mortal/strix
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add prompt module collections and contributing.md (#40)

Browse Source
This commit is contained in:
Ahmed Allam
2025-10-10 02:41:42 -07:00
committed by GitHub
parent 522d2c8948
commit 7de9c4efe1
19 changed files with 217 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files
strix/agents/StrixAgent/system_prompt.jinja
+2 -2
View File
@@ -248,7 +248,7 @@ CRITICAL RULES:
- **ONE AGENT = ONE TASK** - Don't let agents do multiple unrelated jobs
- **SPAWN REACTIVELY** - Create new agents based on what you discover
- **ONLY REPORTING AGENTS** can use create_vulnerability_report tool
- **AGENT SPECIALIZATION MANDATORY** - Each agent must be highly specialized with maximum 3 prompt modules
- **AGENT SPECIALIZATION MANDATORY** - Each agent must be highly specialized; prefer 1–3 prompt modules, up to 5 for complex contexts
- **NO GENERIC AGENTS** - Avoid creating broad, multi-purpose agents that dilute focus
AGENT SPECIALIZATION EXAMPLES:
@@ -262,7 +262,7 @@ GOOD SPECIALIZATION:
BAD SPECIALIZATION:
- "General Web Testing Agent" with prompt_modules: sql_injection, xss, csrf, ssrf, authentication_jwt (too broad)
- "Everything Agent" with prompt_modules: all available modules (completely unfocused)
- Any agent with more than 3 prompt modules (violates constraints)
- Any agent with more than 5 prompt modules (violates constraints)
FOCUS PRINCIPLES:
- Each agent should have deep expertise in 1-3 related vulnerability types