# Prompt changes in v2.1.323 > 8 changes since v2.1.322, landing in 20 of 20 prompts. [Web version](https://changelogs.core-directive.com/prompts/2.1.323) ## 1. Ultracode confirmation now called a message from the system Workflow tool description · line 4 The two Workflow trigger conditions for ultracode now say a "message from the system" confirms the keyword or session mode, where they used to name a system-reminder. The conditions themselves are unchanged. - +8 / -4 words - Landed in 17 of 20 prompts (main prompt 6/6, slash commands 3/3, compaction, system reminders 7/7) ```diff -- The user included the keyword "ultracode" in their prompt (you'll see a system-reminder confirming it). -- Ultracode is on for the session (a system-reminder confirms it) — see **Ultracode** in the workflow authoring reference. +- The user included the keyword "ultracode" in their prompt (you'll see a message from the system confirming it). +- Ultracode is on for the session (a message from the system confirms it) — see **Ultracode** in the workflow authoring reference. ``` ## 2. Deferred tool names described as arriving in a system message ToolSearch tool description · at the opening ToolSearch now says deferred tools appear by name "in a message from the system" rather than in messages. How deferred tools are fetched and then called is unchanged. - +5 / -3 words - Landed in 20 of 20 prompts (main prompt 6/6, slash commands 3/3, compaction, system reminders 7/7, subagents 3/3) ```diff -Deferred tools appear by name in messages. Until fetched, only the name is known — there is no parameter schema, so the tool cannot be invoked. This tool takes a query, matches it against the deferred tool list, and returns the matched tools' complete JSONSchema definitions inside a block. Once a tool's schema appears in that result, it is callable exactly like any tool defined at the top of the prompt. +Deferred tools appear by name in a message from the system. Until fetched, only the name is known — there is no parameter schema, so the tool cannot be invoked. This tool takes a query, matches it against the deferred tool list, and returns the matched tools' complete JSONSchema definitions inside a block. Once a tool's schema appears in that result, it is callable exactly like any tool defined at the top of the prompt. ``` ## 3. Skill listing now described as coming from the system Skill tool description · at the opening The Skill tool now says available skills appear "in a listing from the system" instead of a system-reminder listing. The guidance on when and how to invoke skills is the same. - +4 / -3 words - Landed in 20 of 20 prompts (main prompt 6/6, slash commands 3/3, compaction, system reminders 7/7, subagents 3/3) ```diff -A skill is a packaged set of instructions the user or project has set up for a particular kind of task (deploy steps, a review checklist, a repo-specific workflow). Available skills appear in a system-reminder listing with one-line descriptions. When the task at hand is one a listed skill covers, call this tool first — the skill's instructions load into the turn for you to follow in place of your default approach; some skills instead run in a subagent and return the finished result. A skill that runs in the background returns only the agent's name — its result arrives later as a task notification, so don't wait on it or invoke it again in the meantime. Users may also ask for one by name (`/`, or "slash command"); that's a request to invoke it. +A skill is a packaged set of instructions the user or project has set up for a particular kind of task (deploy steps, a review checklist, a repo-specific workflow). Available skills appear in a listing from the system with one-line descriptions. When the task at hand is one a listed skill covers, call this tool first — the skill's instructions load into the turn for you to follow in place of your default approach; some skills instead run in a subagent and return the finished result. A skill that runs in the background returns only the agent's name — its result arrives later as a task notification, so don't wait on it or invoke it again in the meantime. Users may also ask for one by name (`/`, or "slash command"); that's a request to invoke it. ``` ## 4. Agent types listed in messages from the system, not system-reminders Agent tool description · at the opening The Agent tool now says available agent types are listed in "messages from the system" rather than in messages. This is a wording change with no change in behaviour. - +4 / -3 words - Landed in 18 of 20 prompts (main prompt 6/6, slash commands 3/3, compaction, system reminders 7/7, subagents 1/3) ```diff -Available agent types are listed in messages in the conversation. +Available agent types are listed in messages from the system in the conversation. ``` ## 5. Ship-audit example prompt says feature flag instead of GrowthBook gate Agent tool description · under “Writing the prompt” In the example subagent prompt for auditing a branch before shipping, "the GrowthBook gate" is replaced with the generic "the feature flag". The example otherwise reads the same. It appeared in only 6 of 17 captures. - +2 / -2 words - Landed in 6 of 20 prompts (main prompt 6/6) ```diff - prompt: "Audit what's left before this branch can ship. Check: uncommitted changes, commits ahead of main, whether tests exist, whether the GrowthBook gate is wired up, whether CI-relevant files changed. Report a punch list — done vs. missing. Under 200 words." + prompt: "Audit what's left before this branch can ship. Check: uncommitted changes, commits ahead of main, whether tests exist, whether the feature flag is wired up, whether CI-relevant files changed. Report a punch list — done vs. missing. Under 200 words." ``` ## 6. Audit example reply says feature flag instead of GrowthBook gate Agent tool description · under “Writing the prompt” The example assistant reply summarizing the audit now lists a "feature flag" blocker instead of a "GrowthBook gate" blocker. This matches the edit to the example prompt, and the meaning is the same. It appeared in only 6 of 17 captures. - +2 / -2 words - Landed in 6 of 20 prompts (main prompt 6/6) ```diff -assistant: Audit's back. Three blockers: no tests for the new prompt path, GrowthBook gate wired but not in build_flags.yaml, and one uncommitted file. +assistant: Audit's back. Three blockers: no tests for the new prompt path, feature flag wired but not in build_flags.yaml, and one uncommitted file. ``` ## 7. Git commit rule adds .claude/settings.local.json as a likely secret Bash tool description · under “Committing changes with git” The Bash git guidance now names .claude/settings.local.json alongside .env and credentials.json as files Claude should not commit. Claude should warn the user if they ask to commit it. This appeared in 6 of 17 captures. - +4 / -0 words - Landed in 6 of 20 prompts (main prompt 6/6) ```diff - - Do not commit files that likely contain secrets (.env, credentials.json, etc). Warn the user if they specifically request to commit those files + - Do not commit files that likely contain secrets (.env, credentials.json, .claude/settings.local.json, etc). Warn the user if they specifically request to commit those files ``` ## 8. init and security-review skills get one-line descriptions Appended context (skills, environment) · entries “init” and “security-review” In the appended skills listing, init and security-review now carry descriptions. init creates a CLAUDE.md with codebase documentation, and security-review reviews the pending changes on the current branch. Before, only their names were listed. This appeared in 6 of 17 captures. - Only for default - +24 / -3 words - Landed in 6 of 20 prompts (main prompt 6/6) ```diff -- init -- security-review +- init: Initialize a new CLAUDE.md file with codebase documentation +- security-review: Complete a security review of the pending changes on the current branch ``` ## Where each change landed - [Claude Code, default](https://changelogs.core-directive.com/prompts/2.1.323/system?arm=cli): #1, #2, #3, #4, #5, #6, #7, #8 - [Claude Code, seeded with this account's feature flags](https://changelogs.core-directive.com/prompts/2.1.323/system?arm=cli&config=flags-account): #1, #2, #3, #4, #5, #6, #7, #8 - [Claude Code, seeded with anonymous feature flags](https://changelogs.core-directive.com/prompts/2.1.323/system?arm=cli&config=flags-anon): #1, #2, #3, #4, #5, #6, #7, #8 - [Agent SDK, default](https://changelogs.core-directive.com/prompts/2.1.323/system?arm=sdk-cli): #1, #2, #3, #4, #5, #6, #7, #8 - [Agent SDK, seeded with this account's feature flags](https://changelogs.core-directive.com/prompts/2.1.323/system?arm=sdk-cli&config=flags-account): #1, #2, #3, #4, #5, #6, #7, #8 - [Agent SDK, seeded with anonymous feature flags](https://changelogs.core-directive.com/prompts/2.1.323/system?arm=sdk-cli&config=flags-anon): #1, #2, #3, #4, #5, #6, #7, #8 - [Slash commands: /init](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=command-init&arm=sdk-cli): #1, #2, #3, #4 - [Slash commands: /security-review](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=command-security-review&arm=sdk-cli): #1, #2, #3, #4 - [Slash commands: /team-onboarding](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=command-team-onboarding&arm=sdk-cli): #1, #2, #3, #4 - [Compaction: Compaction instruction](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=compaction&arm=cli): #1, #2, #3, #4 - [System reminders: Claude md](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=reminder-claude-md&arm=sdk-cli): #1, #2, #3, #4 - [System reminders: Hook pretool block](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=reminder-hook-pretool-block&arm=sdk-cli): #1, #2, #3, #4 - [System reminders: Read empty](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=reminder-read-empty&arm=sdk-cli): #1, #2, #3, #4 - [System reminders: Read offset](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=reminder-read-offset&arm=sdk-cli): #1, #2, #3, #4 - [System reminders: Skill run](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=reminder-skill-run&arm=sdk-cli): #1, #2, #3, #4 - [System reminders: Todo nag](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=reminder-todo-nag&arm=sdk-cli): #1, #2, #3, #4 - [System reminders: Toolsearch deferred](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=reminder-toolsearch-deferred&arm=sdk-cli): #1, #2, #3, #4 - [Subagents: explore](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=subagent-explore&arm=sdk-cli): #2, #3 - [Subagents: general-purpose](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=subagent-general-purpose&arm=sdk-cli): #2, #3, #4 - [Subagents: plan](https://changelogs.core-directive.com/prompts/2.1.323/system?surface=subagent-plan&arm=sdk-cli): #2, #3 ## Did not change - 26 tool descriptions are word for word the same, 5 moved and are listed above. Unchanged: AskUserQuestion, CronCreate, CronDelete, CronList, DeferredToolPlaceholder, Edit, EnterPlanMode, EnterWorktree, ExitPlanMode, ExitWorktree, ListAgents, Monitor, NotebookEdit, PushNotification, Read, ReportFindings, ScheduleWakeup, SendMessage, TaskCreate, TaskGet, TaskList, TaskStop, TaskUpdate, WebFetch, WebSearch, 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