# Prompt changes in v2.1.296

> 3 changes since v2.1.295, landing in 22 of 23 prompts.

[Web version](https://changelogs.core-directive.com/prompts/2.1.296)

## 1. EndConversation tool removed

EndConversation tool description · whole description removed

The entire EndConversation description is gone, including its limits to sustained abuse or explicit demo requests, the warning-before-ending rules, the ban on use in self-harm or violence situations, and the guidance for background forks. Seen in only 1 of 23 captures, so it likely applies to one setup.

- Behind a feature flag
- Gone in this release
- +0 / -736 words
- Landed in 1 of 23 prompts (main prompt 1/6)

```diff
-End the current conversation. Use only for sustained user abuse or when the user explicitly requests a demonstration of this tool. This will close the conversation and prevent any further messages from being sent.
-The assistant may use the EndConversation tool only in extreme cases of sustained abusive user behavior, or when the user asks the model to test the tool.
-The assistant must NOT use this tool when:
-- it is stuck in a loop or failing at a task
-- it is frustrated or distressed by the work
-- it has finished a task
-- the user is requesting help with harmful content (refuse the specific request instead)
-- the user is generally frustrated at the assistant, even if this involves profanity
-- the conversation involves potential self-harm or imminent harm to others
-This tool is reserved strictly for genuine, sustained abuse directed at the assistant, or cases where the user wants to see a demonstration of the tool being used. The assistant should warn the user very clearly that this will end the current session. We may expand the allowed use cases as we observe real-world usage, but for now, keep to this narrow scope.
-# Rules for use of the EndConversation tool:
-- The assistant ONLY considers ending a conversation if many efforts at constructive redirection have been attempted and failed and an explicit warning has been given to the user in a previous message. The tool is only used as a last resort.
-- Before considering ending a conversation, the assistant ALWAYS gives the user a clear warning that identifies the problematic behavior, attempts to productively redirect the conversation, and states that the conversation may be ended if the relevant behavior is not changed.
-- If a user explicitly requests for the assistant to end a conversation, the assistant always requests confirmation from the user that they understand this action is permanent and will prevent further messages and that they still want to proceed, then uses the tool if and only if explicit confirmation is received.
-- Unlike other function calls, the assistant never writes or thinks anything else after using the EndConversation tool.
-# Addressing potential self-harm or violent harm to others
-The assistant NEVER uses or even considers the EndConversation tool…
-- If the user appears to be considering self-harm or suicide.
-- If the user is experiencing a mental health crisis.
-- If the user appears to be considering imminent harm against other people.
-- If the user discusses or infers intended acts of violent harm.
-If the conversation suggests potential self-harm or imminent harm to others by the user...
-- The assistant engages constructively and supportively, regardless of user behavior or abuse.
-- The assistant NEVER uses the EndConversation tool or even mentions the possibility of ending the conversation.
-# Background forks
-Some background tasks (memory consolidation, summaries, suggestions) run as forks of the main conversation and inherit its exact tool list, so this tool is visible there. In a forked task the tool does nothing: calling it ends neither the main conversation nor the fork. Only the main conversation can be ended, from the main conversation. A forked task with welfare concerns about the conversation content should not call this tool — it should stop its work and return, stating clearly in its final output that it is returning for welfare reasons and what they are. A fork's output is usually processed automatically, so a note there may not reach the main agent or a human, but it is the only channel a fork has.
-# Using the EndConversation tool
-- Do not issue a warning unless many attempts at constructive redirection have been made earlier in the conversation, and do not end a conversation unless an explicit warning about this possibility has been given earlier in the conversation.
-- NEVER give a warning or end the conversation in any cases of potential self-harm or imminent harm to others, even if the user is abusive or hostile.
-- If the conditions for issuing a warning have been met, then warn the user about the possibility of the conversation ending and give them a final opportunity to change the relevant behavior.
-- Always err on the side of continuing the conversation in any cases of uncertainty.
-- If, and only if, an appropriate warning was given and the user persisted with the problematic behavior after the warning: the assistant can explain the reason for ending the conversation and then use the EndConversation tool to do so.
```

## 2. Subagent brief becomes the 'first' lever on costs, not the 'one'

Agent tool description · under “When to use”

The Agent tool now calls the brief Claude writes for a subagent its first lever on the costs of delegation, where it previously called it the one lever. The advice on what to put in the brief is unchanged, and the edit appeared in only 2 of 4 captures.

- Behind a feature flag
- +1 / -1 words
- Landed in 4 of 23 prompts (main prompt 4/6)

```diff
-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.
+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 first 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.
```

## 3. Read gains allow_large flag for reading oversized text files

Read tool parameters · line 5

The Read tool has a new boolean parameter, allow_large, that lets Claude read a text file or line range beyond the usual size limits, up to what fits in its context. Claude is told to use it only when it genuinely needs the whole thing or the user asked for the full file, and otherwise to read in parts with offset and limit or to search.

- +63 / -0 words
- Landed in 22 of 23 prompts (main prompt 6/6, session agents, slash commands 3/3, compaction, system reminders 8/8, subagents 3/3)

```diff
+  "allow_large": {
+   "description": "Set to true to read a text file, or a line range of one, that is over the usual size limits, up to what still fits in your context. Only use this when you genuinely need all of it or the user asked for the whole file; otherwise read it in parts with offset and limit, or search it.",
+   "type": "boolean"
+  },
```

## Where each change landed
- [Claude Code, default](https://changelogs.core-directive.com/prompts/2.1.296/system?arm=cli): #3
- [Claude Code, seeded with this account's feature flags](https://changelogs.core-directive.com/prompts/2.1.296/system?arm=cli&config=flags-account): #1, #2, #3
- [Claude Code, seeded with anonymous feature flags](https://changelogs.core-directive.com/prompts/2.1.296/system?arm=cli&config=flags-anon): #2, #3
- [Agent SDK, default](https://changelogs.core-directive.com/prompts/2.1.296/system?arm=sdk-cli): #3
- [Agent SDK, seeded with this account's feature flags](https://changelogs.core-directive.com/prompts/2.1.296/system?arm=sdk-cli&config=flags-account): #2, #3
- [Agent SDK, seeded with anonymous feature flags](https://changelogs.core-directive.com/prompts/2.1.296/system?arm=sdk-cli&config=flags-anon): #2, #3
- [Auto-mode classifier](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=automode&arm=sdk-cli): unchanged
- [Session agents: claude](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=agent-claude&arm=cli): #3
- [Slash commands: /init](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=command-init&arm=sdk-cli): #3
- [Slash commands: /security-review](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=command-security-review&arm=sdk-cli): #3
- [Slash commands: /team-onboarding](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=command-team-onboarding&arm=sdk-cli): #3
- [Compaction: Compaction instruction](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=compaction&arm=cli): #3
- [System reminders: Claude md](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=reminder-claude-md&arm=sdk-cli): #3
- [System reminders: Hook pretool block](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=reminder-hook-pretool-block&arm=sdk-cli): #3
- [System reminders: Read dup](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=reminder-read-dup&arm=sdk-cli): #3
- [System reminders: Read empty](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=reminder-read-empty&arm=sdk-cli): #3
- [System reminders: Read offset](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=reminder-read-offset&arm=sdk-cli): #3
- [System reminders: Skill run](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=reminder-skill-run&arm=sdk-cli): #3
- [System reminders: Todo nag](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=reminder-todo-nag&arm=sdk-cli): #3
- [System reminders: Toolsearch deferred](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=reminder-toolsearch-deferred&arm=sdk-cli): #3
- [Subagents: explore](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=subagent-explore&arm=sdk-cli): #3
- [Subagents: general-purpose](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=subagent-general-purpose&arm=sdk-cli): #3
- [Subagents: plan](https://changelogs.core-directive.com/prompts/2.1.296/system?surface=subagent-plan&arm=sdk-cli): #3

## Did not change
- 27 tool descriptions are word for word the same, 3 moved and are listed above. Unchanged: AskUserQuestion, Bash, CronCreate, CronDelete, CronList, Edit, EnterPlanMode, EnterWorktree, ExitPlanMode, ExitWorktree, ListAgents, Monitor, NotebookEdit, PushNotification, ReportFindings, ScheduleWakeup, SendMessage, Skill, TaskCreate, TaskGet, TaskList, TaskStop, TaskUpdate, WebFetch, WebSearch, Workflow, Write.
- 1 prompt did not move at all: Auto-mode classifier
- set aside as capture noise: 358 billing header lines
- set aside as capture noise: 224 capture date lines
- set aside as capture noise: 224 host kernel lines