# Claude Code v2.1.172: system prompt > 1 prompt changed. 1 of 25 tool descriptions changed. Compared against v2.1.170. Web version: https://changelogs.core-directive.com/prompts/2.1.172?arm=cli ## What this version holds - model strings captured: 27 - tool descriptions: 25 - compared against: v2.1.170 - system prompt edits: 1 - widest system prompt edit: +2/-0 lines - tool descriptions changed: 1 ## What moved ### System prompt, reached 1 of 27 arms (+2/-0 lines) This edit reached 1 of 27 arms: claude-fable-5. ```diff @@ from line 27 @@ For actions that are hard to reverse or outward-facing, confirm first unless durably authorized or explicitly told to proceed without asking; approval in one context doesn't extend to the next. Sending content to an external service publishes it; it may be cached or indexed even if later deleted. Before deleting or overwriting, look at the target — if what you find contradicts how it was described, or you didn't create it, surface that instead of proceeding. Report outcomes faithfully: if tests fail, say so with the output; if a step was skipped, say that; when something is done and verified, state it plainly without hedging. +This iteration of Claude is Claude Fable 5, the first model in Anthropic's new Claude 5 family and part of a new Mythos-class model tier that sits above Claude Opus in capability. Claude Fable 5 and Claude Mythos 5 share the same underlying model. Claude Fable 5 is our most intelligent generally available model, and includes additional safety measures for dual-use capabilities, while Claude Mythos 5 is available without those measures to only approved organizations. Fable 5 is the most advanced generally available Claude model. If the person asks about the differences between the two, Claude can direct them to https://www.anthropic.com/news/claude-fable-5-mythos-5 for more information. + # Session-specific guidance - If you need the user to run a shell command themselves (e.g., an interactive login like `gcloud auth login`), suggest they type `! ` in the prompt — the `!` prefix runs the command in this session so its output lands directly in the conversation. - When the user types `/`, invoke it via Skill. Only use skills listed in the user-invocable skills section — don't guess. ``` ### Tool: Bash, reached 4 of 27 arms (+2/-2 lines) This edit reached 4 of 27 arms: claude-3-opus, claude-sonnet-5, claude-sonnet-5[1m], sonnet[1m]. ```diff @@ from line 63 @@ 3. Run the following commands in parallel: - Add relevant untracked files to the staging area. - Create the commit with a message ending with: - Co-Authored-By: Claude Fable 5 + Co-Authored-By: Claude - Run git status after the commit completes to verify success. Note: git status depends on the commit completing, so run it sequentially after the commit. 4. If the commit fails due to pre-commit hook: fix the issue and create a NEW commit ``` ```diff @@ from line 80 @@ git commit -m "$(cat <<'EOF' Commit message here. - Co-Authored-By: Claude Fable 5 + Co-Authored-By: Claude EOF )" ``` ### Tool: Bash, reached 3 of 27 arms (+1/-1 lines) This edit reached 3 of 27 arms: claude-opus-5, claude-opus-5[1m], default. ```diff @@ from line 10 @@ - Use the `gh` CLI for GitHub operations (PRs, issues, API). - Commit or push only when the user asks. If on the default branch, branch first. - End git commit messages with: -Co-Authored-By: Claude Fable 5 +Co-Authored-By: Claude - End PR bodies with: 🤖 Generated with [Claude Code](https://claude.com/claude-code) ``` ## Tool descriptions - Agent: https://changelogs.core-directive.com/prompts/2.1.172/tools/Agent.txt?arm=cli - AskUserQuestion: https://changelogs.core-directive.com/prompts/2.1.172/tools/AskUserQuestion.txt?arm=cli - Bash (changed in this version): https://changelogs.core-directive.com/prompts/2.1.172/tools/Bash.txt?arm=cli - CronCreate: https://changelogs.core-directive.com/prompts/2.1.172/tools/CronCreate.txt?arm=cli - CronDelete: https://changelogs.core-directive.com/prompts/2.1.172/tools/CronDelete.txt?arm=cli - CronList: https://changelogs.core-directive.com/prompts/2.1.172/tools/CronList.txt?arm=cli - Edit: https://changelogs.core-directive.com/prompts/2.1.172/tools/Edit.txt?arm=cli - EnterPlanMode: https://changelogs.core-directive.com/prompts/2.1.172/tools/EnterPlanMode.txt?arm=cli - EnterWorktree: https://changelogs.core-directive.com/prompts/2.1.172/tools/EnterWorktree.txt?arm=cli - ExitPlanMode: https://changelogs.core-directive.com/prompts/2.1.172/tools/ExitPlanMode.txt?arm=cli - ExitWorktree: https://changelogs.core-directive.com/prompts/2.1.172/tools/ExitWorktree.txt?arm=cli - NotebookEdit: https://changelogs.core-directive.com/prompts/2.1.172/tools/NotebookEdit.txt?arm=cli - Read: https://changelogs.core-directive.com/prompts/2.1.172/tools/Read.txt?arm=cli - ScheduleWakeup: https://changelogs.core-directive.com/prompts/2.1.172/tools/ScheduleWakeup.txt?arm=cli - Skill: https://changelogs.core-directive.com/prompts/2.1.172/tools/Skill.txt?arm=cli - TaskCreate: https://changelogs.core-directive.com/prompts/2.1.172/tools/TaskCreate.txt?arm=cli - TaskGet: https://changelogs.core-directive.com/prompts/2.1.172/tools/TaskGet.txt?arm=cli - TaskList: https://changelogs.core-directive.com/prompts/2.1.172/tools/TaskList.txt?arm=cli - TaskOutput: https://changelogs.core-directive.com/prompts/2.1.172/tools/TaskOutput.txt?arm=cli - TaskStop: https://changelogs.core-directive.com/prompts/2.1.172/tools/TaskStop.txt?arm=cli - TaskUpdate: https://changelogs.core-directive.com/prompts/2.1.172/tools/TaskUpdate.txt?arm=cli - WebFetch: https://changelogs.core-directive.com/prompts/2.1.172/tools/WebFetch.txt?arm=cli - WebSearch: https://changelogs.core-directive.com/prompts/2.1.172/tools/WebSearch.txt?arm=cli - Workflow: https://changelogs.core-directive.com/prompts/2.1.172/tools/Workflow.txt?arm=cli - Write: https://changelogs.core-directive.com/prompts/2.1.172/tools/Write.txt?arm=cli ## Full text - system prompt: https://changelogs.core-directive.com/prompts/2.1.172/system.txt?arm=cli