claude-prism 0.3.2 → 0.4.1

package/templates/settings.json

@@ -6,40 +6,31 @@
         "hooks": [
           {
             "type": "command",
-            "command": "node .claude/hooks/commit-guard.mjs",
-            "timeout": 5
+            "command": "node .claude/hooks/pre-tool.mjs",
+            "timeout": 5000
           }
         ]
       }
     ],
     "PostToolUse": [
       {
-        "matcher": "Edit|Write",
+        "matcher": "Edit|Write|Bash",
         "hooks": [
           {
             "type": "command",
-            "command": "node .claude/hooks/debug-loop.mjs",
-            "timeout": 5
+            "command": "node .claude/hooks/post-tool.mjs",
+            "timeout": 5000
           }
         ]
-      },
-      {
-        "matcher": "Edit|Write",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node .claude/hooks/scope-guard.mjs",
-            "timeout": 5
-          }
-        ]
-      },
+      }
+    ],
+    "UserPromptSubmit": [
       {
-        "matcher": "Bash",
         "hooks": [
           {
             "type": "command",
-            "command": "node .claude/hooks/test-tracker.mjs",
-            "timeout": 5
+            "command": "node .claude/hooks/user-prompt.mjs",
+            "timeout": 5000
           }
         ]
       }

package/templates/skills/prism/SKILL.md

@@ -71,8 +71,15 @@ AI agents optimize for speed, not correctness. Without structure, they skip unde
    - Independent verification: each unit has a pass criterion
    - Files specified: list files to create/modify per unit
    - Dependencies noted: mark if unit depends on a previous one
-9. **Save plan** to `docs/plans/YYYY-MM-DD-<topic>.md`
-10. **Get approval**: "Proceed with this plan?"
+9. **Assign size tags** to every task: [S] <30 LOC, [M] 30-100 LOC, [L] >100 LOC
+   - Batch composition: S+S+M = 1 batch, L = 1 batch alone
+10. **Assign verification strategy** per task: `| Verify: TDD` or `| Verify: Build` or `| Verify: Visual`
+11. **Pre-decomposition checklist**:
+    - Required types/interfaces have the necessary fields?
+    - External package APIs behave as expected?
+    - Cross-package dependencies identified and noted as prerequisites?
+12. **Save plan** to `docs/plans/YYYY-MM-DD-<topic>.md`
+13. **Get approval**: "Proceed with this plan?"
 
 ## E — EXECUTE
 
@@ -99,15 +106,21 @@ AI agents optimize for speed, not correctness. Without structure, they skip unde
 
 ## C — CHECKPOINT
 
-17. After each batch, report using this format:
+20. After each batch, report using this format:
 
     | Item | Before | After |
     |------|--------|-------|
     | [what changed] | [old behavior] | [new behavior] |
 
-18. Include: verification results, files modified, tests status
-19. Ask: "Continue to next batch?"
-20. User can redirect, adjust scope, or stop at any checkpoint
+    ```
+    Phase: [current] | Batch: [N/M] | Tasks: [done/total] ([%])
+    [████████░░] 80% — Next: [next batch name]
+    ```
+
+21. Include: verification results, files modified, tests status
+22. **Checkpoint policy**: after 3 consecutive approvals, increase batch size to 5-8 for the rest of the phase
+23. Ask: "Continue to next batch?"
+24. User can redirect, adjust scope, or stop at any checkpoint
 
 ## OMC Integration