claude-code - 💡(How to fix) Fix [FEATURE] Support slash command autocomplete for all /commands on a line, not just the first [1 comments, 2 participants]

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…
GitHub stats
anthropics/claude-code#49412Fetched 2026-04-17 08:41:53
View on GitHub
Comments
1
Participants
2
Timeline
4
Reactions
0
Timeline (top)
labeled ×3commented ×1

Fix Action

Fix / Workaround

Currently, users must invoke commands one at a time in separate prompts, or memorize exact skill names to chain them. There is no workaround that preserves the autocomplete experience for secondary commands.

RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing requests and this feature hasn't been requested yet
  • This is a single feature request (not multiple features)

Problem Statement

When chaining multiple slash commands on a single prompt line (e.g. /commit /simplify), autocomplete only activates for the first command. After Tab-completing the first skill, typing a second / produces no dropdown — the user must type the full command name from memory with no discovery or completion support.

This creates a UX inconsistency: the first skill feels first-class, but every subsequent skill on the same line is invisible to the autocomplete system. The gap is most noticeable precisely when autocomplete would be most useful — when the user is already in a multi-command flow and wants to chain operations quickly.

Proposed Solution

The autocomplete system should recognize any / that appears at a word boundary (preceded by whitespace or at start-of-line) as a potential slash command trigger — not just the first / on a line.

Ideal behavior:

  • Typing /commit then /sim surfaces matching skills (e.g. /simplify) in the dropdown
  • Tab completes the second command just as it does the first
  • The autocomplete anchor follows the cursor position rather than being fixed to column 0

To avoid false positives, / inside URLs (https://...) or filesystem paths (/usr/local/...) should not trigger command autocomplete — a "preceded by whitespace or start-of-line" heuristic covers this.

Alternative Solutions

Currently, users must invoke commands one at a time in separate prompts, or memorize exact skill names to chain them. There is no workaround that preserves the autocomplete experience for secondary commands.

Priority

Low

Feature Category

Interactive mode (TUI)

Use Case Example

  1. I want to commit my current changes and then run a code simplification pass
  2. I type /commit — autocomplete triggers, I Tab to complete it
  3. I type a space and then / to start a second command
  4. Current behavior: no dropdown appears; I must type /simplify in full
  5. Desired behavior: the dropdown appears, filtered by what I've typed after /, and Tab completes it

Additional Context

The fix likely involves generalizing the autocomplete trigger from "position 0" or "first / match" to "any / preceded by whitespace or start-of-line." The dropdown positioning logic may also need to anchor relative to cursor position rather than a fixed column offset.

extent analysis

TL;DR

Update the autocomplete system to recognize any / at a word boundary as a potential slash command trigger, not just the first / on a line.

Guidance

  • Review the current autocomplete trigger logic to understand how it is currently limited to the first / on a line.
  • Modify the trigger logic to check for / preceded by whitespace or at the start of a line, to enable autocomplete for subsequent commands.
  • Consider updating the dropdown positioning logic to anchor relative to the cursor position, rather than a fixed column offset.
  • Test the updated autocomplete system with various command chaining scenarios to ensure it works as expected.

Example

No code snippet is provided as the issue does not include specific code references.

Notes

The fix may require updates to the autocomplete system's parsing and rendering logic. The proposed solution's heuristic of checking for / preceded by whitespace or at the start of a line should help avoid false positives.

Recommendation

Apply the proposed workaround by updating the autocomplete trigger logic to recognize any / at a word boundary, as this should provide a more consistent and user-friendly experience for command chaining.

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 [FEATURE] Support slash command autocomplete for all /commands on a line, not just the first [1 comments, 2 participants]