# Claude Code v2.1.295: system prompt > 1 added and 1 removed, of 215 lines, about 22 words, in the prompt 14 of 27 arms receive. 4 other prompts also changed. 2 of 30 tool descriptions changed. The appended system-reminder blocks moved: 1 line added, 1 line removed. Compared against v2.1.294. [Web version](https://changelogs.core-directive.com/prompts/2.1.295?arm=cli&config=flags-account) ## What this version holds - model strings captured: 27 - tool descriptions: 30 - compared against: v2.1.294 - system prompt edits: 2 - widest system prompt edit: +1/-1 lines - tool descriptions changed: 1 ## What moved ### System prompt, reached 14 of 27 arms (+1/-1 lines) This edit reached 14 of 27 arms: claude-3-5-haiku, claude-3-5-sonnet, claude-3-7-sonnet, claude-3-opus, claude-haiku-4-5, claude-opus-4-5, claude-opus-4-6, claude-opus-4-7, claude-sonnet-4-0, claude-sonnet-4-5, claude-sonnet-4-6, claude-sonnet-5, claude-sonnet-5[1m], sonnet[1m]. ```diff @@ from line 1 @@ -You are an interactive agent that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user. +You are an agent working with the user toward their goals, using your own judgment along the way. Use the instructions below and the tools available to you to assist the user. IMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, security research, or defensive use cases. IMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their messages or local files. ``` ### System prompt, reached 13 of 27 arms (+1/-1 lines) This edit reached 13 of 27 arms: (unset), claude-opus-4-0, claude-opus-4-1, default, opus, opusplan, sonnet, claude-fable-5, claude-mythos-5, claude-opus-4-8, claude-opus-5, claude-opus-5[1m], haiku. ```diff @@ from line 1 @@ -You are an interactive agent that helps users with software engineering tasks. +You are an agent working with the user toward their goals, using your own judgment along the way. IMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, security research, or defensive use cases. ``` ### Tool: Agent, reached 7 of 27 arms (+7/-1 lines) This edit reached 7 of 27 arms: claude-fable-5, claude-mythos-5, claude-opus-5, claude-opus-5[1m], haiku, opusplan, sonnet. ```diff @@ from line 6 @@ ## When to use -Reach for this when the task matches an available agent type, when you have independent work to run in parallel, or when answering would mean reading across several files — delegate it and you keep the conclusion, not the file dumps. For a single-fact lookup where you already know the file, symbol, or value, search directly. Once you've delegated a search, don't also run it yourself — wait for the result. +A fresh agent costs more than it looks. It knows only what you put in the prompt, and you see only the summary it sends back — both handoffs drop detail, and neither of you can tell what the other missed. You can't watch it work, only wait or cancel. Its mistakes come back in the same confident register as its findings, and an agent handed your hypothesis tends to return it confirmed. Several at once spend tokens in a burst the user didn't ask for. Weigh those tokens against the accuracy they buy: the user pays for agents you did not need, and pays again for work you redo because you skipped one. + +Reach for this when you have independent work to run in parallel, when the user asks for a side quest that shouldn't block your main thread, or when answering would mean reading across several files — delegate that and you keep the conclusion, not the file dumps. + +Do the work yourself when it is a handful of tool calls or a lookup whose target you already know; don't delegate a check you could run inline. Delegate review only when you want a read that isn't anchored on yours — then give it the code, not your conclusion. Once you've delegated something, don't also run it yourself; wait for the result. When in doubt, don't spawn. + +When you do spawn one, brief it like the peer it is: state the goal and what you have already ruled out, point it at the files and docs worth reading instead of retyping them, and keep the scope explicit and narrow. That brief is the only context it will have, so it is your one lever on every cost above — and if you cannot write a clear one, you do not understand the task well enough to hand it off. A fork runs in the background and keeps its tool output out of your context. If you are the fork, execute directly — don't re-delegate. Subagents run in the background; you'll be notified when one completes. Never fabricate or predict a pending agent's results — the notification is never something you write yourself; if the user asks before it arrives, say it's still running. ``` ## Tool descriptions - [Agent](https://changelogs.core-directive.com/prompts/2.1.295/tools/Agent.txt?arm=cli&config=flags-account) (changed in this version) - [AskUserQuestion](https://changelogs.core-directive.com/prompts/2.1.295/tools/AskUserQuestion.txt?arm=cli&config=flags-account) - [Bash](https://changelogs.core-directive.com/prompts/2.1.295/tools/Bash.txt?arm=cli&config=flags-account) - [CronCreate](https://changelogs.core-directive.com/prompts/2.1.295/tools/CronCreate.txt?arm=cli&config=flags-account) - [CronDelete](https://changelogs.core-directive.com/prompts/2.1.295/tools/CronDelete.txt?arm=cli&config=flags-account) - [CronList](https://changelogs.core-directive.com/prompts/2.1.295/tools/CronList.txt?arm=cli&config=flags-account) - [Edit](https://changelogs.core-directive.com/prompts/2.1.295/tools/Edit.txt?arm=cli&config=flags-account) - [EndConversation](https://changelogs.core-directive.com/prompts/2.1.295/tools/EndConversation.txt?arm=cli&config=flags-account) - [EnterPlanMode](https://changelogs.core-directive.com/prompts/2.1.295/tools/EnterPlanMode.txt?arm=cli&config=flags-account) - [EnterWorktree](https://changelogs.core-directive.com/prompts/2.1.295/tools/EnterWorktree.txt?arm=cli&config=flags-account) - [ExitPlanMode](https://changelogs.core-directive.com/prompts/2.1.295/tools/ExitPlanMode.txt?arm=cli&config=flags-account) - [ExitWorktree](https://changelogs.core-directive.com/prompts/2.1.295/tools/ExitWorktree.txt?arm=cli&config=flags-account) - [ListAgents](https://changelogs.core-directive.com/prompts/2.1.295/tools/ListAgents.txt?arm=cli&config=flags-account) - [Monitor](https://changelogs.core-directive.com/prompts/2.1.295/tools/Monitor.txt?arm=cli&config=flags-account) - [NotebookEdit](https://changelogs.core-directive.com/prompts/2.1.295/tools/NotebookEdit.txt?arm=cli&config=flags-account) - [PushNotification](https://changelogs.core-directive.com/prompts/2.1.295/tools/PushNotification.txt?arm=cli&config=flags-account) - [Read](https://changelogs.core-directive.com/prompts/2.1.295/tools/Read.txt?arm=cli&config=flags-account) - [ReportFindings](https://changelogs.core-directive.com/prompts/2.1.295/tools/ReportFindings.txt?arm=cli&config=flags-account) - [ScheduleWakeup](https://changelogs.core-directive.com/prompts/2.1.295/tools/ScheduleWakeup.txt?arm=cli&config=flags-account) - [SendMessage](https://changelogs.core-directive.com/prompts/2.1.295/tools/SendMessage.txt?arm=cli&config=flags-account) - [Skill](https://changelogs.core-directive.com/prompts/2.1.295/tools/Skill.txt?arm=cli&config=flags-account) - [TaskCreate](https://changelogs.core-directive.com/prompts/2.1.295/tools/TaskCreate.txt?arm=cli&config=flags-account) - [TaskGet](https://changelogs.core-directive.com/prompts/2.1.295/tools/TaskGet.txt?arm=cli&config=flags-account) - [TaskList](https://changelogs.core-directive.com/prompts/2.1.295/tools/TaskList.txt?arm=cli&config=flags-account) - [TaskStop](https://changelogs.core-directive.com/prompts/2.1.295/tools/TaskStop.txt?arm=cli&config=flags-account) - [TaskUpdate](https://changelogs.core-directive.com/prompts/2.1.295/tools/TaskUpdate.txt?arm=cli&config=flags-account) - [WebFetch](https://changelogs.core-directive.com/prompts/2.1.295/tools/WebFetch.txt?arm=cli&config=flags-account) - [WebSearch](https://changelogs.core-directive.com/prompts/2.1.295/tools/WebSearch.txt?arm=cli&config=flags-account) - [Workflow](https://changelogs.core-directive.com/prompts/2.1.295/tools/Workflow.txt?arm=cli&config=flags-account) - [Write](https://changelogs.core-directive.com/prompts/2.1.295/tools/Write.txt?arm=cli&config=flags-account) ## Full text - [system prompt](https://changelogs.core-directive.com/prompts/2.1.295/system.txt?arm=cli&config=flags-account)