# Prompt changes in v2.1.321

> 4 changes since v2.1.319, landing in 20 of 20 prompts.

[Web version](https://changelogs.core-directive.com/prompts/2.1.321)

## 1. Fable model ID moves to 5.2; fast mode no longer always uses Opus

System prompt · under “Environment”

The listed Fable model is now Fable 5.2 ('claude-fable-5-2') instead of Fable 5.1. Fast mode is now described as speeding up output on the session's current model when that model supports it, and switching to Claude Opus only otherwise; before, fast mode was described as always using Opus. The line about where Claude Code is available is unchanged.

- +21 / -14 words
- Landed in 17 of 20 prompts (main prompt 6/6, slash commands 3/3, compaction, system reminders 7/7)

```diff
- - The most recent Claude models are the Claude 5 family. Model IDs — Fable 5.1: 'claude-fable-5-1', Opus 5.5: 'claude-opus-5-5', Sonnet 5.5: 'claude-sonnet-5-5', Haiku 5.5: 'claude-haiku-5-5'. When building AI applications, default to the latest and most capable Claude models.
- - Claude Code is available as a CLI in the terminal, desktop app (Mac/Windows), web app (claude.ai/code), and IDE extensions (VS Code, JetBrains).
- - Fast mode for Claude Code uses Claude Opus with faster output (it does not downgrade to a smaller model). It can be toggled with /fast.
+ - The most recent Claude models are the Claude 5 family. Model IDs — Fable 5.2: 'claude-fable-5-2', Opus 5.5: 'claude-opus-5-5', Sonnet 5.5: 'claude-sonnet-5-5', Haiku 5.5: 'claude-haiku-5-5'. When building AI applications, default to the latest and most capable Claude models.
+ - Claude Code is available as a CLI in the terminal, desktop app (Mac/Windows), web app (claude.ai/code), and IDE extensions (VS Code, JetBrains).
+ - Fast mode for Claude Code gives faster output on this session's model if it supports fast mode, and otherwise switches the session to Claude Opus. It can be toggled with /fast.
```

## 2. EndConversation deferred-tool guidance removed

System prompt · under “Context management”

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
- Landed in 1 of 20 prompts (main prompt 1/6)

```diff
-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.
```

## 3. Claude API skill must load before any answer, command or file read

Appended context (skills, environment) · at “TRIGGER — read FIRST, before you answer, run a command or op…”

The trigger now says to read the skill first, before answering, running a command or opening a file, and to read it immediately if work has already started. Before, it only said to read it before opening the target file. The skip rule now adds that if the provider grep finds nothing, the skill should be loaded.

- +22 / -5 words
- Landed in 20 of 20 prompts (main prompt 6/6, slash commands 3/3, compaction, system reminders 7/7, subagents 3/3)

```diff
-TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).
-SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).
+TRIGGER — read FIRST, before you answer, run a command or open a file (already started? read it now); don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens).
+SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file; if nothing hits, load this skill).
```

## 4. EndConversation dropped from appended tool listing

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

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
- Landed in 1 of 20 prompts (main prompt 1/6)

```diff
-EndConversation
```

## Where each change landed
- [Claude Code, default](https://changelogs.core-directive.com/prompts/2.1.321/system?arm=cli): #1, #3
- [Claude Code, seeded with this account's feature flags](https://changelogs.core-directive.com/prompts/2.1.321/system?arm=cli&config=flags-account): #1, #2, #3, #4
- [Claude Code, seeded with anonymous feature flags](https://changelogs.core-directive.com/prompts/2.1.321/system?arm=cli&config=flags-anon): #1, #3
- [Agent SDK, default](https://changelogs.core-directive.com/prompts/2.1.321/system?arm=sdk-cli): #1, #3
- [Agent SDK, seeded with this account's feature flags](https://changelogs.core-directive.com/prompts/2.1.321/system?arm=sdk-cli&config=flags-account): #1, #3
- [Agent SDK, seeded with anonymous feature flags](https://changelogs.core-directive.com/prompts/2.1.321/system?arm=sdk-cli&config=flags-anon): #1, #3
- [Slash commands: /init](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=command-init&arm=sdk-cli): #1, #3
- [Slash commands: /security-review](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=command-security-review&arm=sdk-cli): #1, #3
- [Slash commands: /team-onboarding](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=command-team-onboarding&arm=sdk-cli): #1, #3
- [Compaction: Compaction instruction](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=compaction&arm=cli): #1, #3
- [System reminders: Claude md](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=reminder-claude-md&arm=sdk-cli): #1, #3
- [System reminders: Hook pretool block](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=reminder-hook-pretool-block&arm=sdk-cli): #1, #3
- [System reminders: Read empty](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=reminder-read-empty&arm=sdk-cli): #1, #3
- [System reminders: Read offset](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=reminder-read-offset&arm=sdk-cli): #1, #3
- [System reminders: Skill run](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=reminder-skill-run&arm=sdk-cli): #1, #3
- [System reminders: Todo nag](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=reminder-todo-nag&arm=sdk-cli): #1, #3
- [System reminders: Toolsearch deferred](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=reminder-toolsearch-deferred&arm=sdk-cli): #1, #3
- [Subagents: explore](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=subagent-explore&arm=sdk-cli): #3
- [Subagents: general-purpose](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=subagent-general-purpose&arm=sdk-cli): #3
- [Subagents: plan](https://changelogs.core-directive.com/prompts/2.1.321/system?surface=subagent-plan&arm=sdk-cli): #3

## Did not change
- 31 tool descriptions are word for word the same. Unchanged: 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.
- set aside as capture noise: 352 billing header lines
- set aside as capture noise: 220 capture date lines
- set aside as capture noise: 220 host kernel lines