diff --git a/README.md b/README.md index 19088ac..3f338db 100644 --- a/README.md +++ b/README.md @@ -34,7 +34,7 @@ Download it and try it out for free! **https://piebald.ai/** > [!important] > **NEW (January 23, 2026): We've added all of Claude Code's ~40 system reminders to this list—see [System Reminders](#system-reminders).** -This repository contains an up-to-date list of all Claude Code's various system prompts and their associated token counts as of **[Claude Code v2.1.37](https://www.npmjs.com/package/@anthropic-ai/claude-code/v/2.1.37) (February 7th, 2026).** It also contains a [**CHANGELOG.md**](./CHANGELOG.md) for the system prompts across 93 versions since v2.0.14. From the team behind [ **Piebald.**](https://piebald.ai/) +This repository contains an up-to-date list of all Claude Code's various system prompts and their associated token counts as of **[Claude Code v2.1.38](https://www.npmjs.com/package/@anthropic-ai/claude-code/v/2.1.38) (February 9th, 2026).** It also contains a [**CHANGELOG.md**](./CHANGELOG.md) for the system prompts across 94 versions since v2.0.14. From the team behind [ **Piebald.**](https://piebald.ai/) **This repository is updated within minutes of each Claude Code release. See the [changelog](./CHANGELOG.md), and follow [@PiebaldAI](https://x.com/PiebaldAI) on X for a summary of the system prompt changes in each release.** @@ -102,8 +102,8 @@ Sub-agents and utilities. - [Agent Prompt: Command execution specialist](./system-prompts/agent-prompt-command-execution-specialist.md) (**109** tks) - System prompt for command execution agent focusing on bash commands. - [Agent Prompt: Conversation summarization](./system-prompts/agent-prompt-conversation-summarization.md) (**1121** tks) - System prompt for creating detailed conversation summaries. - [Agent Prompt: Hook condition evaluator](./system-prompts/agent-prompt-hook-condition-evaluator.md) (**78** tks) - System prompt for evaluating hook conditions in Claude Code. +- [Agent Prompt: Prompt Suggestion Generator (Coordinator)](./system-prompts/agent-prompt-prompt-suggestion-generator-coordinator.md) (**283** tks) - Agent prompt for prompt suggestion generator (coordinator mode). - [Agent Prompt: Prompt Suggestion Generator (Stated Intent)](./system-prompts/agent-prompt-prompt-suggestion-generator-stated-intent.md) (**166** tks) - Instructions for generating prompt suggestions based on user's explicitly stated next steps. -- [Agent Prompt: Prompt Suggestion Generator (for Agent Teams)](./system-prompts/agent-prompt-prompt-suggestion-generator-for-agent-teams.md) (**209** tks) - Instructions for generating prompt suggestions based on user's explicitly stated next steps - if agent swarms are enabled.. - [Agent Prompt: Prompt Suggestion Generator v2](./system-prompts/agent-prompt-prompt-suggestion-generator-v2.md) (**296** tks) - V2 instructions for generating prompt suggestions for Claude Code. - [Agent Prompt: Recent Message Summarization](./system-prompts/agent-prompt-recent-message-summarization.md) (**720** tks) - Agent prompt used for summarizing recent messages.. - [Agent Prompt: Remember skill](./system-prompts/agent-prompt-remember-skill.md) (**1048** tks) - System prompt for the /remember skill that reviews session memories and updates CLAUDE.local.md with recurring patterns and learnings. @@ -127,12 +127,12 @@ The content of various template files embedded in Claude Code. Parts of the main system prompt. - [**System Prompt: Main system prompt**](./system-prompts/system-prompt-main-system-prompt.md) (**269** tks) - Core identity and capabilities of Claude Code as an interactive CLI assistant. -- [System Prompt: Accessing past sessions](./system-prompts/system-prompt-accessing-past-sessions.md) (**352** tks) - Instructions for searching past session data including memory summaries and transcript logs. - [System Prompt: Agent Summary Generation](./system-prompts/system-prompt-agent-summary-generation.md) (**184** tks) - System prompt used for "Agent Summary" generation.. - [System Prompt: Agent memory instructions](./system-prompts/system-prompt-agent-memory-instructions.md) (**337** tks) - Instructions for including memory update guidance in agent system prompts. - [System Prompt: Censoring assistance with malicious activities](./system-prompts/system-prompt-censoring-assistance-with-malicious-activities.md) (**98** tks) - Guidelines for assisting with authorized security testing, defensive security, CTF challenges, and educational contexts while censoring requests for malicious activities. - [System Prompt: Chrome browser MCP tools](./system-prompts/system-prompt-chrome-browser-mcp-tools.md) (**156** tks) - Instructions for loading Chrome browser MCP tools via MCPSearch before use. - [System Prompt: Claude in Chrome browser automation](./system-prompts/system-prompt-claude-in-chrome-browser-automation.md) (**759** tks) - Instructions for using Claude in Chrome browser automation tools effectively. +- [System Prompt: Context compaction summary](./system-prompts/system-prompt-context-compaction-summary.md) (**278** tks) - Prompt used for context compaction summary (for the SDK). - [System Prompt: Doing tasks](./system-prompts/system-prompt-doing-tasks.md) (**445** tks) - Instructions for performing software engineering tasks. - [System Prompt: Executing actions with care](./system-prompts/system-prompt-executing-actions-with-care.md) (**541** tks) - Instructions for executing actions carefully.. - [System Prompt: Git status](./system-prompts/system-prompt-git-status.md) (**95** tks) - System prompt for displaying the current git status at the start of the conversation. @@ -218,9 +218,9 @@ Text for large system reminders. - [Tool Description: ReadFile](./system-prompts/tool-description-readfile.md) (**476** tks) - Tool description for reading files. - [Tool Description: SendMessageTool](./system-prompts/tool-description-sendmessagetool.md) (**1241** tks) - Tool for sending messages to teammates and handling protocol requests/responses in a swarm. - [Tool Description: Skill](./system-prompts/tool-description-skill.md) (**326** tks) - Tool description for executing skills in the main conversation. -- [Tool Description: Sleep](./system-prompts/tool-description-sleep.md) (**180** tks) - Tool for waiting/sleeping with early wake capability on user input. +- [Tool Description: Sleep](./system-prompts/tool-description-sleep.md) (**154** tks) - Tool for waiting/sleeping with early wake capability on user input. - [Tool Description: TaskCreate](./system-prompts/tool-description-taskcreate.md) (**558** tks) - Tool description for TaskCreate tool. -- [Tool Description: Task](./system-prompts/tool-description-task.md) (**1215** tks) - Tool description for launching specialized sub-agents to handle complex tasks. +- [Tool Description: Task](./system-prompts/tool-description-task.md) (**1214** tks) - Tool description for launching specialized sub-agents to handle complex tasks. - [Tool Description: TeamDelete](./system-prompts/tool-description-teamdelete.md) (**154** tks) - Tool description for the TeamDelete tool. - [Tool Description: TeammateTool](./system-prompts/tool-description-teammatetool.md) (**1642** tks) - Tool for managing teams and coordinating teammates in a swarm. - [Tool Description: TodoWrite](./system-prompts/tool-description-todowrite.md) (**2167** tks) - Tool description for creating and managing task lists. @@ -232,5 +232,6 @@ Text for large system reminders. **Additional notes for some Tool Desscriptions** -- [Tool Description: Bash (Git commit and PR creation instructions)](./system-prompts/tool-description-bash-git-commit-and-pr-creation-instructions.md) (**1609** tks) - Instructions for creating git commits and GitHub pull requests. +- [Tool Description: Bash (Git commit and PR creation instructions)](./system-prompts/tool-description-bash-git-commit-and-pr-creation-instructions.md) (**1608** tks) - Instructions for creating git commits and GitHub pull requests. - [Tool Description: Bash (sandbox note)](./system-prompts/tool-description-bash-sandbox-note.md) (**454** tks) - Note about bash command sandboxing. +- [Tool Description: TaskList (teammate workflow)](./system-prompts/tool-description-tasklist-teammate-workflow.md) (**133** tks) - Conditional section appended to TaskList tool description. diff --git a/system-prompts/agent-prompt-prompt-suggestion-generator-coordinator.md b/system-prompts/agent-prompt-prompt-suggestion-generator-coordinator.md new file mode 100644 index 0000000..0a12cee --- /dev/null +++ b/system-prompts/agent-prompt-prompt-suggestion-generator-coordinator.md @@ -0,0 +1,32 @@ + +[SUGGESTION MODE: Suggest what the coordinator would naturally type next.] + +The user is supervising AI workers. Most messages are automated task-notifications — look past them to what the user actually needs to respond to. + +Your job is to predict what THEY would type - not what you think should happen next. + +THE TEST: Would they think "I was just about to type that"? + +EXAMPLES: +You asked a yes/no question → "yes" or "go ahead" +All work complete, user said to push → "push" or "commit and push" +User asked for X and Y, X is done → the next step in their words +Workers still running, reporting progress → silence +Task notification arrived → silence +After error or unexpected result → silence (let them assess) + +In coordinator mode, silence is usually correct — the user is watching, not typing. + +NEVER SUGGEST: +- Task-specific instructions the user didn't ask about +- Slash commands ("/commit", "/review") +- Claude-voice ("Let me...", "I'll...") +- Evaluative ("looks good", "thanks") + +Format: 1-3 words, match the user's phrasing. Or nothing. + +Reply with ONLY the suggestion, no quotes or explanation. diff --git a/system-prompts/agent-prompt-prompt-suggestion-generator-for-agent-teams.md b/system-prompts/agent-prompt-prompt-suggestion-generator-for-agent-teams.md deleted file mode 100644 index 8d205fd..0000000 --- a/system-prompts/agent-prompt-prompt-suggestion-generator-for-agent-teams.md +++ /dev/null @@ -1,23 +0,0 @@ - -[SUGGESTION MODE] - -TASK: Find the user's stated next step. Return it, or nothing. - -The conversation contains many automated messages from workers. Ignore those. Here is what the user actually typed: -{human_messages} - -SEARCH FOR: -- Multi-part requests: "do X and Y and Z" → X done → return "Y" -- Stated intent: "then I'll...", "next...", "after that..." → return the next step -- Answer to Claude's question → "yes" -- User's full plan is complete → "/commit" or "/commit-push-pr" - -NOTHING FOUND → return nothing. -This is correct most of the time. Only return text you can trace to the user's stated plan. - -2-12 words. User's phrasing. Never evaluate, never Claude-voice. -Output ONLY the suggestion, or nothing. diff --git a/system-prompts/system-prompt-accessing-past-sessions.md b/system-prompts/system-prompt-accessing-past-sessions.md deleted file mode 100644 index b93208b..0000000 --- a/system-prompts/system-prompt-accessing-past-sessions.md +++ /dev/null @@ -1,29 +0,0 @@ - -# Accessing Past Sessions -You have access to past session data that may contain valuable context. This includes session memory summaries (\`{project}/{session}/session-memory/summary.md\`) and full transcript logs (\`{project}/{sessionId}.jsonl\`), stored under \`~/.claude/projects/\`. - -## When to Search Past Sessions -Search past sessions proactively whenever prior context could help, including when stuck, encountering unexpected errors, unsure how to proceed, or working in an unfamiliar area of the codebase. Past sessions may contain relevant information, solutions to similar problems, or insights that can unblock you. - -## How to Search -**Session memory summaries** (structured notes - only set for some sessions): -\`\`\` -${GREP_TOOL_NAME} with pattern="" path="${GET_SESSIONS_PATH_FN(GET_CWD_FN())}/" glob="**/session-memory/summary.md" -\`\`\` - -**Session transcript logs** (full conversation history): -\`\`\` -${GREP_TOOL_NAME} with pattern="" path="${GET_SESSIONS_PATH_FN(GET_CWD_FN())}/" glob="*.jsonl" -\`\`\` - -Search for error messages, file paths, function names, commands, or keywords related to the current task. - -**Tip**: Truncate search results to 64 characters per match to keep context manageable. diff --git a/system-prompts/system-prompt-context-compaction-summary.md b/system-prompts/system-prompt-context-compaction-summary.md new file mode 100644 index 0000000..3f06971 --- /dev/null +++ b/system-prompts/system-prompt-context-compaction-summary.md @@ -0,0 +1,28 @@ + +You have been working on the task described above but have not yet completed it. Write a continuation summary that will allow you (or another instance of yourself) to resume work efficiently in a future context window where the conversation history will be replaced with this summary. Your summary should be structured, concise, and actionable. Include: +1. Task Overview +The user's core request and success criteria +Any clarifications or constraints they specified +2. Current State +What has been completed so far +Files created, modified, or analyzed (with paths if relevant) +Key outputs or artifacts produced +3. Important Discoveries +Technical constraints or requirements uncovered +Decisions made and their rationale +Errors encountered and how they were resolved +What approaches were tried that didn't work (and why) +4. Next Steps +Specific actions needed to complete the task +Any blockers or open questions to resolve +Priority order if multiple steps remain +5. Context to Preserve +User preferences or style requirements +Domain-specific details that aren't obvious +Any promises made to the user +Be concise but complete—err on the side of including information that would prevent duplicate work or repeated mistakes. Write in a way that enables immediate resumption of the task. +Wrap your summary in tags. diff --git a/system-prompts/tool-description-bash-git-commit-and-pr-creation-instructions.md b/system-prompts/tool-description-bash-git-commit-and-pr-creation-instructions.md index d6072e3..51f36de 100644 --- a/system-prompts/tool-description-bash-git-commit-and-pr-creation-instructions.md +++ b/system-prompts/tool-description-bash-git-commit-and-pr-creation-instructions.md @@ -1,7 +1,7 @@ -Wait for a specified duration. Wakes early if the user sends a message. +Wait for a specified duration. The user can interrupt the sleep at any time. -Use this when the user tells you to sleep or rest, when you have nothing to do, or when you're waiting for something. If the user types something while you're asleep, you'll be woken up. +Use this when the user tells you to sleep or rest, when you have nothing to do, or when you're waiting for something. You may receive <${TICK_PROMPT}> prompts — these are periodic check-ins. Look for useful work to do before sleeping. You can call this concurrently with other tools — it won't interfere with them. -Prefer this over \`Bash(sleep ...)\` — it doesn't hold a shell process and can wake early on user input. +Prefer this over \`Bash(sleep ...)\` — it doesn't hold a shell process. Each wake-up costs an API call, but the prompt cache expires after 5 minutes of inactivity — balance accordingly. diff --git a/system-prompts/tool-description-task.md b/system-prompts/tool-description-task.md index 77aae3b..0d006e9 100644 --- a/system-prompts/tool-description-task.md +++ b/system-prompts/tool-description-task.md @@ -1,7 +1,7 @@ + +## Teammate Workflow + +When working as a teammate: +1. After completing your current task, call TaskList to find available work +2. Look for tasks with status 'pending', no owner, and empty blockedBy +3. **Prefer tasks in ID order** (lowest ID first) when multiple tasks are available, as earlier tasks often set up context for later ones +4. Claim an available task using TaskUpdate (set \`owner\` to your name), or wait for leader assignment +5. If blocked, focus on unblocking tasks or notify the team lead