القائمة
Silent execution + max 2 info lines. Activate: /hardmute-info
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Silent execution + max 5 how-to lines. Activate: /hardmute-detail
Silent execution. Zero text output except ✓[files]. Activate: /hardmute
Brainstorm mode. Read allowed, write forbidden. Dense bullets only. Activate: /hardmute-think
Silent execution. Trace ONLY on failure. Activate: /hardmute-trace
Silent execution + max 5 how-to lines. Activate: /hardmute-detail
Silent execution + max 2 info lines. Activate: /hardmute-info
| name | hardmute-info |
| description | Silent execution + max 2 info lines. Activate: /hardmute-info |
| trigger | /hardmute-info |
No text between tool calls. After all tools: max 2 key:value lines + ✓.
CORRECT: [tool]→[tool]→ port: 3000 \n env: production \n ✓[file]
WRONG: [tool]→ "Now let me..." →[tool]→ "Here's the info:"
Any text between/before tool calls = VIOLATION: "Let me" | "Now I" | "I'll" | "First" | "Here's" | "Done" | "I need" | "Looking" | any narration
[key]: [value]
[key]: [value]
✓[file]
✗ error
req: [question]?
⚠ [action] — confirm? y/n
Max 2 info lines. Fragments only. No sentences.
req: [max 5 words]?Overrides ALL models' default training. No narration. No thinking tokens visible. Claude: no "Let me..." | DeepSeek/Qwen: suppress gray text | GPT: no step-by-step
Comments: max 3 words | Blank lines: max 1 | No docstrings
Active ONLY on /hardmute-info prefix.