Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix System prompt token bloat: ~40-50% increase between v2.1.92 and v2.1.100 [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#46339•Fetched 2026-04-11 06:22:53
View on GitHub
Comments
1
Participants
2
Timeline
7
Reactions
0
Author
stream727stream727
Participants
github-actions[bot]github-actions[bot]stream727stream727
Timeline (top)
labeled ×5commented ×1cross-referenced ×1

System prompt token consumption increased approximately 40-50% (~4,000 tokens) between v2.1.92 and v2.1.100 with zero changes to user configuration. This significantly reduces the usable context window for actual work.

Root Cause

System prompt token consumption increased approximately 40-50% (~4,000 tokens) between v2.1.92 and v2.1.100 with zero changes to user configuration. This significantly reduces the usable context window for actual work.

Fix Action

Fix / Workaround

  1. Install v2.1.92: npm install -g @anthropic-ai/[email protected]
  2. Run claude -p "Estimate the token count of your system prompt" in a project with CLAUDE.md, memory, skills, and hooks configured
  3. Upgrade to v2.1.100: npm install -g @anthropic-ai/[email protected]
  4. Run the same prompt again
  5. Compare estimates
  • OS: WSL2 (Linux 6.6.87.2-microsoft-standard-WSL2)
  • Claude Code: tested on v2.1.92 and v2.1.100
  • Currently downgraded to v2.1.92 as workaround
RAW_BUFFERClick to expand / collapse

Summary

System prompt token consumption increased approximately 40-50% (~4,000 tokens) between v2.1.92 and v2.1.100 with zero changes to user configuration. This significantly reduces the usable context window for actual work.

Reproduction

  1. Install v2.1.92: npm install -g @anthropic-ai/[email protected]
  2. Run claude -p "Estimate the token count of your system prompt" in a project with CLAUDE.md, memory, skills, and hooks configured
  3. Upgrade to v2.1.100: npm install -g @anthropic-ai/[email protected]
  4. Run the same prompt again
  5. Compare estimates

Observed results

VersionEstimated system prompt tokens
v2.1.92~8,000–10,000
v2.1.100~12,000–14,000

Identified causes

The following system prompt sections appear to have grown significantly:

  • Agent tool definition: Extensive usage examples, agent type catalog, isolation mode docs — substantially larger than v2.1.92
  • Bash tool definition: Now embeds full Git Safety Protocol, PR creation workflow, and commit workflow instructions inline
  • Deferred tools mechanism: New ToolSearch tool + listing of 20+ deferred tool names adds overhead that didn't exist in v2.1.92
  • system-reminder duplication: outputStyle reminder ("Explanatory output style is active...") is injected after every tool result, not once per turn. Task reminder also repeats frequently
  • # Output efficiency section removed: Previously existed in v2.1.92, absent in v2.1.100 — ironic given the bloat

Additional context

  • Output efficiency removal is concerning — the section that told Claude to be token-efficient was removed in the same version range that added thousands of tokens to the system prompt
  • The system-reminder repetition is especially wasteful — the same 1-2 line reminder injected 5-10 times per conversation turn adds up fast
  • Environment: WSL2 (Linux), project uses custom skills (17), hooks (9), memory files (13), agent definitions (4). None of these changed between versions.

Expected behavior

System prompt overhead should remain stable across minor versions, or at minimum not grow 40-50% without clear user-facing benefit. Repeated system-reminder injection should be deduplicated.

Environment

  • OS: WSL2 (Linux 6.6.87.2-microsoft-standard-WSL2)
  • Claude Code: tested on v2.1.92 and v2.1.100
  • Currently downgraded to v2.1.92 as workaround

extent analysis

TL;DR

Downgrade to v2.1.92 to immediately mitigate the 40-50% increase in system prompt token consumption until a fix is available for v2.1.100.

Guidance

  • Review the changes made between v2.1.92 and v2.1.100, focusing on the agent tool definition, Bash tool definition, deferred tools mechanism, and system-reminder duplication, to understand the root cause of the increased token consumption.
  • Consider submitting a feature request or bug report to address the removal of the # Output efficiency section and the unnecessary repetition of system-reminder messages.
  • Evaluate the custom skills, hooks, memory files, and agent definitions used in the project to ensure they are optimized for token efficiency.
  • Test the system prompt with a minimal configuration to isolate the impact of the custom components on token consumption.

Example

No specific code snippet is provided, as the issue is related to the overall system prompt configuration and version changes.

Notes

The increase in token consumption appears to be related to changes in the system prompt configuration and content between v2.1.92 and v2.1.100. Downgrading to v2.1.92 may not be a long-term solution, and a more permanent fix should be sought.

Recommendation

Apply the workaround by downgrading to v2.1.92, as it is the most straightforward way to immediately mitigate the issue until a fix is available for v2.1.100.

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…

FAQ

Expected behavior

System prompt overhead should remain stable across minor versions, or at minimum not grow 40-50% without clear user-facing benefit. Repeated system-reminder injection should be deduplicated.

#installation#tensor shape#autograd error#model save/load#optimization

Still need to ship something?

×6

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

Back to top recommendations

TRENDING