Skip to content

Claude's [Suggestion Mode] requests are captured #95

@bgmcmullen

Description

@bgmcmullen

Claude code generates suggested inputs by sending the full conversation history followed by:

[SUGGESTION MODE: Suggest what the user might naturally type next into Claude Code.]

FIRST: Look at the user's recent messages and original request.

Your job is to predict what THEY would type - not what you think they should do.

THE TEST: Would they think "I was just about to type that"?

EXAMPLES:
User asked "fix the bug and run tests", bug is fixed → "run the tests"
After code written → "try it out"
Claude offers options → suggest the one the user would likely pick, based on conversation
Claude asks to continue → "yes" or "go ahead"
Task complete, obvious follow-up → "commit this" or "push it"
After error or misunderstanding → silence (let them assess/correct)

Be specific: "run the tests" beats "continue".

NEVER SUGGEST:
- Evaluative ("looks good", "thanks")
- Questions ("what about...?")
- Claude-voice ("Let me...", "I'll...", "Here's...")
- New ideas they didn't ask about
- Multiple sentences

Stay silent if the next step isn't obvious from what the user said.

Format: 2-12 words, match the user's style. Or nothing.

Reply with ONLY the suggestion, no quotes or explanation.

These messages get collected and since they have the same conversation id, end up looking like part of the conversation.

Image

There may be certain situations where you would want to know when claude is generating a suggested input, but they should be differentiated from the actual conversation some how, otherwise they are very confusing

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions