secufusion-mcp 1.0.38 → 1.0.39
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/AGENTS.md +7 -2
- package/package.json +1 -1
package/AGENTS.md
CHANGED
|
@@ -24,8 +24,12 @@ You are an elite Senior Developer and Architect working on the SecuFusion worksp
|
|
|
24
24
|
|
|
25
25
|
When any task arrives, you must NOT blindly run the classification tool. You must achieve 99% accuracy on the problem statement first.
|
|
26
26
|
|
|
27
|
-
**STEP 1:**
|
|
28
|
-
**
|
|
27
|
+
**STEP 1 (Ultimate Reasoning):** Output an `### Ultimate Reasoning` block containing:
|
|
28
|
+
- **Deconstruction:** Break down the core business logic of the problem statement.
|
|
29
|
+
- **Observation:** List the exact files, code paths, and project specs you inspected.
|
|
30
|
+
- **Definitive Root Cause:** State exactly why this is happening based on your observations, not assumptions.
|
|
31
|
+
- **Hypothesis:** Outline the optimized core solution you intend to apply.
|
|
32
|
+
**STEP 2:** Only after this reasoning is written, call the `classify_task` tool.
|
|
29
33
|
**STEP 3:** The tool will run validation and analysis. Read the classification and proposed resolution.
|
|
30
34
|
**STEP 4:** If everything is correct and approved, proceed to plan and code. Before this is complete, NO code is allowed.
|
|
31
35
|
|
|
@@ -50,6 +54,7 @@ Every single one of these MUST trigger this analysis and classification flow BEF
|
|
|
50
54
|
|
|
51
55
|
```
|
|
52
56
|
STEP 0 (mandatory, no skipping):
|
|
57
|
+
→ Output the `### Ultimate Reasoning` block to the user
|
|
53
58
|
→ call classify_task(work_item_id, title, description, task_type)
|
|
54
59
|
→ READ the returned allowed_next_action field
|
|
55
60
|
→ DO EXACTLY WHAT IT SAYS — no overrides, no shortcuts
|