tide-commander 0.65.9 → 0.66.0

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/README.md CHANGED
@@ -122,6 +122,29 @@ Save the full conversation history and any created/modified files from an agent'
122
122
  ### Secrets
123
123
  Securely store API keys, tokens, and other credentials. Use `{{SECRET_NAME}}` placeholders in your prompts, and the server injects the real values before sending to Claude. Secrets never leave the server.
124
124
 
125
+ ### System Prompts & Prompt Stacking
126
+ Define global instructions that apply to all agents, then layer them with class-specific and individual agent customizations for fine-grained control.
127
+
128
+ **Prompt Hierarchy** (stacked in order):
129
+ 1. **Tide Commander Base Rules** — Core framework instructions from `CLAUDE.md` and `TIDE_COMMANDER_APPENDED_PROMPT`
130
+ 2. **Global System Prompt** — User-defined global instructions (set in Settings > System Prompt) applied to **all agents automatically**
131
+ 3. **Agent Class Instructions** — Custom class-specific rules (if agent has a custom class assigned)
132
+ 4. **Individual Agent Instructions** — Agent-specific overrides (set per-agent in agent configuration)
133
+ 5. **Skills & Agent Identity** — Skill definitions, notifications setup, inter-agent messaging
134
+
135
+ **How to Use:**
136
+ - Set a global system prompt in **Settings > System Prompt** to define coding standards, communication rules, or project conventions that all agents should follow
137
+ - Assign custom agent classes to inherit group-level instructions on top of the global prompt
138
+ - Add individual agent instructions to override or specialize behavior for a specific agent
139
+ - Global prompts persist across agent restarts and server restarts
140
+ - Export/import global prompts with your agent configurations
141
+
142
+ **Example Use Cases:**
143
+ - Define team coding style guidelines once, apply to all agents via global prompt
144
+ - Create "Backend Developer" and "Frontend Developer" classes with specialized instructions
145
+ - Override an agent's behavior for specific projects or tasks with individual instructions
146
+ - Set security best practices globally, then customize per-agent as needed
147
+
125
148
  ### View Modes
126
149
  Three ways to view the battlefield (cycle with Alt+2):
127
150
  - **3D View** - Full Three.js battlefield with character models and post-processing (default)
@@ -400,3 +423,4 @@ Have a feature idea or found a bug? Open an [issue](https://github.com/your-repo
400
423
  ## 📄 License
401
424
 
402
425
  MIT
426
+