Fix reload instructions to be platform-specific and actionable

.claude/commands/deepwork_jobs.implement.md

@@ -231,11 +231,9 @@ This will:
 - Generate slash-commands for each step
 - Make the commands available in `.claude/commands/` (or appropriate platform directory)
 
-### Step 6: Reload Commands
+### Step 6: Relay Reload Instructions
 
-Instruct the user to reload commands in their current session:
-- Run `/reload` command (if available)
-- Or restart the Claude session
+After running `deepwork sync`, look at the "To use the new commands" section in the output. **Relay these exact reload instructions to the user** so they know how to pick up the new commands. Don't just reference the sync output - tell them directly what they need to do (e.g., "Type 'exit' then run 'claude --resume'" for Claude Code, or "Run '/memory refresh'" for Gemini CLI).
 
 ### Step 7: Consider Policies for the New Job
 
@@ -461,7 +459,7 @@ After running `deepwork sync`, the following slash-commands are now available:
 
 ## Next Steps
 
-1. **Reload commands**: Run `/reload` or restart your Claude session
+1. **Reload commands**: [Include the specific reload instructions from the `deepwork sync` output here]
 2. **Start the workflow**: Run `/[job_name].[first_step_id]` to begin
 3. **Test the job**: Try executing the first step to ensure everything works
 
@@ -488,7 +486,7 @@ Before marking this step complete, ensure:
 - [ ] Each instruction file is complete and actionable
 - [ ] `deepwork sync` executed successfully
 - [ ] Commands generated in platform directory
-- [ ] User informed of next steps (reload commands)
+- [ ] User informed to follow reload instructions from `deepwork sync`
 - [ ] implementation_summary.md created
 - [ ] Considered whether policies would benefit this job (Step 7)
 - [ ] If policies suggested, offered to run `/deepwork_policy.define`

.claude/commands/deepwork_jobs.learn.md

@@ -291,7 +291,7 @@ If instruction files were modified:
    - [Any additional suggestions]
    ```
 
-3. **Instruct user to reload** if commands were regenerated
+3. **If commands were regenerated**, look at the "To use the new commands" section in the `deepwork sync` output and **relay these exact reload instructions to the user** (e.g., "Type 'exit' then run 'claude --resume'" for Claude Code)
 
 ## File Reference Patterns
 
@@ -382,7 +382,7 @@ I found the following job executions:
 
 **Summary**
 
-Created `learning_summary.md` documenting all changes. Please run `/reload` to get the updated commands.
+Created `learning_summary.md` documenting all changes. To get the updated commands, type 'exit' then run 'claude --resume'.
 ```
 
 ## Handling Edge Cases

.deepwork/jobs/deepwork_jobs/steps/implement.md

@@ -161,11 +161,9 @@ This will:
 - Generate slash-commands for each step
 - Make the commands available in `.claude/commands/` (or appropriate platform directory)
 
-### Step 6: Reload Commands
+### Step 6: Relay Reload Instructions
 
-Instruct the user to reload commands in their current session:
-- Run `/reload` command (if available)
-- Or restart the Claude session
+After running `deepwork sync`, look at the "To use the new commands" section in the output. **Relay these exact reload instructions to the user** so they know how to pick up the new commands. Don't just reference the sync output - tell them directly what they need to do (e.g., "Type 'exit' then run 'claude --resume'" for Claude Code, or "Run '/memory refresh'" for Gemini CLI).
 
 ### Step 7: Consider Policies for the New Job
 
@@ -391,7 +389,7 @@ After running `deepwork sync`, the following slash-commands are now available:
 
 ## Next Steps
 
-1. **Reload commands**: Run `/reload` or restart your Claude session
+1. **Reload commands**: [Include the specific reload instructions from the `deepwork sync` output here]
 2. **Start the workflow**: Run `/[job_name].[first_step_id]` to begin
 3. **Test the job**: Try executing the first step to ensure everything works
 
@@ -418,7 +416,7 @@ Before marking this step complete, ensure:
 - [ ] Each instruction file is complete and actionable
 - [ ] `deepwork sync` executed successfully
 - [ ] Commands generated in platform directory
-- [ ] User informed of next steps (reload commands)
+- [ ] User informed to follow reload instructions from `deepwork sync`
 - [ ] implementation_summary.md created
 - [ ] Considered whether policies would benefit this job (Step 7)
 - [ ] If policies suggested, offered to run `/deepwork_policy.define`

.deepwork/jobs/deepwork_jobs/steps/learn.md

@@ -228,7 +228,7 @@ If instruction files were modified:
    - [Any additional suggestions]
    ```
 
-3. **Instruct user to reload** if commands were regenerated
+3. **If commands were regenerated**, look at the "To use the new commands" section in the `deepwork sync` output and **relay these exact reload instructions to the user** (e.g., "Type 'exit' then run 'claude --resume'" for Claude Code)
 
 ## File Reference Patterns
 
@@ -319,7 +319,7 @@ I found the following job executions:
 
 **Summary**
 
-Created `learning_summary.md` documenting all changes. Please run `/reload` to get the updated commands.
+Created `learning_summary.md` documenting all changes. To get the updated commands, type 'exit' then run 'claude --resume'.
 ```
 
 ## Handling Edge Cases

.gemini/commands/deepwork_jobs/implement.toml

@@ -199,11 +199,9 @@ This will:
 - Generate slash-commands for each step
 - Make the commands available in `.claude/commands/` (or appropriate platform directory)
 
-### Step 6: Reload Commands
+### Step 6: Relay Reload Instructions
 
-Instruct the user to reload commands in their current session:
-- Run `/reload` command (if available)
-- Or restart the Claude session
+After running `deepwork sync`, look at the "To use the new commands" section in the output. **Relay these exact reload instructions to the user** so they know how to pick up the new commands. Don't just reference the sync output - tell them directly what they need to do (e.g., "Type 'exit' then run 'claude --resume'" for Claude Code, or "Run '/memory refresh'" for Gemini CLI).
 
 ### Step 7: Consider Policies for the New Job
 
@@ -429,7 +427,7 @@ After running `deepwork sync`, the following slash-commands are now available:
 
 ## Next Steps
 
-1. **Reload commands**: Run `/reload` or restart your Claude session
+1. **Reload commands**: [Include the specific reload instructions from the `deepwork sync` output here]
 2. **Start the workflow**: Run `/[job_name].[first_step_id]` to begin
 3. **Test the job**: Try executing the first step to ensure everything works
 
@@ -456,7 +454,7 @@ Before marking this step complete, ensure:
 - [ ] Each instruction file is complete and actionable
 - [ ] `deepwork sync` executed successfully
 - [ ] Commands generated in platform directory
-- [ ] User informed of next steps (reload commands)
+- [ ] User informed to follow reload instructions from `deepwork sync`
 - [ ] implementation_summary.md created
 - [ ] Considered whether policies would benefit this job (Step 7)
 - [ ] If policies suggested, offered to run `/deepwork_policy.define`

.gemini/commands/deepwork_jobs/learn.toml

@@ -260,7 +260,7 @@ If instruction files were modified:
    - [Any additional suggestions]
    ```
 
-3. **Instruct user to reload** if commands were regenerated
+3. **If commands were regenerated**, look at the "To use the new commands" section in the `deepwork sync` output and **relay these exact reload instructions to the user** (e.g., "Type 'exit' then run 'claude --resume'" for Claude Code)
 
 ## File Reference Patterns
 
@@ -351,7 +351,7 @@ I found the following job executions:
 
 **Summary**
 
-Created `learning_summary.md` documenting all changes. Please run `/reload` to get the updated commands.
+Created `learning_summary.md` documenting all changes. To get the updated commands, run '/memory refresh' or restart your session.
 ```
 
 ## Handling Edge Cases

.gemini/commands/deepwork_jobs/refine.toml

@@ -292,7 +292,7 @@ After updating the changelog:
    ```
 
 2. **Reload commands**
-   - Instruct user to run `/reload` or restart session
+   - Instruct user to follow the reload instructions shown by `deepwork sync`
 
 3. **Provide summary**
    - Show what changed
@@ -410,7 +410,7 @@ Now run:
 deepwork sync
 ```
 
-Then reload your session and you'll have:
+Then follow the reload instructions shown by `deepwork sync` and you'll have:
 - /competitive_research.validate_positioning (new!)
 - All other commands updated
 ```

src/deepwork/cli/sync.py

@@ -117,6 +117,7 @@ def sync_commands(project_path: Path) -> None:
     # Sync each platform
     generator = CommandGenerator()
     stats = {"platforms": 0, "commands": 0, "hooks": 0}
+    synced_adapters: list[AgentAdapter] = []
 
     for platform_name in platforms:
         try:
@@ -157,6 +158,7 @@ def sync_commands(project_path: Path) -> None:
                 console.print(f"    [red]✗[/red] Failed to sync hooks: {e}")
 
         stats["platforms"] += 1
+        synced_adapters.append(adapter)
 
     # Summary
     console.print()
@@ -174,3 +176,10 @@ def sync_commands(project_path: Path) -> None:
 
     console.print(table)
     console.print()
+
+    # Show reload instructions for each synced platform
+    if synced_adapters and stats["commands"] > 0:
+        console.print("[bold]To use the new commands:[/bold]")
+        for adapter in synced_adapters:
+            console.print(f"  [cyan]{adapter.display_name}:[/cyan] {adapter.reload_instructions}")
+        console.print()

src/deepwork/core/adapters.py

@@ -57,6 +57,12 @@ class AgentAdapter(ABC):
     commands_dir: ClassVar[str] = "commands"
     command_template: ClassVar[str] = "command-job-step.md.jinja"
 
+    # Instructions for reloading commands after sync (shown to users)
+    # Subclasses should override with platform-specific instructions.
+    reload_instructions: ClassVar[str] = (
+        "Restart your AI assistant session to use the new commands."
+    )
+
     # Mapping from generic CommandLifecycleHook to platform-specific event names.
     # Subclasses should override this to provide platform-specific mappings.
     hook_name_mapping: ClassVar[dict[CommandLifecycleHook, str]] = {}
@@ -253,6 +259,12 @@ class ClaudeAdapter(AgentAdapter):
     display_name = "Claude Code"
     config_dir = ".claude"
 
+    # Claude Code doesn't have a reload command - must restart session
+    reload_instructions: ClassVar[str] = (
+        "Type 'exit' to leave your current session, then run "
+        "'claude --resume' (your history will be maintained)."
+    )
+
     # Claude Code uses PascalCase event names
     hook_name_mapping: ClassVar[dict[CommandLifecycleHook, str]] = {
         CommandLifecycleHook.AFTER_AGENT: "Stop",
@@ -333,6 +345,11 @@ class GeminiAdapter(AgentAdapter):
     config_dir = ".gemini"
     command_template = "command-job-step.toml.jinja"
 
+    # Gemini CLI can reload with /memory refresh
+    reload_instructions: ClassVar[str] = (
+        "Run '/memory refresh' to reload commands, or restart your Gemini CLI session."
+    )
+
     # Gemini CLI does NOT support command-level hooks
     # Hooks are global/project-level in settings.json, not per-command
     hook_name_mapping: ClassVar[dict[CommandLifecycleHook, str]] = {}

src/deepwork/standard_jobs/deepwork_jobs/steps/implement.md

@@ -167,11 +167,9 @@ This will:
 - Generate slash-commands for each step
 - Make the commands available in `.claude/commands/` (or appropriate platform directory)
 
-### Step 6: Reload Commands
+### Step 6: Relay Reload Instructions
 
-Instruct the user to reload commands in their current session:
-- Run `/reload` command (if available)
-- Or restart the Claude session
+After running `deepwork sync`, look at the "To use the new commands" section in the output. **Relay these exact reload instructions to the user** so they know how to pick up the new commands. Don't just reference the sync output - tell them directly what they need to do (e.g., "Type 'exit' then run 'claude --resume'" for Claude Code, or "Run '/memory refresh'" for Gemini CLI).
 
 ### Step 7: Consider Policies for the New Job
 
@@ -397,7 +395,7 @@ After running `deepwork sync`, the following slash-commands are now available:
 
 ## Next Steps
 
-1. **Reload commands**: Run `/reload` or restart your Claude session
+1. **Reload commands**: [Include the specific reload instructions from the `deepwork sync` output here]
 2. **Start the workflow**: Run `/[job_name].[first_step_id]` to begin
 3. **Test the job**: Try executing the first step to ensure everything works
 
@@ -424,7 +422,7 @@ Before marking this step complete, ensure:
 - [ ] Each instruction file is complete and actionable
 - [ ] `deepwork sync` executed successfully
 - [ ] Commands generated in platform directory
-- [ ] User informed of next steps (reload commands)
+- [ ] User informed to follow reload instructions from `deepwork sync`
 - [ ] implementation_summary.md created
 - [ ] Considered whether policies would benefit this job (Step 7)
 - [ ] If policies suggested, offered to run `/deepwork_policy.define`

src/deepwork/standard_jobs/deepwork_jobs/steps/learn.md

@@ -228,7 +228,7 @@ If instruction files were modified:
    - [Any additional suggestions]
    ```
 
-3. **Instruct user to reload** if commands were regenerated
+3. **If commands were regenerated**, look at the "To use the new commands" section in the `deepwork sync` output and **relay these exact reload instructions to the user** (e.g., "Type 'exit' then run 'claude --resume'" for Claude Code)
 
 ## File Reference Patterns
 
@@ -319,7 +319,7 @@ I found the following job executions:
 
 **Summary**
 
-Created `learning_summary.md` documenting all changes. Please run `/reload` to get the updated commands.
+Created `learning_summary.md` documenting all changes. To get the updated commands, type 'exit' then run 'claude --resume'.
 ```
 
 ## Handling Edge Cases