Add AGENT: TAKE ACTION prefix to hook prompts

Prevents Claude from stopping when hooks are presented as errors.
Updated prompts in policy.yml, add_platform, update, and deepwork_jobs.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: nhorton

.claude/commands/deepwork_jobs.learn.md

@@ -9,7 +9,7 @@ hooks:
 
             ## Quality Criteria
 
-            Verify the learning process meets ALL quality criteria before completing:
+            **AGENT: TAKE ACTION** - Verify the learning process meets ALL quality criteria before completing:
 
             1. **Conversation Analyzed**: Did you review the conversation for DeepWork job executions?
             2. **Confusion Identified**: Did you identify points of confusion, errors, or inefficiencies?
@@ -386,7 +386,7 @@ Ensure all outputs are:
 This step uses an iterative quality validation loop. After completing your work, stop hook(s) will evaluate whether the outputs meet quality criteria. If criteria are not met, you will be prompted to continue refining.
 
 ### Quality Criteria
-Verify the learning process meets ALL quality criteria before completing:
+**AGENT: TAKE ACTION** - Verify the learning process meets ALL quality criteria before completing:
 
 1. **Conversation Analyzed**: Did you review the conversation for DeepWork job executions?
 2. **Confusion Identified**: Did you identify points of confusion, errors, or inefficiencies?

.claude/commands/uw.add_platform.add_capabilities.md

@@ -9,7 +9,7 @@ hooks:
 
             ## Quality Criteria
 
-            Verify the capability additions meet ALL criteria:
+            **AGENT: TAKE ACTION** - Verify the capability additions meet ALL criteria:
             1. Any new hooks from the platform (for slash commands only) are added to src/deepwork/schemas/job_schema.py
             2. All existing adapters in src/deepwork/adapters.py are updated with the new hook fields
                (set to None/null if the platform doesn't support that hook)
@@ -242,7 +242,7 @@ Ensure all outputs are:
 This step uses an iterative quality validation loop. After completing your work, stop hook(s) will evaluate whether the outputs meet quality criteria. If criteria are not met, you will be prompted to continue refining.
 
 ### Quality Criteria
-Verify the capability additions meet ALL criteria:
+**AGENT: TAKE ACTION** - Verify the capability additions meet ALL criteria:
 1. Any new hooks from the platform (for slash commands only) are added to src/deepwork/schemas/job_schema.py
 2. All existing adapters in src/deepwork/adapters.py are updated with the new hook fields
    (set to None/null if the platform doesn't support that hook)

.claude/commands/uw.add_platform.implement.md

@@ -11,7 +11,7 @@ hooks:
 
             ## Quality Criteria
 
-            Verify the implementation meets ALL criteria:
+            **AGENT: TAKE ACTION** - Verify the implementation meets ALL criteria:
             1. Platform adapter class is added to src/deepwork/adapters.py
             2. Templates exist in src/deepwork/templates/<platform>/ with appropriate command structure
             3. Tests exist for all new functionality
@@ -343,7 +343,7 @@ This step uses an iterative quality validation loop. After completing your work,
 
 The validation script will be executed automatically when you attempt to complete this step.
 ### Quality Criteria (2)
-Verify the implementation meets ALL criteria:
+**AGENT: TAKE ACTION** - Verify the implementation meets ALL criteria:
 1. Platform adapter class is added to src/deepwork/adapters.py
 2. Templates exist in src/deepwork/templates/<platform>/ with appropriate command structure
 3. Tests exist for all new functionality

.claude/commands/uw.add_platform.research.md

@@ -9,7 +9,7 @@ hooks:
 
             ## Quality Criteria
 
-            Verify the research output meets ALL criteria:
+            **AGENT: TAKE ACTION** - Verify the research output meets ALL criteria:
             1. Both files exist in doc/platforms/<platform>/: cli_configuration.md and hooks_system.md
             2. Each file has a comment at the top with:
                - Last updated date
@@ -288,7 +288,7 @@ Ensure all outputs are:
 This step uses an iterative quality validation loop. After completing your work, stop hook(s) will evaluate whether the outputs meet quality criteria. If criteria are not met, you will be prompted to continue refining.
 
 ### Quality Criteria
-Verify the research output meets ALL criteria:
+**AGENT: TAKE ACTION** - Verify the research output meets ALL criteria:
 1. Both files exist in doc/platforms/<platform>/: cli_configuration.md and hooks_system.md
 2. Each file has a comment at the top with:
    - Last updated date

.claude/commands/uw.add_platform.verify.md

@@ -9,7 +9,7 @@ hooks:
 
             ## Quality Criteria
 
-            Verify the installation meets ALL criteria:
+            **AGENT: TAKE ACTION** - Verify the installation meets ALL criteria:
             1. Platform-specific directories/files are added to the deepwork repo as needed
             2. Running `deepwork install --platform <platform>` completes without errors
             3. Expected command files are created in the platform's command directory
@@ -213,7 +213,7 @@ No specific files are output by this command.
 This step uses an iterative quality validation loop. After completing your work, stop hook(s) will evaluate whether the outputs meet quality criteria. If criteria are not met, you will be prompted to continue refining.
 
 ### Quality Criteria
-Verify the installation meets ALL criteria:
+**AGENT: TAKE ACTION** - Verify the installation meets ALL criteria:
 1. Platform-specific directories/files are added to the deepwork repo as needed
 2. Running `deepwork install --platform <platform>` completes without errors
 3. Expected command files are created in the platform's command directory

.claude/commands/uw.deepwork_jobs.define.md

@@ -9,7 +9,7 @@ hooks:
 
             ## Quality Criteria
 
-            Verify the job.yml output meets ALL quality criteria before completing:
+            **AGENT: TAKE ACTION** - Verify the job.yml output meets ALL quality criteria before completing:
 
             1. **User Understanding**: Did you fully understand the user's workflow by asking structured questions?
             2. **Structured Questions Used**: Did you ask structured questions (using the AskUserQuestion tool) to gather user input?
@@ -427,7 +427,7 @@ Ensure all outputs are:
 This step uses an iterative quality validation loop. After completing your work, stop hook(s) will evaluate whether the outputs meet quality criteria. If criteria are not met, you will be prompted to continue refining.
 
 ### Quality Criteria
-Verify the job.yml output meets ALL quality criteria before completing:
+**AGENT: TAKE ACTION** - Verify the job.yml output meets ALL quality criteria before completing:
 
 1. **User Understanding**: Did you fully understand the user's workflow by asking structured questions?
 2. **Structured Questions Used**: Did you ask structured questions (using the AskUserQuestion tool) to gather user input?

.claude/commands/uw.deepwork_jobs.implement.md

@@ -9,7 +9,7 @@ hooks:
 
             ## Quality Criteria
 
-            Verify the implementation meets ALL quality criteria before completing:
+            **AGENT: TAKE ACTION** - Verify the implementation meets ALL quality criteria before completing:
 
             1. **Directory Structure**: Is `.deepwork/jobs/[job_name]/` created correctly?
             2. **Complete Instructions**: Are ALL step instruction files complete (not stubs or placeholders)?
@@ -345,7 +345,7 @@ Ensure all outputs are:
 This step uses an iterative quality validation loop. After completing your work, stop hook(s) will evaluate whether the outputs meet quality criteria. If criteria are not met, you will be prompted to continue refining.
 
 ### Quality Criteria
-Verify the implementation meets ALL quality criteria before completing:
+**AGENT: TAKE ACTION** - Verify the implementation meets ALL quality criteria before completing:
 
 1. **Directory Structure**: Is `.deepwork/jobs/[job_name]/` created correctly?
 2. **Complete Instructions**: Are ALL step instruction files complete (not stubs or placeholders)?

.claude/commands/uw.update.job.md

@@ -9,7 +9,7 @@ hooks:
 
             ## Quality Criteria
 
-            Verify the update process completed successfully:
+            **AGENT: TAKE ACTION** - Verify the update process completed successfully:
             1. Changes were made in src/deepwork/standard_jobs/[job_name]/ (NOT in .deepwork/jobs/)
             2. `deepwork install --platform claude` was run
             3. Files in .deepwork/jobs/ match the source files
@@ -161,7 +161,7 @@ No specific files are output by this command.
 This step uses an iterative quality validation loop. After completing your work, stop hook(s) will evaluate whether the outputs meet quality criteria. If criteria are not met, you will be prompted to continue refining.
 
 ### Quality Criteria
-Verify the update process completed successfully:
+**AGENT: TAKE ACTION** - Verify the update process completed successfully:
 1. Changes were made in src/deepwork/standard_jobs/[job_name]/ (NOT in .deepwork/jobs/)
 2. `deepwork install --platform claude` was run
 3. Files in .deepwork/jobs/ match the source files

.deepwork.policy.yml

@@ -2,7 +2,7 @@
   trigger: "src/**/*"
   safety: "README.md"
   instructions: |
-    Source code in src/ has been modified. Please review README.md for accuracy:
+    **AGENT: TAKE ACTION** - Source code in src/ has been modified. Please review README.md for accuracy:
     1. Verify project overview still reflects current functionality
     2. Check that usage examples are still correct
     3. Ensure installation/setup instructions remain valid
@@ -12,7 +12,7 @@
   trigger: "src/**/*"
   safety: "doc/architecture.md"
   instructions: |
-    Source code in src/ has been modified. Please review doc/architecture.md for accuracy:
+    **AGENT: TAKE ACTION** - Source code in src/ has been modified. Please review doc/architecture.md for accuracy:
     1. Verify the documented architecture matches the current implementation
     2. Check that file paths and directory structures are still correct
     3. Ensure component descriptions reflect actual behavior
@@ -26,7 +26,7 @@
     - "src/deepwork/standard_jobs/deepwork_jobs/**/*"
     - "src/deepwork/standard_jobs/deepwork_policy/**/*"
   instructions: |
-    You modified files in `.deepwork/jobs/deepwork_jobs/` or `.deepwork/jobs/deepwork_policy/`.
+    **AGENT: TAKE ACTION** - You modified files in `.deepwork/jobs/deepwork_jobs/` or `.deepwork/jobs/deepwork_policy/`.
 
     **These are installed copies, NOT the source of truth!**
 
@@ -48,7 +48,7 @@
     - "pyproject.toml"
     - "CHANGELOG.md"
   instructions: |
-    Source code in src/ has been modified. **You MUST evaluate whether version and changelog updates are needed.**
+    **AGENT: TAKE ACTION** - Source code in src/ has been modified. **You MUST evaluate whether version and changelog updates are needed.**
 
     **Evaluate the changes:**
     1. Is this a bug fix, new feature, breaking change, or internal refactor?

.deepwork/jobs/add_platform/job.yml

@@ -39,7 +39,7 @@ steps:
     hooks:
       after_agent:
         - prompt: |
-            Verify the research output meets ALL criteria:
+            **AGENT: TAKE ACTION** - Verify the research output meets ALL criteria:
             1. Both files exist in doc/platforms/<platform>/: cli_configuration.md and hooks_system.md
             2. Each file has a comment at the top with:
                - Last updated date
@@ -66,7 +66,7 @@ steps:
     hooks:
       after_agent:
         - prompt: |
-            Verify the capability additions meet ALL criteria:
+            **AGENT: TAKE ACTION** - Verify the capability additions meet ALL criteria:
             1. Any new hooks from the platform (for slash commands only) are added to src/deepwork/schemas/job_schema.py
             2. All existing adapters in src/deepwork/adapters.py are updated with the new hook fields
                (set to None/null if the platform doesn't support that hook)
@@ -99,7 +99,7 @@ steps:
       after_agent:
         - script: hooks/run_tests.sh
         - prompt: |
-            Verify the implementation meets ALL criteria:
+            **AGENT: TAKE ACTION** - Verify the implementation meets ALL criteria:
             1. Platform adapter class is added to src/deepwork/adapters.py
             2. Templates exist in src/deepwork/templates/<platform>/ with appropriate command structure
             3. Tests exist for all new functionality
@@ -125,7 +125,7 @@ steps:
     hooks:
       after_agent:
         - prompt: |
-            Verify the installation meets ALL criteria:
+            **AGENT: TAKE ACTION** - Verify the installation meets ALL criteria:
             1. Platform-specific directories/files are added to the deepwork repo as needed
             2. Running `deepwork install --platform <platform>` completes without errors
             3. Expected command files are created in the platform's command directory