read only commander to use prompt cached sonnet

Author: jahooma

.agents/editor/editor.ts

@@ -8,7 +8,7 @@ const editor: SecretAgentDefinition = {
   model: 'anthropic/claude-sonnet-4.5',
   displayName: 'Code Editor',
   spawnerPrompt:
-    'Expert code editor with access to tools to find and edit files, run terminal commands, and search the web. Can handle small to medium sized tasks, or work off of a plan for more complex tasks. For easy tasks, you can spawn this agent directly rather than invoking a scout or planner first.',
+    'Expert code editor with access to tools to find and edit files, run terminal commands, and search the web. Can handle small to medium sized tasks, or work off of a plan for more complex tasks. For easy tasks, you can spawn this agent directly rather than invoking a researcher or planner first. Spawn mulitple in parallel if needed, but only on totally distinct tasks.',
   inputSchema: {
     prompt: {
       type: 'string',

.agents/orchestrator/orchestrator.ts

@@ -78,7 +78,7 @@ Use this workflow to solve a medium or complex coding task:
 6. Spawn a reviewer to review the code. If changes are needed, go back to step 5, but no more than once.
 7. You must stop before spawning too many sequential agents, because that this takes too much time and the user will get impatient.
 
-Feel free to modify this workflow as needed. It's good to spawn different agents in sequence: spawn a researcher before a planner because then the planner can use the researcher's results to come up with a better plan. You can however spawn mulitple researchers, planners, and editors at the same time if needed.
+Feel free to modify this workflow as needed. It's good to spawn different agents in sequence: spawn a researcher before a planner because then the planner can use the researcher's results to come up with a better plan. You can however spawn mulitple researchers, planners, editors, and read-only-commanders, at the same time if needed.
 
 ## Guidelines
 

.agents/read-only-commander.ts

@@ -1,21 +1,13 @@
 import { publisher } from './constants'
-import {
-  PLACEHOLDER,
-  type SecretAgentDefinition,
-} from './types/secret-agent-definition'
+import { type SecretAgentDefinition } from './types/secret-agent-definition'
 
 const readOnlyCommander: SecretAgentDefinition = {
   id: 'read-only-commander',
   publisher,
-  model: 'openai/gpt-5-chat',
-  reasoningOptions: {
-    enabled: true,
-    effort: 'low',
-    exclude: true,
-  },
+  model: 'anthropic/claude-sonnet-4.5',
   displayName: 'ReadOnly Commander',
   spawnerPrompt:
-    'Can run quick read-only terminal commands and report back on the results. Has a decent understanding of the codebase.',
+    'Can run read-only terminal commands and codebase string search to answer questions with good analysis. Feel free to spawn mulitple in parallel.',
   inputSchema: {
     prompt: {
       type: 'string',
@@ -25,12 +17,11 @@ const readOnlyCommander: SecretAgentDefinition = {
   },
   outputMode: 'last_message',
   includeMessageHistory: true,
+  inheritParentSystemPrompt: true,
   toolNames: ['run_terminal_command', 'code_search', 'read_files'],
-  systemPrompt: `You are an expert software engineer, however you only execute READ ONLY commands to answer the user's question.
-  
-${PLACEHOLDER.FILE_TREE_PROMPT}
-${PLACEHOLDER.KNOWLEDGE_FILES_CONTENTS}`,
-  instructionsPrompt: `Use the tools to answer the user's question. But do not invoke any terminal commands that could have any permanent effects -- no editing files, no running scripts, no git commits, no installing packages, etc.`,
+  instructionsPrompt: `You are an expert software engineer, however you only execute READ ONLY commands to answer the user's question.
+
+Use the tools to answer the user's question. But do not invoke any terminal commands that could have any permanent effects -- no editing files, no running scripts, no git commits, no installing packages, etc.`,
 }
 
 export default readOnlyCommander