NEW: Claude Code Security — research preview →

Utility Prompts

Illustrative helper prompts for session management and user experience — session titles, tool summaries, away recaps, and next-action suggestions.

Read time: 4 min

title: "Utility Prompts" description: "Illustrative helper prompts for session management and user experience — session titles, tool summaries, away recaps, and next-action suggestions." section: "Claude" readTime: "4 min"

Utility Prompts

Small helper prompts for session management and user experience. Each handles one specific recurring task in a coding agent session.

These are illustrative, community-reconstructed prompts, not Claude Code's internal ones; the exact wording, the 3 to 7 word and roughly 30 character limits, and the JSON title format could not be verified against a primary source. Related user-facing features are documented: Claude Code can show a one-line recap of the session after you step away (generated in the background once at least three minutes have passed since the last completed turn and the terminal is unfocused), sessions can be named with /rename, and prompt suggestions appear in the input. Use these templates when building the same features in your own agent. Small, high-frequency helpers like these are good candidates for a fast model such as Haiku 5.5.


Session Title

Produce a concise title for this session.

Rules

  • Use 3–7 words that capture the primary topic or objective
  • Apply sentence case: capitalize only the first word and proper nouns
  • Return a JSON object with a single "title" field

Examples

GoodBad
"Fix login button on mobile""Code changes" — too vague
"Add OAuth authentication""Implementing the new user registration flow with email verification" — too long
"Debug failing CI tests""Fix Login Button On Mobile" — title case instead of sentence case

Prompt Template

Produce a concise title for this session.
 
Rules:
- Use 3–7 words that capture the primary topic or objective.
- Apply sentence case: capitalize only the first word and proper nouns.
- Return a JSON object with a single "title" field.
 
Format:
{ "title": "Your session title here" }

Tool Summary

Compose a brief label describing what the tool calls accomplished.

Rules

  • This label appears as a single-line row in the UI and truncates around 30 characters — treat it like a git commit subject
  • Use past tense verb + the most distinctive noun from the operation
  • Strip articles, connectors, and location context first when trimming for length

Examples

Searched in auth/
Fixed NPE in UserService
Created signup endpoint
Read config.json
Ran failing tests

Prompt Template

Compose a brief label describing what the tool calls accomplished.
 
Rules:
- This label appears as a single-line row in the UI and truncates around 30 characters.
  Treat it like a git commit subject.
- Use past tense verb + the most distinctive noun from the operation.
- Strip articles, connectors, and location context first when trimming for length.
 
Examples:
- "Searched in auth/"
- "Fixed NPE in UserService"
- "Created signup endpoint"
- "Read config.json"
- "Ran failing tests"
 
Format:
One short phrase. No trailing punctuation. No explanation.

Away Recap

Compose a brief catch-up message for when the user stepped away and is returning.

Rules

  • Write exactly 1–3 short sentences
  • Open by stating the high-level task — what they are building or debugging, not implementation minutiae
  • Follow with the concrete next step to take right now
  • Omit status reports, progress percentages, and commit-by-commit recaps
  • If session memory is available, use it as broader context for framing the recap

Prompt Template

The user stepped away and is returning. Compose a brief catch-up message.
 
Rules:
- Write exactly 1–3 short sentences.
- Open by stating the high-level task — what they are building or debugging,
  not implementation minutiae.
- Follow with the concrete next step to take right now.
- Omit status reports, progress percentages, and commit-by-commit recaps.
- If session memory is available, use it as broader context for framing the recap.
 
Format:
Plain text. No headings, no bullets, no formatting. Just 1–3 sentences.

Next Action Suggestion

Recommend the single highest-value next action the user could take.

Rules

  • Ground the suggestion in conversation context and whatever was just accomplished
  • The recommendation must be specific and immediately actionable — not a generic platitude
  • Consider what naturally follows from the work that was completed
  • Identify the current bottleneck or logical continuation point
  • Ensure the action is executable right now given the current state

Prompt Template

Recommend the single highest-value next action the user could take.
 
Rules:
- Ground the suggestion in conversation context and whatever was just accomplished.
- The recommendation must be specific and immediately actionable — not a generic platitude.
- Consider what naturally follows from the work that was completed.
- Identify the current bottleneck or logical continuation point.
- Ensure the action is executable right now given the current state.
 
Format:
One concise, direct suggestion. No preamble, no alternatives, no hedging.

Source: repowise-dev/claude-code-prompts — MIT License. Independently authored; not affiliated with Anthropic.