Prompt changes · v2.1.308 against v2.1.307

2 changes since v2.1.307, landing in 1 of 23 prompts.

Every prompt v2.1.308 sent, compared word for word with the capture before it. Each card is one edit, with every prompt it reached; the table after them shows where each one landed.

What changed 2

System prompt · under “Context management”

EndConversation deferred-tool guidance removed

The system prompt no longer mentions the deferred EndConversation tool. It previously said to use it only for sustained user abuse aimed at the assistant or when the user explicitly asked for a demonstration, and to load its full guidance via ToolSearch first. This appeared in only 1 of 23 captures, so it likely applies to one specific setup.

Behind a feature flag

+0 −34 words

EndConversation (deferred tool): use only for sustained user abuse directed at the assistant, or when the user explicitly asks to see it demonstrated. Load the full guidance via ToolSearch("select:EndConversation") before using it.

Appended context (skills, environment) · at “EndConversation”

EndConversation dropped from appended tool listing

The name EndConversation was removed from the appended context, so it is no longer listed there as an available deferred tool. This was seen in only 1 of 23 captures and matches the removal of the EndConversation guidance from the system prompt.

Behind a feature flag

+0 −1 words

~~EndConversation~~

Where each change landed

Every prompt the release sent, one row each. A number is a change from the list above; click it to jump there. Rows with more than one model string count them, because each model gets its own copy of the prompt.

Prompt	1	2	Status
Main prompt
Claude Code, default27 models	·	·	unchanged
Claude Code, seeded with this account's feature flags27 models	13/27	13/27	2 changes
Claude Code, seeded with anonymous feature flags27 models	·	·	unchanged
Agent SDK, default27 models	·	·	unchanged
Agent SDK, seeded with this account's feature flags27 models	·	·	unchanged
Agent SDK, seeded with anonymous feature flags27 models	·	·	unchanged
Auto-mode classifier
Auto-mode classifier1 model	·	·	unchanged
Session agents
claude1 model	·	·	unchanged
Slash commands
/init1 model	·	·	unchanged
/security-review1 model	·	·	unchanged
/team-onboarding1 model	·	·	unchanged
Compaction
Compaction instruction1 model	·	·	unchanged
System reminders
Claude md1 model	·	·	unchanged
Hook pretool block1 model	·	·	unchanged
Read dup1 model	·	·	unchanged
Read empty1 model	·	·	unchanged
Read offset1 model	·	·	unchanged
Skill run1 model	·	·	unchanged
Todo nag1 model	·	·	unchanged
Toolsearch deferred1 model	·	·	unchanged
Subagents
explore1 model	·	·	unchanged
general-purpose1 model	·	·	unchanged
plan1 model	·	·	unchanged

Did not change

31 tool descriptions are word for word the same.

Agent AskUserQuestion Bash CronCreate CronDelete CronList DeferredToolPlaceholder Edit EnterPlanMode EnterWorktree ExitPlanMode ExitWorktree ListAgents Monitor NotebookEdit PushNotification Read ReportFindings ScheduleWakeup SendMessage Skill TaskCreate TaskGet TaskList TaskStop TaskUpdate ToolSearch WebFetch WebSearch Workflow Write

22 prompts did not move at all: Claude Code, default, Claude Code, seeded with anonymous feature flags, Agent SDK, default, Agent SDK, seeded with this account's feature flags, Agent SDK, seeded with anonymous feature flags, Auto-mode classifier, Session agents: claude, Slash commands: /init, Slash commands: /security-review, Slash commands: /team-onboarding, Compaction: Compaction instruction, System reminders: Claude md, System reminders: Hook pretool block, System reminders: Read dup, System reminders: Read empty, System reminders: Read offset, System reminders: Skill run, System reminders: Todo nag, System reminders: Toolsearch deferred, Subagents: explore, Subagents: general-purpose, Subagents: plan.

Set aside as capture noise

These change on every capture by construction, so they are masked before comparing and never counted as a change.

358 billing header lines
224 capture date lines
224 host kernel lines