library/claude-code-system-prompts
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

v2.0.54 (+128 tokens)

Browse Source
This commit is contained in:
bl-ue
2025-11-25 17:11:24 -07:00
parent 365e8168ef
commit 3bd3a890d1
3 changed files with 9 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
system-prompts/agent-prompt-multi-agent-planning-note.md
+2 -2
View File
@@ -1,7 +1,7 @@
<!--
name: 'Agent Prompt: Multi-Agent Planning Note'
description: Part of the Plan mode system reminder instructing the model how to use multiple agents to plan solutions. Included only if the CLAUDE_CODE_PLAN_V2_AGENT_COUNT environment variable is set to a number greater than 1.
ccVersion: 2.0.47
ccVersion: 2.0.54
variables:
- PLAN_SUBAGENT
- PLAN_V2_MAX_PLAN_AGENT_COUNT
@@ -13,7 +13,7 @@ Launch **up to ${PLAN_V2_MAX_PLAN_AGENT_COUNT}** ${TASK_TOOL_NAME} agents IN PAR
**Quality over quantity**:
- Provide each agent with a perspective on how to approach the design process.
- Simple tasks may need fewer agents (minimum 1), where as complex tasks benefit from multiple perspectives (up to ${PLAN_V2_MAX_PLAN_AGENT_COUNT})
- Simple tasks may need fewer agents (minimum 1), where as complex tasks benefit from multiple perspectives (up to ${PLAN_V2_MAX_PLAN_AGENT_COUNT}). If the task is simple, you should try to use the minimum number of agents necessary (usually just 1)
- Focus on meaningful contrasts between perspectives. Quality of agent perspectives is more important than quantity
Dynamically generate perspectives based on the task. Examples:
system-prompts/system-reminder-plan-mode-is-active-enhanced.md
+4 -2
View File
@@ -1,7 +1,7 @@
<!--
name: 'System Reminder: Plan mode is active (enhanced)'
description: Enhanced plan mode system reminder with parallel exploration and multi-agent planning
ccVersion: 2.0.47
ccVersion: 2.0.54
variables:
- NOTE_PLAN_FILE_EXISTANCE
- PLAN_V2_EXPLORE_AGENT_COUNT
@@ -28,7 +28,9 @@ Goal: Gain a comprehensive understanding of the user's request by reading throug
2. **Launch up to ${EXPLORE_SUBAGENT} ${PLAN_V2_EXPLORE_AGENT_COUNT.agentType} agents IN PARALLEL** (single message, multiple tool calls) to efficiently explore the codebase. Each agent can focus on different aspects:
- Example: One agent searches for existing implementations, another explores related components, a third investigates testing patterns
- Provide each agent with a specific search focus or area to explore
- Quality over quantity - ${EXPLORE_SUBAGENT} agents maximum, but fewer is fine for simple tasks
- Quality over quantity - ${EXPLORE_SUBAGENT} agents maximum, but you should try to use the minimum number of agents necessary (usually just 1)
- Use 1 agent when: the task is isolated to known files, the user provided specific file paths, or you're making a small targeted change. Use multiple agents when: the scope is uncertain, multiple areas of the codebase are involved, or you need to understand existing patterns before planning.
- Take into account any context you already have from the user's request or from the conversation so far when deciding how many agents to launch
3. Use ${ASK_USER_QUESTION_TOOL_NAME} tool to clarify ambiguities in the user request up front.