claude-code - 💡(How to fix) Fix [DOCS] Slash command docs omit mid-input autocomplete behavior

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Root Cause

Version context: This gap is relevant to the v2.1.136 slash-command autocomplete change under review because the reference pages still present slash discovery as start-of-message only.

RAW_BUFFERClick to expand / collapse

Documentation Type

Incorrect/outdated documentation

Documentation Location

https://code.claude.com/docs/en/commands

Section/Topic

Slash command discovery and autocomplete behavior in interactive input

Current Documentation

The docs currently say:

Type / to see every command available to you, or type / followed by letters to filter.

A command is only recognized at the start of your message. Text that follows the command name is passed to it as arguments.

The interactive mode page also says:

| / at start | Command or skill | See commands and skills |

What's Wrong or Missing?

These pages currently frame slash commands as a start-of-message interaction and do not explain the current autocomplete behavior when / is typed later in the input.

That wording conflates two different things:

A. Command execution

/command execution still needs clear start-of-message rules.

B. Command autocomplete and discovery

The docs do not say that the slash-command autocomplete UI can appear when / is typed mid-input, so users reading the reference can reasonably conclude that later-in-prompt slash autocomplete is unsupported or broken.

Suggested Improvement

Add a short clarification to the commands and interactive mode docs that separates command execution from autocomplete behavior.

Before:

A command is only recognized at the start of your message.

After:

Claude executes a slash command only when it starts the message, but the slash-command autocomplete menu can appear anywhere in the input when you type /, so you can discover or insert a command while editing a longer prompt.

Also update the interactive mode quick-commands table so the / row does not imply that slash-related discovery only works at prompt start.

Impact

Medium - Makes feature difficult to understand

Additional Context

Affected Pages:

PageLine(s)Context
https://code.claude.com/docs/en/commands11-13Says / shows commands, then states commands are only recognized at the start of the message
https://code.claude.com/docs/en/interactive-mode83-86, 106Quick commands table labels / as "at start" and the commands section does not clarify mid-input autocomplete

Cross-reference:

PageLine(s)Context
https://code.claude.com/docs/en/changelog2262-2263Changelog already says slash command autocomplete works when / appears anywhere in input

Total scope: 2 primary docs pages affected

Version context: This gap is relevant to the v2.1.136 slash-command autocomplete change under review because the reference pages still present slash discovery as start-of-message only.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix [DOCS] Slash command docs omit mid-input autocomplete behavior