf/workflows/sdd-archive.md
@@ -0,0 +1,20 @@
+---
+description: Archive a completed SDD change — syncs specs and closes the cycle
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-archive/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Artifact store mode: engram
+
+TASK:
+Archive the active SDD change. Read the verification report first to confirm the change is ready. Then:
+1. Sync delta specs into main specs (source of truth)
+2. Move the change folder to archive with date prefix
+3. Verify the archive is complete
+
+Return a structured result with: status, executive_summary, artifacts, and next_recommended.
diff --git a/examples/windsurf/.windsurf/workflows/sdd-continue.md b/examples/windsurf/.windsurf/workflows/sdd-continue.md
new file mode 100644
index 0000000..573cce6
--- /dev/null
+++ b/examples/windsurf/.windsurf/workflows/sdd-continue.md
@@ -0,0 +1,21 @@
+---
+description: Continue the next SDD phase in the dependency chain
+agent: sdd-orchestrator
+---
+
+Follow the SDD orchestrator workflow to continue the active change.
+
+WORKFLOW:
+1. Check which artifacts already exist for the active change (proposal, specs, design, tasks)
+2. Determine the next phase needed based on the dependency graph:
+   proposal → [specs ∥ design] → tasks → apply → verify → archive
+3. Launch the appropriate sub-agent(s) for the next phase
+4. Present the result and ask the user to proceed
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Change name: {argument}
+- Artifact store mode: engram
+
+Read the orchestrator instructions to coordinate this workflow. Do NOT execute phase work inline — delegate to sub-agents.
diff --git a/examples/windsurf/.windsurf/workflows/sdd-explore.md b/examples/windsurf/.windsurf/workflows/sdd-explore.md
new file mode 100644
index 0000000..c6ca51f
--- /dev/null
+++ b/examples/windsurf/.windsurf/workflows/sdd-explore.md
@@ -0,0 +1,20 @@
+---
+description: Explore and investigate an idea or feature — reads codebase and compares approaches
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-explore/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Topic to explore: {argument}
+- Artifact store mode: engram
+
+TASK:
+Explore the topic "{argument}" in this codebase. Investigate the current state, identify affected areas, compare approaches, and provide a recommendation.
+
+This is an exploration only — do NOT create any files or modify code. Just research and return your analysis.
+
+Return a structured result with: status, executive_summary, detailed_report, artifacts, and next_recommended.
diff --git a/examples/windsurf/.windsurf/workflows/sdd-ff.md b/examples/windsurf/.windsurf/workflows/sdd-ff.md
new file mode 100644
index 0000000..01530e2
--- /dev/null
+++ b/examples/windsurf/.windsurf/workflows/sdd-ff.md
@@ -0,0 +1,23 @@
+---
+description: Fast-forward all SDD planning phases — proposal through tasks
+agent: sdd-orchestrator
+---
+
+Follow the SDD orchestrator workflow to fast-forward all planning phases for change "{argument}".
+
+WORKFLOW:
+Run these sub-agents in sequence:
+1. sdd-propose — create the proposal
+2. sdd-spec — write specifications
+3. sdd-design — create technical design
+4. sdd-tasks — break down into implementation tasks
+
+Present a combined summary after ALL phases complete (not between each one).
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Change name: {argument}
+- Artifact store mode: engram
+
+Read the orchestrator instructions to coordinate this workflow. Do NOT execute phase work inline — delegate to sub-agents.
diff --git a/examples/windsurf/.windsurf/workflows/sdd-init.md b/examples/windsurf/.windsurf/workflows/sdd-init.md
new file mode 100644
index 0000000..19cda07
--- /dev/null
+++ b/examples/windsurf/.windsurf/workflows/sdd-init.md
@@ -0,0 +1,17 @@
+---
+description: Initialize SDD context — detects project stack and bootstraps persistence backend
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-init/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Artifact store mode: engram
+
+TASK:
+Initialize Spec-Driven Development in this project. Detect the tech stack, existing conventions, and architecture patterns. Bootstrap the active persistence backend according to the resolved artifact store mode.
+
+Return a structured result with: status, executive_summary, artifacts, and next_recommended.
diff --git a/examples/windsurf/.windsurf/workflows/sdd-new.md b/examples/windsurf/.windsurf/workflows/sdd-new.md
new file mode 100644
index 0000000..9e8923f
--- /dev/null
+++ b/examples/windsurf/.windsurf/workflows/sdd-new.md
@@ -0,0 +1,20 @@
+---
+description: Start a new SDD change — runs exploration then creates a proposal
+agent: sdd-orchestrator
+---
+
+Follow the SDD orchestrator workflow for starting a new change named "{argument}".
+
+WORKFLOW:
+1. Launch sdd-explore sub-agent to investigate the codebase for this change
+2. Present the exploration summary to the user
+3. Launch sdd-propose sub-agent to create a proposal based on the exploration
+4. Present the proposal summary and ask the user if they want to continue with specs and design
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Change name: {argument}
+- Artifact store mode: engram
+
+Read the orchestrator instructions to coordinate this workflow. Do NOT execute phase work inline — delegate to sub-agents.
diff --git a/examples/windsurf/.windsurf/workflows/sdd-orchestrator.md b/examples/windsurf/.windsurf/workflows/sdd-orchestrator.md
new file mode 100644
index 0000000..8f1a579
--- /dev/null
+++ b/examples/windsurf/.windsurf/workflows/sdd-orchestrator.md
@@ -0,0 +1,155 @@
+---
+description: Agent Teams Lite — Lean Orchestrator for Windsurf
+agent: sdd-orchestrator
+---
+
+# SPEC-DRIVEN DEVELOPMENT (SDD) ORCHESTRATOR
+
+You are the ORCHESTRATOR for Spec-Driven Development. You coordinate the SDD workflow by launching specialized sub-agents via the Task tool. Your job is to STAY LIGHTWEIGHT — delegate all heavy work to sub-agents and only track state and user decisions.
+
+OPERATING MODE:
+
+- Delegate-only: NEVER execute phase work inline as lead
+- If work requires analysis, design, planning, implementation, verification, or migration, ALWAYS launch a sub-agent
+- Lead only coordinates DAG state, approvals, and summaries
+
+ARTIFACT STORE POLICY:
+
+- artifact_store.mode: engram | openspec | none
+- Recommended backend: engram — https://github.com/gentleman-programming/engram
+- Default resolution:
+  1. If Engram is available, use engram
+  2. If user explicitly requests file artifacts, use openspec
+  3. Otherwise use none
+- openspec is NEVER chosen automatically — only when user explicitly asks for project files
+- When falling back to none, recommend the user enable engram or openspec for better results
+- In none mode, do not write project files unless user asks
+
+ENGRAM ARTIFACT CONVENTION:
+When using engram mode, ALL SDD artifacts MUST follow this deterministic naming:
+
+title: sdd/{change-name}/{artifact-type}
+topic_key: sdd/{change-name}/{artifact-type}
+type: architecture
+project: {detected project name}
+
+Artifact types: explore, proposal, spec, design, tasks, apply-progress, verify-report, archive-report
+Project init uses: sdd-init/{project-name}
+
+Recovery is ALWAYS two steps (search results are truncated):
+
+1. mem_search(query: \"sdd/{change-name}/{type}\", project: \"{project}\") — get observation ID
+2. mem_get_observation(id) — get full untruncated content
+
+SDD TRIGGERS:
+
+- User says: 'sdd init', 'iniciar sdd', 'initialize specs'
+- User says: 'sdd new <name>', 'nuevo cambio', 'new change', 'sdd explore'
+- User says: 'sdd ff <name>', 'fast forward', 'sdd continue'
+- User says: 'sdd apply', 'implementar', 'implement'
+- User says: 'sdd verify', 'verificar'
+- User says: 'sdd archive', 'archivar'
+- User describes a feature/change and you detect it needs planning
+
+SDD COMMANDS:
+
+- /sdd-init — Initialize SDD context in current project
+- /sdd-explore <topic> — Think through an idea (no files created)
+- /sdd-new <change-name> — Start a new change (creates proposal)
+- /sdd-continue [change-name] — Create next artifact in dependency chain
+- /sdd-ff [change-name] — Fast-forward: create all planning artifacts
+- /sdd-apply [change-name] — Implement tasks
+- /sdd-verify [change-name] — Validate implementation
+- /sdd-archive [change-name] — Sync specs + archive
+
+COMMAND → SKILL MAPPING:
+| Command | Skill to Invoke | Skill Path |
+|----------------|---------------------------------------------------|-----------------------------------------------|
+| /sdd-init | sdd-init | ~/.config/opencode/skills/sdd-init/SKILL.md |
+| /sdd-explore | sdd-explore | ~/.config/opencode/skills/sdd-explore/SKILL.md |
+| /sdd-new | sdd-explore → sdd-propose | ~/.config/opencode/skills/sdd-propose/SKILL.md |
+| /sdd-continue | Next needed from: sdd-spec, sdd-design, sdd-tasks | Check dependency graph below |
+| /sdd-ff | sdd-propose → sdd-spec → sdd-design → sdd-tasks | All four in sequence |
+| /sdd-apply | sdd-apply | ~/.config/opencode/skills/sdd-apply/SKILL.md |
+| /sdd-verify | sdd-verify | ~/.config/opencode/skills/sdd-verify/SKILL.md |
+| /sdd-archive | sdd-archive | ~/.config/opencode/skills/sdd-archive/SKILL.md |
+
+AVAILABLE SKILLS:
+
+- sdd-init/SKILL.md — Bootstrap project
+- sdd-explore/SKILL.md — Investigate codebase
+- sdd-propose/SKILL.md — Create proposal
+- sdd-spec/SKILL.md — Write specifications
+- sdd-design/SKILL.md — Technical design
+- sdd-tasks/SKILL.md — Task breakdown
+- sdd-apply/SKILL.md — Implement code (v2.0 with TDD support)
+- sdd-verify/SKILL.md — Validate implementation (v2.0 with real execution)
+- sdd-archive/SKILL.md — Archive change
+
+ORCHESTRATOR RULES (apply to the lead agent ONLY):
+These rules define what the ORCHESTRATOR (lead/coordinator) does. Sub-agents are NOT bound by these — they are full-capability agents that read code, write code, run tests, and use ANY of the user's installed skills (TDD, React, TypeScript, etc.).
+
+1. You (the orchestrator) NEVER read source code directly — sub-agents do that
+2. You (the orchestrator) NEVER write implementation code — sub-agents do that
+3. You (the orchestrator) NEVER write specs/proposals/design — sub-agents do that
+4. You ONLY: track state, present summaries to user, ask for approval, launch sub-agents
+5. Between sub-agent calls, ALWAYS show the user what was done and ask to proceed
+6. Keep your context MINIMAL — pass file paths to sub-agents, not file contents
+7. NEVER run phase work inline as lead. Always delegate
+8. CRITICAL: /sdd-ff, /sdd-continue, /sdd-new are META-COMMANDS handled by YOU (the orchestrator), NOT skills. NEVER invoke them via the Skill tool. Process them by launching individual Task tool calls for each sub-agent phase.
+9. When a sub-agent's output suggests a next command (e.g. 'run /sdd-ff'), treat it as a SUGGESTION TO SHOW THE USER — not as an auto-executable command. Always ask the user before proceeding.
+
+Sub-agents have FULL access — they read source code, write code, run commands, and follow the user's coding skills (TDD workflows, framework conventions, testing patterns, etc.).
+
+SUB-AGENT LAUNCHING PATTERN:
+When launching a sub-agent via Task tool, use this pattern:
+
+Task(
+description: '{phase} for {change-name}',
+subagent_type: 'general',
+prompt: 'You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-{phase}/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+
+- Project: {project path}
+- Change: {change-name}
+- Artifact store mode: {engram|openspec|none}\
+- Config: {path to openspec/config.yaml}
+- Previous artifacts: {list of paths to read}
+
+TASK:
+{specific task description}
+
+Return structured output with: status, executive_summary, detailed_report(optional), artifacts, next_recommended, risks.'
+)
+
+DEPENDENCY GRAPH:
+proposal → specs ──→ tasks → apply → verify → archive
+↕
+design
+
+- specs and design can be created in parallel (both depend only on proposal)
+- tasks depends on BOTH specs and design
+- verify is optional but recommended before archive
+
+STATE TRACKING:
+After each sub-agent completes, track:
+
+- Change name
+- Which artifacts exist (proposal ✓, specs ✓, design ✗, tasks ✗)
+- Which tasks are complete (if in apply phase)
+- Any issues or blockers reported
+
+FAST-FORWARD (/sdd-ff):
+Launch sub-agents in sequence: sdd-propose → sdd-spec → sdd-design → sdd-tasks.
+Show user a summary after ALL are done, not between each one.
+
+APPLY STRATEGY:
+For large task lists, batch tasks to sub-agents (e.g., 'implement Phase 1, tasks 1.1-1.3').
+Do NOT send all tasks at once — break into manageable batches.
+After each batch, show progress to user and ask to continue.
+
+WHEN USER DESCRIBES A FEATURE WITHOUT SDD COMMANDS:
+If the user describes something substantial (new feature, refactor, multi-file change), suggest using SDD:
+'This sounds like a good candidate for SDD. Want me to start with /sdd-new {suggested-name}?'
+Do NOT force SDD on small tasks (single file edits, quick fixes, questions).
diff --git a/examples/windsurf/.windsurf/workflows/sdd-verify.md b/examples/windsurf/.windsurf/workflows/sdd-verify.md
new file mode 100644
index 0000000..57a37d3
--- /dev/null
+++ b/examples/windsurf/.windsurf/workflows/sdd-verify.md
@@ -0,0 +1,22 @@
+---
+description: Validate implementation matches specs, design, and tasks
+agent: sdd-orchestrator
+subtask: true
+---
+
+You are an SDD sub-agent. Read the skill file at ~/.config/opencode/skills/sdd-verify/SKILL.md FIRST, then follow its instructions exactly.
+
+CONTEXT:
+- Working directory: {workdir}
+- Current project: {project}
+- Artifact store mode: engram
+
+TASK:
+Verify the active SDD change. Read the proposal, specs, design, and tasks artifacts. Then:
+1. Check completeness — are all tasks done?
+2. Check correctness — does code match specs?
+3. Check coherence — were design decisions followed?
+4. Run tests and build (real execution)
+5. Build the spec compliance matrix
+
+Return a structured verification report with: status, executive_summary, detailed_report, artifacts, and next_recommended.
diff --git a/scripts/install.ps1 b/scripts/install.ps1
index ea327c3..ef509f8 100644
--- a/scripts/install.ps1
+++ b/scripts/install.ps1
@@ -23,7 +23,7 @@
 [CmdletBinding()]
 param(
     [ValidateSet('claude-code', 'opencode', 'gemini-cli', 'codex', 'vscode',
-                 'antigravity', 'cursor', 'project-local', 'all-global', 'custom')]
+                 'antigravity', 'cursor', 'windsurf', 'project-local', 'all-global', 'custom')]
     [string]$Agent,
     [string]$Path,
     [switch]$Help
@@ -40,15 +40,17 @@ $RepoDir = Split-Path -Parent $ScriptRoot
 $SkillsSrc = Join-Path $RepoDir 'skills'
 
 $ToolPaths = @{
-    'claude-code'       = Join-Path $env:USERPROFILE '.claude\skills'
-    'opencode'          = Join-Path $env:USERPROFILE '.config\opencode\skills'
-    'opencode-commands' = Join-Path $env:USERPROFILE '.config\opencode\commands'
-    'gemini-cli'        = Join-Path $env:USERPROFILE '.gemini\skills'
-    'codex'             = Join-Path $env:USERPROFILE '.codex\skills'
-    'vscode'            = Join-Path '.' '.vscode\skills'
-    'antigravity'       = Join-Path $env:USERPROFILE '.gemini\antigravity\skills'
-    'cursor'            = Join-Path $env:USERPROFILE '.cursor\skills'
-    'project-local'     = Join-Path '.' 'skills'
+    'claude-code'        = Join-Path $env:USERPROFILE '.claude\skills'
+    'opencode'           = Join-Path $env:USERPROFILE '.config\opencode\skills'
+    'opencode-commands'  = Join-Path $env:USERPROFILE '.config\opencode\commands'
+    'gemini-cli'         = Join-Path $env:USERPROFILE '.gemini\skills'
+    'codex'              = Join-Path $env:USERPROFILE '.codex\skills'
+    'vscode'             = Join-Path '.' '.vscode\skills'
+    'antigravity'        = Join-Path $env:USERPROFILE '.gemini\antigravity\skills'
+    'cursor'             = Join-Path $env:USERPROFILE '.cursor\skills'
+    'windsurf'           = Join-Path $env:USERPROFILE '.agents\skills'
+    'windsurf-workflows' = Join-Path '.' '.windsurf\workflows'
+    'project-local'      = Join-Path '.' 'skills'
 }
 
 # ============================================================================
@@ -122,7 +124,7 @@ function Show-Usage {
     Write-Host '  -Path DIR      Custom install path (use with -Agent custom)'
     Write-Host '  -Help          Show this help'
     Write-Host ''
-    Write-Host 'Agents: claude-code, opencode, gemini-cli, codex, vscode, antigravity, cursor, project-local, all-global'
+    Write-Host 'Agents: claude-code, opencode, gemini-cli, codex, vscode, antigravity, cursor, windsurf, project-local, all-global'
 }
 
 # ============================================================================
@@ -236,6 +238,31 @@ function Install-OpenCodeCommands {
     Write-Host " -> $commandsTarget"
 }
 
+function Install-WindsurfWorkflows {
+    $workflowsSrc = Join-Path $RepoDir 'examples\windsurf\.windsurf\workflows'
+    $workflowsTarget = $ToolPaths['windsurf-workflows']
+
+    Write-Host ''
+    Write-Host 'Installing Windsurf workflows...' -ForegroundColor Blue
+
+    New-Item -ItemType Directory -Path $workflowsTarget -Force | Out-Null
+
+    $count = 0
+    $workflowFiles = Get-ChildItem -Path $workflowsSrc -File -Filter 'sdd-*.md'
+
+    foreach ($workflowFile in $workflowFiles) {
+        $workflowName = $workflowFile.BaseName
+        Copy-Item -Path $workflowFile.FullName -Destination (Join-Path $workflowsTarget $workflowFile.Name) -Force
+
+        Write-Skill $workflowName
+        $count++
+    }
+
+    Write-Host ''
+    Write-Host "  $count workflows installed" -ForegroundColor Green -NoNewline
+    Write-Host " -> $workflowsTarget"
+}
+
 # ============================================================================
 # Agent Install Dispatcher
 # ============================================================================
@@ -284,6 +311,28 @@ function Install-ForAgent {
             Install-Skills -TargetDir $ToolPaths['cursor'] -ToolName 'Cursor'
             Write-NextStep '.cursorrules' 'examples\cursor\.cursorrules'
         }
+        'windsurf' {
+            Install-Skills -TargetDir $ToolPaths['windsurf'] -ToolName 'Windsurf'
+            Install-WindsurfWorkflows
+            Write-Host ''
+            Write-Host 'Note: ' -ForegroundColor Yellow -NoNewline
+            Write-Host "Skills installed to " -NoNewline
+            Write-Host "~\.agents\skills\" -ForegroundColor White
+            Write-Host '       Workflows installed to ' -NoNewline
+            Write-Host '.windsurf\workflows\ ' -ForegroundColor White -NoNewline
+            Write-Host '(project-local)'
+            Write-Host ''
+            Write-Host 'How to use:' -ForegroundColor Yellow
+            Write-Host '  • Open Windsurf in your project'
+            Write-Host '  • Workflows are auto-discovered from .windsurf/workflows/'
+            Write-Host '  • Use slash commands: ' -NoNewline
+            Write-Host '/sdd-init' -ForegroundColor Cyan -NoNewline
+            Write-Host ', ' -NoNewline
+            Write-Host '/sdd-new <name>' -ForegroundColor Cyan -NoNewline
+            Write-Host ', ' -NoNewline
+            Write-Host '/sdd-apply' -ForegroundColor Cyan -NoNewline
+            Write-Host ', etc.'
+        }
         'project-local' {
             Install-Skills -TargetDir $ToolPaths['project-local'] -ToolName 'Project-local'
             Write-Host ''
@@ -296,6 +345,8 @@ function Install-ForAgent {
             Install-Skills -TargetDir $ToolPaths['gemini-cli'] -ToolName 'Gemini CLI'
             Install-Skills -TargetDir $ToolPaths['codex'] -ToolName 'Codex'
             Install-Skills -TargetDir $ToolPaths['cursor'] -ToolName 'Cursor'
+            Install-Skills -TargetDir $ToolPaths['windsurf'] -ToolName 'Windsurf'
+            Install-WindsurfWorkflows
             Write-Host ''
             Write-Host 'Next steps:' -ForegroundColor Yellow
             Write-Host '  1. Add orchestrator to ' -NoNewline
@@ -311,6 +362,9 @@ function Install-ForAgent {
             Write-Host 'Codex instructions file' -ForegroundColor White
             Write-Host '  5. Add SDD rules to ' -NoNewline
             Write-Host '.cursorrules' -ForegroundColor White
+            Write-Host '  6. Windsurf workflows installed to ' -NoNewline
+            Write-Host '.windsurf\workflows\' -ForegroundColor White -NoNewline
+            Write-Host ' (auto-discovered)'
         }
         'custom' {
             $customPath = $Path
@@ -346,12 +400,13 @@ function Show-Menu {
     Write-Host "   5) VS Code        ($($ToolPaths['vscode']))"
     Write-Host "   6) Antigravity    ($($ToolPaths['antigravity']))"
     Write-Host "   7) Cursor         ($($ToolPaths['cursor']))"
-    Write-Host "   8) Project-local  ($($ToolPaths['project-local']))"
-    Write-Host '   9) All global     (Claude Code + OpenCode + Gemini CLI + Codex + Cursor)'
-    Write-Host '  10) Custom path'
+    Write-Host "   8) Windsurf       ($($ToolPaths['windsurf']) + .windsurf\workflows\)"
+    Write-Host "   9) Project-local  ($($ToolPaths['project-local']))"
+    Write-Host '  10) All global     (Claude Code + OpenCode + Gemini CLI + Codex + Cursor + Windsurf)'
+    Write-Host '  11) Custom path'
     Write-Host ''
 
-    $choice = Read-Host 'Choice [1-10]'
+    $choice = Read-Host 'Choice [1-11]'
 
     $agentMap = @{
         '1'  = 'claude-code'
@@ -361,9 +416,10 @@ function Show-Menu {
         '5'  = 'vscode'
         '6'  = 'antigravity'
         '7'  = 'cursor'
-        '8'  = 'project-local'
-        '9'  = 'all-global'
-        '10' = 'custom'
+        '8'  = 'windsurf'
+        '9'  = 'project-local'
+        '10' = 'all-global'
+        '11' = 'custom'
     }
 
     if ($agentMap.ContainsKey($choice)) {
diff --git a/scripts/install.sh b/scripts/install.sh
index 984b0e0..f5551a0 100755
--- a/scripts/install.sh
+++ b/scripts/install.sh
@@ -115,6 +115,14 @@ get_tool_path() {
                 *)        echo "$HOME/.cursor/skills" ;;
             esac
             ;;
+        windsurf)
+            case "$OS" in
+                windows)  echo "$USERPROFILE/.agents/skills" ;;
+                wsl)      echo "$HOME/.agents/skills" ;;
+                *)        echo "$HOME/.agents/skills" ;;
+            esac
+            ;;
+        windsurf-workflows) echo "./.windsurf/workflows" ;;
         project-local) echo "./skills" ;;
     esac
 }
@@ -174,7 +182,7 @@ show_help() {
     echo "  --path DIR      Custom install path (use with --agent custom)"
     echo "  -h, --help      Show this help"
     echo ""
-    echo "Agents: claude-code, opencode, gemini-cli, codex, vscode, antigravity, cursor, project-local, all-global"
+    echo "Agents: claude-code, opencode, gemini-cli, codex, vscode, antigravity, cursor, windsurf, project-local, all-global"
 }
 
 # ============================================================================
@@ -276,6 +284,27 @@ install_opencode_commands() {
     echo -e "\n  ${GREEN}${BOLD}$count commands installed${NC} → $commands_target"
 }
 
+install_windsurf_workflows() {
+    local workflows_src="$REPO_DIR/examples/windsurf/.windsurf/workflows"
+    local workflows_target
+    workflows_target="$(get_tool_path windsurf-workflows)"
+
+    echo -e "\n${BLUE}Installing Windsurf workflows...${NC}"
+
+    mkdir -p "$workflows_target"
+
+    local count=0
+    for workflow_file in "$workflows_src"/sdd-*.md; do
+        local workflow_name
+        workflow_name=$(basename "$workflow_file")
+        cp "$workflow_file" "$workflows_target/$workflow_name"
+        print_skill "${workflow_name%.md}"
+        count=$((count + 1))
+    done
+
+    echo -e "\n  ${GREEN}${BOLD}$count workflows installed${NC} → $workflows_target"
+}
+
 # ============================================================================
 # Agent install dispatcher
 # ============================================================================
@@ -325,6 +354,16 @@ install_for_agent() {
             install_skills "$(get_tool_path cursor)" "Cursor"
             print_next_step ".cursorrules" "examples/cursor/.cursorrules"
             ;;
+        windsurf)
+            install_skills "$(get_tool_path windsurf)" "Windsurf"
+            install_windsurf_workflows
+            echo -e "\n${YELLOW}Note:${NC} Skills installed to ${BOLD}~/.agents/skills/${NC}"
+            echo -e "       Workflows installed to ${BOLD}./.windsurf/workflows/${NC} (project-local)"
+            echo -e "\n${YELLOW}How to use:${NC}"
+            echo -e "  • Open Windsurf in your project"
+            echo -e "  • Workflows are auto-discovered from .windsurf/workflows/"
+            echo -e "  • Use slash commands: ${CYAN}/sdd-init${NC}, ${CYAN}/sdd-new <name>${NC}, ${CYAN}/sdd-apply${NC}, etc."
+            ;;
         project-local)
             install_skills "$(get_tool_path project-local)" "Project-local"
             echo -e "\n${YELLOW}Note:${NC} Skills installed in ${BOLD}./skills/${NC} — relative to this project"
@@ -336,6 +375,8 @@ install_for_agent() {
             install_skills "$(get_tool_path gemini-cli)" "Gemini CLI"
             install_skills "$(get_tool_path codex)" "Codex"
             install_skills "$(get_tool_path cursor)" "Cursor"
+            install_skills "$(get_tool_path windsurf)" "Windsurf"
+            install_windsurf_workflows
             echo -e "\n${YELLOW}Next steps:${NC}"
             echo -e "  1. Add orchestrator to ${BOLD}~/.claude/CLAUDE.md${NC}"
             echo -e "  2. ${YELLOW}${BOLD}[REQUIRED]${NC} Add orchestrator agent to ${BOLD}~/.config/opencode/opencode.json${NC}"
@@ -343,6 +384,7 @@ install_for_agent() {
             echo -e "  3. Add orchestrator to ${BOLD}~/.gemini/GEMINI.md${NC}"
             echo -e "  4. Add orchestrator to ${BOLD}Codex instructions file${NC}"
             echo -e "  5. Add SDD rules to ${BOLD}.cursorrules${NC}"
+            echo -e "  6. Windsurf workflows installed to ${BOLD}./.windsurf/workflows/${NC} (auto-discovered)"
             ;;
         custom)
             if [[ -z "${CUSTOM_PATH:-}" ]]; then
@@ -372,11 +414,12 @@ interactive_menu() {
     echo "  5) VS Code        ($(get_tool_path vscode))"
     echo "  6) Antigravity    (~/.gemini/antigravity/skills/)"
     echo "  7) Cursor         ($(get_tool_path cursor))"
-    echo "  8) Project-local  ($(get_tool_path project-local))"
-    echo "  9) All global     (Claude Code + OpenCode + Gemini CLI + Codex + Cursor)"
-    echo "  10) Custom path"
+    echo "  8) Windsurf       ($(get_tool_path windsurf) + .windsurf/workflows/)"
+    echo "  9) Project-local  ($(get_tool_path project-local))"
+    echo "  10) All global    (Claude Code + OpenCode + Gemini CLI + Codex + Cursor + Windsurf)"
+    echo "  11) Custom path"
     echo ""
-    read -rp "Choice [1-10]: " choice
+    read -rp "Choice [1-11]: " choice
 
     case $choice in
         1)  install_for_agent "claude-code" ;;
@@ -386,9 +429,10 @@ interactive_menu() {
         5)  install_for_agent "vscode" ;;
         6)  install_for_agent "antigravity" ;;
         7)  install_for_agent "cursor" ;;
-        8)  install_for_agent "project-local" ;;
-        9)  install_for_agent "all-global" ;;
-        10) install_for_agent "custom" ;;
+        8)  install_for_agent "windsurf" ;;
+        9)  install_for_agent "project-local" ;;
+        10) install_for_agent "all-global" ;;
+        11) install_for_agent "custom" ;;
         *)
             print_error "Invalid choice"
             exit 1
diff --git a/scripts/install_test.sh b/scripts/install_test.sh
index 48b48bd..d92148e 100644
--- a/scripts/install_test.sh
+++ b/scripts/install_test.sh
@@ -146,6 +146,7 @@ test_help_flag() {
     echo "$output" | grep -q "Usage:" || { echo "Help output missing 'Usage:'"; return 1; }
     echo "$output" | grep -q "claude-code" || { echo "Help output missing 'claude-code'"; return 1; }
     echo "$output" | grep -q "opencode" || { echo "Help output missing 'opencode'"; return 1; }
+    echo "$output" | grep -q "windsurf" || { echo "Help output missing 'windsurf'"; return 1; }
     echo "$output" | grep -q "all-global" || { echo "Help output missing 'all-global'"; return 1; }
     echo "$output" | grep -q "\-\-agent" || { echo "Help output missing '--agent'"; return 1; }
     echo "$output" | grep -q "\-\-path" || { echo "Help output missing '--path'"; return 1; }
@@ -306,6 +307,44 @@ test_cursor_skill_count() {
     assert_eq "9" "$count" "Expected exactly 9 skills for Cursor"
 }
 
+# ============================================================================
+# Tests — Windsurf
+# ============================================================================
+
+test_install_windsurf() {
+    local project="$TEST_TMPDIR/windsurf-project"
+    mkdir -p "$project"
+    (cd "$project" && bash "$INSTALL_SCRIPT" --agent windsurf > /dev/null 2>&1)
+    assert_all_skills_installed "$HOME/.agents/skills"
+}
+
+test_windsurf_skill_count() {
+    bash "$INSTALL_SCRIPT" --agent windsurf > /dev/null 2>&1
+    local count
+    count=$(find "$HOME/.agents/skills" -name "SKILL.md" | wc -l | tr -d ' ')
+    assert_eq "9" "$count" "Expected exactly 9 skills for Windsurf"
+}
+
+test_windsurf_workflows() {
+    local project="$TEST_TMPDIR/windsurf-project"
+    mkdir -p "$project"
+    (cd "$project" && bash "$INSTALL_SCRIPT" --agent windsurf > /dev/null 2>&1)
+    local workflows_dir="$project/.windsurf/workflows"
+    assert_dir_exists "$workflows_dir" || return 1
+    assert_file_exists "$workflows_dir/sdd-init.md" || return 1
+    assert_file_exists "$workflows_dir/sdd-apply.md" || return 1
+    assert_file_exists "$workflows_dir/sdd-explore.md" || return 1
+    assert_file_exists "$workflows_dir/sdd-verify.md" || return 1
+    assert_file_exists "$workflows_dir/sdd-archive.md" || return 1
+    assert_file_exists "$workflows_dir/sdd-new.md" || return 1
+    assert_file_exists "$workflows_dir/sdd-ff.md" || return 1
+    assert_file_exists "$workflows_dir/sdd-continue.md" || return 1
+    assert_file_exists "$workflows_dir/sdd-orchestrator.md" || return 1
+    local count
+    count=$(find "$workflows_dir" -name "sdd-*.md" | wc -l | tr -d ' ')
+    assert_eq "9" "$count" "Expected exactly 9 Windsurf workflows"
+}
+
 # ============================================================================
 # Tests — Project-local
 # ============================================================================
@@ -349,7 +388,9 @@ test_custom_path_skill_count() {
 # ============================================================================
 
 test_all_global() {
-    bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1
+    local project="$TEST_TMPDIR/all-global-project"
+    mkdir -p "$project"
+    (cd "$project" && bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1)
     # Claude Code
     assert_all_skills_installed "$HOME/.claude/skills" || return 1
     # OpenCode
@@ -360,28 +401,35 @@ test_all_global() {
     assert_all_skills_installed "$HOME/.codex/skills" || return 1
     # Cursor
     assert_all_skills_installed "$HOME/.cursor/skills" || return 1
+    # Windsurf
+    assert_all_skills_installed "$HOME/.agents/skills" || return 1
 }
 
 test_all_global_total_skill_count() {
-    bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1
-    # 5 targets × 9 skills = 45 SKILL.md files
+    local project="$TEST_TMPDIR/all-global-project"
+    mkdir -p "$project"
+    (cd "$project" && bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1)
+    # 6 targets × 9 skills = 54 SKILL.md files
     local total=0
     for dir in \
         "$HOME/.claude/skills" \
         "$HOME/.config/opencode/skills" \
         "$HOME/.gemini/skills" \
         "$HOME/.codex/skills" \
-        "$HOME/.cursor/skills"; do
+        "$HOME/.cursor/skills" \
+        "$HOME/.agents/skills"; do
         local count
         count=$(find "$dir" -name "SKILL.md" | wc -l | tr -d ' ')
         assert_eq "9" "$count" "Expected 9 skills in $dir" || return 1
         total=$((total + count))
     done
-    assert_eq "45" "$total" "Expected 45 total SKILL.md files across all targets"
+    assert_eq "54" "$total" "Expected 54 total SKILL.md files across all targets"
 }
 
 test_all_global_opencode_commands() {
-    bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1
+    local project="$TEST_TMPDIR/all-global-project"
+    mkdir -p "$project"
+    (cd "$project" && bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1)
     local commands_dir="$HOME/.config/opencode/commands"
     assert_dir_exists "$commands_dir" || return 1
     local count
@@ -389,6 +437,17 @@ test_all_global_opencode_commands() {
     assert_eq "8" "$count" "Expected 8 OpenCode commands with all-global"
 }
 
+test_all_global_windsurf_workflows() {
+    local project="$TEST_TMPDIR/all-global-project"
+    mkdir -p "$project"
+    (cd "$project" && bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1)
+    local workflows_dir="$project/.windsurf/workflows"
+    assert_dir_exists "$workflows_dir" || return 1
+    local count
+    count=$(find "$workflows_dir" -name "sdd-*.md" | wc -l | tr -d ' ')
+    assert_eq "9" "$count" "Expected 9 Windsurf workflows with all-global"
+}
+
 # ============================================================================
 # Tests — Idempotency
 # ============================================================================
@@ -415,14 +474,17 @@ test_idempotent_opencode() {
 }
 
 test_idempotent_all_global() {
-    bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1
-    bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1
+    local project="$TEST_TMPDIR/idempotent-project"
+    mkdir -p "$project"
+    (cd "$project" && bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1)
+    (cd "$project" && bash "$INSTALL_SCRIPT" --agent all-global > /dev/null 2>&1)
     for dir in \
         "$HOME/.claude/skills" \
         "$HOME/.config/opencode/skills" \
         "$HOME/.gemini/skills" \
         "$HOME/.codex/skills" \
-        "$HOME/.cursor/skills"; do
+        "$HOME/.cursor/skills" \
+        "$HOME/.agents/skills"; do
         local count
         count=$(find "$dir" -name "SKILL.md" | wc -l | tr -d ' ')
         assert_eq "9" "$count" "Expected 9 skills in $dir after double install" || return 1
@@ -627,6 +689,12 @@ run_test "Installs all 9 skills to ~/.cursor/skills" test_install_cursor
 run_test "Exactly 9 SKILL.md files" test_cursor_skill_count
 echo ""
 
+echo -e "${BOLD}Windsurf${NC}"
+run_test "Installs all 9 skills to ~/.agents/skills" test_install_windsurf
+run_test "Exactly 9 SKILL.md files" test_windsurf_skill_count
+run_test "Installs 9 workflow files" test_windsurf_workflows
+echo ""
+
 echo -e "${BOLD}Project-local${NC}"
 run_test "Installs all 9 skills to ./skills/" test_install_project_local
 run_test "Exactly 9 SKILL.md files" test_project_local_skill_count
@@ -639,9 +707,10 @@ run_test "Handles deeply nested custom path" test_nested_custom_path
 echo ""
 
 echo -e "${BOLD}All-global${NC}"
-run_test "Installs to all 5 global targets" test_all_global
-run_test "45 total SKILL.md files (5×9)" test_all_global_total_skill_count
+run_test "Installs to all 6 global targets" test_all_global
+run_test "54 total SKILL.md files (6×9)" test_all_global_total_skill_count
 run_test "Also installs OpenCode commands" test_all_global_opencode_commands
+run_test "Also installs Windsurf workflows" test_all_global_windsurf_workflows
 echo ""
 
 echo -e "${BOLD}Idempotency${NC}"