Improve command hooks promise message text (#16)

* Improve promise tag format to show policy name with checkmark

Change the promise tag body from generic "addressed" text to a more
compelling "✓ Policy Name" format that clearly shows which policy was
addressed. This provides better visibility for end users when viewing
the LLM's response.

* Simplify promise tag format and improve QUALITY_COMPLETE display

Changes:
- Remove redundant policy= attribute from promise tags
- New format: <promise>✓ Policy Name</promise>
- Extract policy name from tag body after checkmark
- Update QUALITY_COMPLETE to <promise>✓ Quality Criteria Met</promise>
- Update all documentation and tests

This makes the promise format less redundant and more user-friendly
when displayed in LLM responses.

* Format: use double quotes for consistency

---------

Co-authored-by: Claude <noreply@anthropic.com>

Author: nhorton

.claude/commands/add_platform.add_capabilities.md

@@ -18,15 +18,15 @@ hooks:
             5. adapters.py remains consistent - all adapters have the same hook fields
             6. If no new hooks are needed, document why in a comment
 
-            If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+            If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
 
             ## Instructions
 
             Review the conversation and determine if ALL quality criteria above have been satisfied.
             Look for evidence that each criterion has been addressed.
 
-            If the agent has included `<promise>QUALITY_COMPLETE</promise>` in their response AND
+            If the agent has included `<promise>✓ Quality Criteria Met</promise>` in their response AND
             all criteria appear to be met, respond with: {"ok": true}
 
             If criteria are NOT met AND the promise tag is missing, respond with:
@@ -178,7 +178,7 @@ Or if no changes are needed, add a documentation comment:
 - `job_schema.py` has no syntax errors (verified with py_compile)
 - `adapters.py` has no syntax errors (verified with py_compile)
 - All adapters have consistent hook fields (same fields across all adapters)
-- When all criteria are met, include `<promise>QUALITY_COMPLETE</promise>` in your response
+- When all criteria are met, include `<promise>✓ Quality Criteria Met</promise>` in your response
 
 ## Context
 
@@ -251,15 +251,15 @@ Verify the capability additions meet ALL criteria:
 5. adapters.py remains consistent - all adapters have the same hook fields
 6. If no new hooks are needed, document why in a comment
 
-If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
 
 ### Completion Promise
 
 To signal that all quality criteria have been met, include this tag in your final response:
 
 ```
-<promise>QUALITY_COMPLETE</promise>
+<promise>✓ Quality Criteria Met</promise>
 ```
 
 **Important**: Only include this promise tag when you have verified that ALL quality criteria above are satisfied. The validation loop will continue until this promise is detected.

.claude/commands/add_platform.implement.md

@@ -22,15 +22,15 @@ hooks:
                - Installation instructions for the platform
                - Any platform-specific notes
 
-            If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+            If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
 
             ## Instructions
 
             Review the conversation and determine if ALL quality criteria above have been satisfied.
             Look for evidence that each criterion has been addressed.
 
-            If the agent has included `<promise>QUALITY_COMPLETE</promise>` in their response AND
+            If the agent has included `<promise>✓ Quality Criteria Met</promise>` in their response AND
             all criteria appear to be met, respond with: {"ok": true}
 
             If criteria are NOT met AND the promise tag is missing, respond with:
@@ -281,7 +281,7 @@ deepwork install --platform <platform_name>
   - Platform listed in supported platforms
   - Installation command documented
   - Any platform-specific notes included
-- When all criteria are met, include `<promise>QUALITY_COMPLETE</promise>` in your response
+- When all criteria are met, include `<promise>✓ Quality Criteria Met</promise>` in your response
 
 ## Context
 
@@ -354,15 +354,15 @@ Verify the implementation meets ALL criteria:
    - Installation instructions for the platform
    - Any platform-specific notes
 
-If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
 
 ### Completion Promise
 
 To signal that all quality criteria have been met, include this tag in your final response:
 
 ```
-<promise>QUALITY_COMPLETE</promise>
+<promise>✓ Quality Criteria Met</promise>
 ```
 
 **Important**: Only include this promise tag when you have verified that ALL quality criteria above are satisfied. The validation loop will continue until this promise is detected.

.claude/commands/add_platform.research.md

@@ -19,15 +19,15 @@ hooks:
             5. No extraneous documentation (only these two specific topics)
             6. Documentation is comprehensive enough to implement the platform
 
-            If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+            If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
 
             ## Instructions
 
             Review the conversation and determine if ALL quality criteria above have been satisfied.
             Look for evidence that each criterion has been addressed.
 
-            If the agent has included `<promise>QUALITY_COMPLETE</promise>` in their response AND
+            If the agent has included `<promise>✓ Quality Criteria Met</promise>` in their response AND
             all criteria appear to be met, respond with: {"ok": true}
 
             If criteria are NOT met AND the promise tag is missing, respond with:
@@ -234,7 +234,7 @@ Source: [URL where this documentation was obtained]
   - NOT general CLI hooks (only command-level hooks)
 - Documentation is detailed enough to implement the platform adapter
 - No extraneous topics (only CLI config and command hooks)
-- When all criteria are met, include `<promise>QUALITY_COMPLETE</promise>` in your response
+- When all criteria are met, include `<promise>✓ Quality Criteria Met</promise>` in your response
 
 ## Context
 
@@ -298,15 +298,15 @@ Verify the research output meets ALL criteria:
 5. No extraneous documentation (only these two specific topics)
 6. Documentation is comprehensive enough to implement the platform
 
-If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
 
 ### Completion Promise
 
 To signal that all quality criteria have been met, include this tag in your final response:
 
 ```
-<promise>QUALITY_COMPLETE</promise>
+<promise>✓ Quality Criteria Met</promise>
 ```
 
 **Important**: Only include this promise tag when you have verified that ALL quality criteria above are satisfied. The validation loop will continue until this promise is detected.

.claude/commands/add_platform.verify.md

@@ -17,15 +17,15 @@ hooks:
             5. Established DeepWork jobs (deepwork_jobs, deepwork_policy) are installed correctly
             6. The platform can be used alongside existing platforms without conflicts
 
-            If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+            If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
 
             ## Instructions
 
             Review the conversation and determine if ALL quality criteria above have been satisfied.
             Look for evidence that each criterion has been addressed.
 
-            If the agent has included `<promise>QUALITY_COMPLETE</promise>` in their response AND
+            If the agent has included `<promise>✓ Quality Criteria Met</promise>` in their response AND
             all criteria appear to be met, respond with: {"ok": true}
 
             If criteria are NOT met AND the promise tag is missing, respond with:
@@ -159,7 +159,7 @@ Ensure the implementation step is complete:
   - No template errors or missing content
 - Existing platforms still work (if applicable)
 - No conflicts between platforms
-- When all criteria are met, include `<promise>QUALITY_COMPLETE</promise>` in your response
+- When all criteria are met, include `<promise>✓ Quality Criteria Met</promise>` in your response
 
 ## Context
 
@@ -221,15 +221,15 @@ Verify the installation meets ALL criteria:
 5. Established DeepWork jobs (deepwork_jobs, deepwork_policy) are installed correctly
 6. The platform can be used alongside existing platforms without conflicts
 
-If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
 
 ### Completion Promise
 
 To signal that all quality criteria have been met, include this tag in your final response:
 
 ```
-<promise>QUALITY_COMPLETE</promise>
+<promise>✓ Quality Criteria Met</promise>
 ```
 
 **Important**: Only include this promise tag when you have verified that ALL quality criteria above are satisfied. The validation loop will continue until this promise is detected.

.claude/commands/deepwork_jobs.define.md

@@ -20,15 +20,15 @@ hooks:
             7. **File Created**: Has the job.yml file been created in `.deepwork/jobs/[job_name]/job.yml`?
 
             If ANY criterion is not met, continue working to address it.
-            If ALL criteria are satisfied, include `<promise>QUALITY_COMPLETE</promise>` in your response.
+            If ALL criteria are satisfied, include `<promise>✓ Quality Criteria Met</promise>` in your response.
 
 
             ## Instructions
 
             Review the conversation and determine if ALL quality criteria above have been satisfied.
             Look for evidence that each criterion has been addressed.
 
-            If the agent has included `<promise>QUALITY_COMPLETE</promise>` in their response AND
+            If the agent has included `<promise>✓ Quality Criteria Met</promise>` in their response AND
             all criteria appear to be met, respond with: {"ok": true}
 
             If criteria are NOT met AND the promise tag is missing, respond with:
@@ -235,7 +235,7 @@ steps:
           Verify this step's output meets quality criteria:
           1. [Criterion 1]
           2. [Criterion 2]
-          If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+          If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
   - id: [another_step]
     name: "[Another Step]"
@@ -464,15 +464,15 @@ Verify the job.yml output meets ALL quality criteria before completing:
 7. **File Created**: Has the job.yml file been created in `.deepwork/jobs/[job_name]/job.yml`?
 
 If ANY criterion is not met, continue working to address it.
-If ALL criteria are satisfied, include `<promise>QUALITY_COMPLETE</promise>` in your response.
+If ALL criteria are satisfied, include `<promise>✓ Quality Criteria Met</promise>` in your response.
 
 
 ### Completion Promise
 
 To signal that all quality criteria have been met, include this tag in your final response:
 
 ```
-<promise>QUALITY_COMPLETE</promise>
+<promise>✓ Quality Criteria Met</promise>
 ```
 
 **Important**: Only include this promise tag when you have verified that ALL quality criteria above are satisfied. The validation loop will continue until this promise is detected.

.claude/commands/deepwork_jobs.implement.md

@@ -24,15 +24,15 @@ hooks:
                - Not every job needs policies - only suggest when genuinely helpful.
 
             If ANY criterion is not met, continue working to address it.
-            If ALL criteria are satisfied, include `<promise>QUALITY_COMPLETE</promise>` in your response.
+            If ALL criteria are satisfied, include `<promise>✓ Quality Criteria Met</promise>` in your response.
 
 
             ## Instructions
 
             Review the conversation and determine if ALL quality criteria above have been satisfied.
             Look for evidence that each criterion has been addressed.
 
-            If the agent has included `<promise>QUALITY_COMPLETE</promise>` in their response AND
+            If the agent has included `<promise>✓ Quality Criteria Met</promise>` in their response AND
             all criteria appear to be met, respond with: {"ok": true}
 
             If criteria are NOT met AND the promise tag is missing, respond with:
@@ -187,7 +187,7 @@ If a step in the job.yml has `stop_hooks` defined, the generated instruction fil
 
 1. **Mirror the quality criteria** - The "Quality Criteria" section should match what the stop hooks will validate
 2. **Be explicit about success** - Help the agent understand when the step is truly complete
-3. **Include the promise pattern** - Mention that `<promise>QUALITY_COMPLETE</promise>` should be included when criteria are met
+3. **Include the promise pattern** - Mention that `<promise>✓ Quality Criteria Met</promise>` should be included when criteria are met
 
 **Example: If the job.yml has:**
 ```yaml
@@ -208,7 +208,7 @@ If a step in the job.yml has `stop_hooks` defined, the generated instruction fil
 - Each competitor has at least 3 distinct data points
 - All information is sourced with citations
 - Data is current (from within the last year)
-- When all criteria are met, include `<promise>QUALITY_COMPLETE</promise>` in your response
+- When all criteria are met, include `<promise>✓ Quality Criteria Met</promise>` in your response
 ```
 
 This alignment ensures the AI agent knows exactly what will be validated and can self-check before completing.
@@ -556,15 +556,15 @@ Verify the implementation meets ALL quality criteria before completing:
    - Not every job needs policies - only suggest when genuinely helpful.
 
 If ANY criterion is not met, continue working to address it.
-If ALL criteria are satisfied, include `<promise>QUALITY_COMPLETE</promise>` in your response.
+If ALL criteria are satisfied, include `<promise>✓ Quality Criteria Met</promise>` in your response.
 
 
 ### Completion Promise
 
 To signal that all quality criteria have been met, include this tag in your final response:
 
 ```
-<promise>QUALITY_COMPLETE</promise>
+<promise>✓ Quality Criteria Met</promise>
 ```
 
 **Important**: Only include this promise tag when you have verified that ALL quality criteria above are satisfied. The validation loop will continue until this promise is detected.

.claude/commands/deepwork_jobs.refine.md

@@ -21,15 +21,15 @@ hooks:
             8. **Sync Complete**: Has `deepwork sync` been run to regenerate commands?
 
             If ANY criterion is not met, continue working to address it.
-            If ALL criteria are satisfied, include `<promise>QUALITY_COMPLETE</promise>` in your response.
+            If ALL criteria are satisfied, include `<promise>✓ Quality Criteria Met</promise>` in your response.
 
 
             ## Instructions
 
             Review the conversation and determine if ALL quality criteria above have been satisfied.
             Look for evidence that each criterion has been addressed.
 
-            If the agent has included `<promise>QUALITY_COMPLETE</promise>` in their response AND
+            If the agent has included `<promise>✓ Quality Criteria Met</promise>` in their response AND
             all criteria appear to be met, respond with: {"ok": true}
 
             If criteria are NOT met AND the promise tag is missing, respond with:
@@ -554,15 +554,15 @@ Verify the refinement meets ALL quality criteria before completing:
 8. **Sync Complete**: Has `deepwork sync` been run to regenerate commands?
 
 If ANY criterion is not met, continue working to address it.
-If ALL criteria are satisfied, include `<promise>QUALITY_COMPLETE</promise>` in your response.
+If ALL criteria are satisfied, include `<promise>✓ Quality Criteria Met</promise>` in your response.
 
 
 ### Completion Promise
 
 To signal that all quality criteria have been met, include this tag in your final response:
 
 ```
-<promise>QUALITY_COMPLETE</promise>
+<promise>✓ Quality Criteria Met</promise>
 ```
 
 **Important**: Only include this promise tag when you have verified that ALL quality criteria above are satisfied. The validation loop will continue until this promise is detected.

.claude/commands/deepwork_policy.define.md

@@ -203,7 +203,7 @@ Policies are evaluated automatically when you finish working on a task. The syst
 3. Skips policies where safety patterns also matched
 4. Prompts you with instructions for any triggered policies
 
-You can mark a policy as addressed by including `<promise policy="Policy Name">considered</promise>` in your response. This tells the system you've already handled that policy's requirements.
+You can mark a policy as addressed by including `<promise>✓ Policy Name</promise>` in your response (replace Policy Name with the actual policy name). This tells the system you've already handled that policy's requirements.
 
 
 ## Inputs

.deepwork/jobs/add_platform/job.yml

@@ -49,7 +49,7 @@ steps:
             5. No extraneous documentation (only these two specific topics)
             6. Documentation is comprehensive enough to implement the platform
 
-            If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+            If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
   - id: add_capabilities
     name: "Add Hook Capabilities"
@@ -75,7 +75,7 @@ steps:
             5. adapters.py remains consistent - all adapters have the same hook fields
             6. If no new hooks are needed, document why in a comment
 
-            If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+            If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
   - id: implement
     name: "Implement Platform Support"
@@ -110,7 +110,7 @@ steps:
                - Installation instructions for the platform
                - Any platform-specific notes
 
-            If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+            If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.
 
   - id: verify
     name: "Verify Installation"
@@ -133,4 +133,4 @@ steps:
             5. Established DeepWork jobs (deepwork_jobs, deepwork_policy) are installed correctly
             6. The platform can be used alongside existing platforms without conflicts
 
-            If ALL criteria are met, include `<promise>QUALITY_COMPLETE</promise>`.
+            If ALL criteria are met, include `<promise>✓ Quality Criteria Met</promise>`.

.deepwork/jobs/add_platform/steps/add_capabilities.md

@@ -108,7 +108,7 @@ Or if no changes are needed, add a documentation comment:
 - `job_schema.py` has no syntax errors (verified with py_compile)
 - `adapters.py` has no syntax errors (verified with py_compile)
 - All adapters have consistent hook fields (same fields across all adapters)
-- When all criteria are met, include `<promise>QUALITY_COMPLETE</promise>` in your response
+- When all criteria are met, include `<promise>✓ Quality Criteria Met</promise>` in your response
 
 ## Context