Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix [FEATURE] /Context is too verbose [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#48798•Fetched 2026-04-16 06:50:41
View on GitHub
Comments
1
Participants
2
Timeline
3
Reactions
0
Author
matyasLevinskymatyasLevinsky
Participants
github-actions[bot]github-actions[bot]matyasLevinskymatyasLevinsky
Timeline (top)
labeled ×2commented ×1
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

9 out of 10 times I am typing the /context command I am only interested in one single piece of information: how many tokens are in the current context, and what percentage is that from the available total. The original /context could answer that question quickly and adequately. The current context writes you an novel. I see available MCP tools, memory and files. In my case I even see all available, instead of only allowed mcp tools. While there is a standanlone command for that. (/mcp)

What i am asking for is a command that lets me get the important part of the context, eg. how full it is, without overwhelming me with useless details. I am asking to either add a flag to /context or to add a /mincontext command, which will answer the main question in 1, or at most 2 lines.

Alternatively allow for modification of the verbosity of default CC commands.

Proposed Solution

Add a /mincontext or /quickcontext command that will give only the number and percentage of tokens.

Alternative Solutions

Alternatively fix the verbosity of the current implementation.

Priority

Medium - Would be very helpful

Feature Category

Interactive mode (TUI)

Use Case Example

My current /context output: (I do not claim my usage to be good/optimal.):| """ /context ⎿ Context Usage ⛁ ⛁ ⛁ ⛀ ⛀ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ Opus 4.6 (1M context) claude-opus-4-6[1m] ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛁ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ 158.6k/1m tokens (16%)

 ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶   Estimated usage by category
                                           ⛁ System prompt: 6.1k tokens (0.6%)
 ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶   ⛁ System tools: 10.2k tokens (1.0%)
                                           ⛁ Memory files: 340 tokens (0.0%)
 ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶   ⛁ Skills: 631 tokens (0.1%)
                                           ⛁ Messages: 141.4k tokens (14.1%)
 ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶   ⛶ Free space: 808.4k (80.8%)
                                           ⛝ Autocompact buffer: 33k tokens
 ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶                         (3.3%)

 ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶

 ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶

 ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛶ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝ ⛝

 MCP tools · /mcp (loaded on-demand)

 Available
 └ mcp__claude_ai_Asana__authenticate
 └ mcp__claude_ai_Asana__complete_authentication
 └ mcp__claude_ai_Atlassian__authenticate
 └ mcp__claude_ai_Atlassian__complete_authentication
 └ mcp__claude_ai_Box__authenticate
 └ mcp__claude_ai_Box__complete_authentication
 └ mcp__claude_ai_Canva__authenticate
 └ mcp__claude_ai_Canva__complete_authentication
 └ mcp__claude_ai_HubSpot__authenticate
 └ mcp__claude_ai_HubSpot__complete_authentication
 └ mcp__claude_ai_Intercom__authenticate
 └ mcp__claude_ai_Intercom__complete_authentication
 └ mcp__claude_ai_Linear__authenticate
 └ mcp__claude_ai_Linear__complete_authentication
 └ mcp__claude_ai_monday_com__authenticate
 └ mcp__claude_ai_monday_com__complete_authentication
 └ mcp__claude_ai_Notion__authenticate
 └ mcp__claude_ai_Notion__complete_authentication

 Memory files · /memory
 └ ~/.claude/projects/-home-matyas/memory/MEMORY.md: 340 tokens

 Skills · /skills

"""

Additional Context

No response

extent analysis

TL;DR

The user is requesting a simpler way to get the context information, specifically the number and percentage of tokens, without the overwhelming details provided by the current /context command.

Guidance

  • Consider adding a flag to the /context command to allow users to specify the level of detail they want to see.
  • Introduce a new command, such as /mincontext or /quickcontext, that provides only the essential information about the context, like the number and percentage of tokens.
  • Review the current implementation of the /context command to see if its verbosity can be reduced or made configurable.
  • Evaluate the possibility of allowing users to customize the output of the /context command through configuration options or preferences.

Example

No code example is provided as the issue is more related to the functionality and user experience of the /context command rather than a specific code snippet.

Notes

The solution should focus on enhancing the user experience by providing a more concise and relevant output for the /context command, either through a new command or by modifying the existing one. The exact implementation details would depend on the underlying architecture and design of the system.

Recommendation

Apply a workaround by introducing a new command, such as /mincontext, which would provide the simplified context information, allowing users to quickly access the essential details without the need for a full overhaul of the /context command. This approach would offer a straightforward solution to the user's request without potentially disrupting the existing functionality.

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…
#tensor shape#autograd error#model save/load#optimization#mixed precision

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] /Context is too verbose [1 comments, 2 participants]