### Preflight Checklist - [x] I have searched [existing issues](https://github.com/anthropics/claude-code/issues?q=is%3Aissue%20state%3Aopen%20label%3Abug) and this hasn't been reported yet - [x] This is a single bug report (please file separate reports for different bugs) - [x] I am using the latest version of Claude Code ### What's Wrong? Excessive token usage for trivial prompts in Claude Code CLI. In a completely clean environment (empty folder, no repository, no CLAUDE.md), very simple

[BUG] Excessive token usage (~20k–30k tokens) for trivial prompts in Claude Code CLI

Status Closed — not planned

Reported on v2.1.119

Maintainer reply None cached

Activity 13 comments · opened Apr 24, 2026 · closed Jun 10, 2026

Preflight Checklist

[x] I have searched existing issues and this hasn't been reported yet
[x] This is a single bug report (please file separate reports for different bugs)
[x] I am using the latest version of Claude Code

What's Wrong?

Excessive token usage for trivial prompts in Claude Code CLI.

In a completely clean environment (empty folder, no repository, no CLAUDE.md), very simple prompts are consuming tens of thousands of tokens.

Examples:

Prompt: "hi" → ~31,000 tokens
Prompt: "what colour is the sky?" → ~19,000 tokens

This occurs consistently even in a fresh session using:

claude --verbose
different models (sonnet-4.6, haiku-4.5)
different effort levels (low/medium)

Expected behavior:
Simple prompts should use ~50–200 tokens.

Actual behavior:
There appears to be a large fixed token overhead (~20k–30k tokens) per request, even with no files or tools involved.

Impact:
This significantly increases cost and makes the CLI impractical for lightweight usage.

Additional notes:

Issue reproducible in empty directory (C:\claude-clean)
No repo, no agents, no commands executed
ccusage shows very high cache read tokens for these simple prompts

This suggests excessive system prompt/context injection or a context/caching issue where tokens are not being trimmed properly.

What Should Happen?

For trivial prompts (e.g. "hi" or "what colour is the sky?"), Claude Code should use a minimal number of tokens (~50–200).

There should not be a large fixed baseline token overhead per request in a clean environment with no files, tools, or context.

Token usage should scale with the size and complexity of the prompt.

Error Messages/Logs

No explicit error messages.

Observed via:
- Claude Code verbose mode token display (~19k–31k tokens per trivial prompt)
- ccusage showing very high cache read tokens

Example:
Prompt: "hi"
Observed tokens: ~31,000

Steps to Reproduce

Create an empty folder (e.g. C:\claude-clean)
Open terminal and navigate to the folder
Run: claude --verbose
Enter: "hi"
Observe token usage in the top-right (~30k tokens)

Repeat with:

"what colour is the sky?"
different models (haiku, sonnet)
different effort levels

Result is consistent across all tests.

Claude Model

Not sure / Multiple models

Is this a regression?

Yes, this worked in a previous version

Last Working Version

Earlier versions (and API/chat usage) showed ~50–200 tokens for trivial prompts. Exact CLI version unknown.

Claude Code Version

2.1.119 (Claude Code)

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

PowerShell

Additional Information

Issue occurs in completely empty directory with no repository or CLAUDE.md
No tools or commands are executed during tests
Token usage is consistently high (~20k–30k) regardless of prompt size
ccusage shows extremely high cache read tokens for simple prompts
Suggests large fixed system prompt or context not being trimmed properly

This makes Claude Code significantly more expensive for simple interactions compared to expected usage.

View original on GitHub ↗

12 Comments

github-actions[bot] · 4 months ago

Found 3 possible duplicate issues:

This issue will be automatically closed as a duplicate in 3 days.

If your issue is a duplicate, please close it and 👍 the existing issue instead
To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

dripcreate · 4 months ago

👎 This appears related but not an exact duplicate.

My reproduction shows significantly higher baseline token usage:

Clean empty folder (no repo, no CLAUDE.md)
Prompt "hi" → ~31k tokens
Prompt "what colour is the sky?" → ~19k tokens
Reproduced consistently on Claude Code 2.1.119
Occurs across models (haiku, sonnet) and effort levels

This suggests a larger fixed overhead than #51809 (~6–8k tokens).

#52413 seems closest, but this issue highlights the baseline cost in a completely clean environment.

junaidtitan · 4 months ago

20-30K for "hi" is painful. Most of that bloat accumulates from stale tool results, metadata, and old attachments that get re-sent every turn. Cozempic's strategies (stale-reads, tool-result-age, metadata-strip) strip that accumulated bloat so each API call sends only what matters.

pipx install cozempic && cozempic treat — https://github.com/Ruya-AI/cozempic

dripcreate · 4 months ago

Still reproducible on Claude Code 2.1.123, Windows 11.
Confirmed clean environment: no MCP servers, no user skills, ~16 KB auto-memory.
Symptom unchanged after initial report. Likely related to #54410 (medium-effort regression) and #53925.

dripcreate · 4 months ago

<html>
<body>
<hr style="font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;"><p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Update — still reproducing on Claude Code 2.1.123, Windows 11 (8 days after original report)<p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Re-ran the original test in a fresh empty directory. No MCP servers, no user skills, no project context, no <code style="font-family: monospace; color: rgb(208, 208, 208); background-color: rgb(60, 60, 60); padding: 2px 4px; border-radius: 3px; word-break: break-word; font-size: 0.9em;">CLAUDE.md</code>, ~16 KB of auto-memory total. Pristine baseline, same as the original report.
Model + effort | Original (v2.1.119) | Today (v2.1.123)
-- | -- | --
Haiku 4.5, low effort | 31,642 tokens | 31,877 tokens
Sonnet 4.6, medium effort | 19,122 tokens | —
Opus 4.7, medium effort | — | 26,575 tokens (new datapoint)

<p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Prompt in every case: "what colour is the sky?"<p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Two observations:<ol style="padding-inline-start: 2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;"><li>Haiku-low is essentially unchanged across 8 days and 4 patch versions (~31k tokens for a one-line prompt in an empty directory).</li><li>Opus 4.7 medium effort uses fewer baseline tokens (26,575) than Haiku 4.5 low effort (31,877) for an identical prompt. Since the user-content is identical, this strongly suggests the inflated baseline is in CLI-side system prompt / context construction, not in model behaviour.</li></ol><p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Effective impact: a 5-hour Claude Max session is delivering noticeably less work than 7 days ago. The same routine tasks now consume materially more of the session quota.<p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Likely related (please link/cluster as appropriate):<ul style="padding-inline-start: 2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; white-space: normal; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;"><li>#53925 — Excessive token usage on small prompts (macOS)</li><li>#54410 — Unexpected token consumption increase with <code style="font-family: monospace; color: rgb(208, 208, 208); background-color: rgb(60, 60, 60); padding: 2px 4px; border-radius: 3px; word-break: break-word; font-size: 0.9em;">medium</code> effort after recent update</li><li>#54596 — Token waste in routines/MCP (different surface, but plausibly same root)</li></ul><p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">This setup has no MCP and no skills, so the issue is reproducible without either of those subsystems being involved.<p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Happy to provide further reproductions, version-by-version comparisons, or a diagnostic dump if useful. Screenshots from both today's runs are attached.
</body>
</html>

dripcreate · 4 months ago

<html>
<body>
<p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">Update — referencing your 2026-04-23 post-mortem<p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">I've read the <a href="https://www.anthropic.com/engineering/april-23-postmortem" target="_blank" rel="noopener noreferrer" style="color: rgb(77, 170, 252); text-decoration: rgb(77, 170, 252);">post-mortem</a> covering the thinking-block clearing bug fixed on 2026-04-10. Appreciated the transparency and the quota reset.<p style="white-space: pre-wrap; margin-top: 0.1em; margin-bottom: 0.2em; color: rgb(204, 204, 204); font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif; font-size: 13px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: rgb(24, 24, 24); text-decoration-thickness: initial; text-decoration-style: initial; text-decoration-color: initial;">I'm still seeing high baseline tokens on Claude Code 2.1.123 / Windows 11, post-fix:
Test (clean empty dir, no MCP, no skills, no project) | Tokens
-- | --
Haiku 4.5, low effort, "what colour is the sky?" | 31,877
Opus 4.7, medium effort, same prompt | 26,575

I've read the post-mortem covering the thinking-block clearing bug fixed on 2026-04-10. Appreciated the transparency and the quota reset.

I'm still seeing high baseline tokens on Claude Code 2.1.123 / Windows 11, post-fix:

Test (clean empty dir, no MCP, no skills, no project) Tokens
Haiku 4.5, low effort, "what colour is the sky?" 31,877
Opus 4.7, medium effort, same prompt 26,575
Two questions to clarify:

The post-mortem mentions Sonnet 4.6 and Opus 4.6 were affected. Were Haiku 4.5 and Opus 4.7 also touched, or are these models supposed to be unaffected?
The thinking-block bug specifically caused cache misses on subsequent turns. My reproduction is on the first turn of a fresh session — would that even be affected by the cached-thinking-block code path? If not, my symptom is something separate.
If useful, I can provide a mitmproxy capture of the actual POST + response usage JSON breaking down what's cache_creation_input_tokens vs cache_read_input_tokens vs plain input_tokens on a clean first turn.

Cross-references: #41930 (parent), #38335, #53925, #54410, #54596.

daliovic · 3 months ago

I am also so confused about this. It's been a while and I never took the time to investigate what on earth is going on. But this basically the exact same what I've been experiencing. I tried different models and different versions ~~(going back to v 2.0.64)~~ with no luck.
Edit: actually it seems to be reproduceable after v 2.1.100.

dripcreate · 3 months ago

Update — debug log reveals the per-prompt cost is actually multiple separate API calls

Ran with ANTHROPIC_LOG=debug claude --debug --verbose on 2.1.123 (Windows 11), clean empty directory, single prompt "what colour is the sky?". Debug log shows the CLI fires three separate API calls per user-visible exchange:

| Source | Model | max_tokens | When |
| --- | --- | --- | --- |
| quota_check | Haiku 4.5 | 1 | Boot |
| generate_session_title | Haiku 4.5 | 32000 | First prompt |
| repl_main_thread | Opus 4.7 (default) | 64000 | First prompt |

The CLI displays 26,556 tokens for this single user-visible exchange, but that figure is the sum across all three calls, not one request's overhead. The session-title generator alone uses max_tokens: 32000 for a title that's typically a few words — appears to be a budget mismatch.

Also visible in the response headers: anthropic-ratelimit-unified-5h-utilization: 0.31 was already at 31% on a fresh session — i.e. the boot itself contributed measurably to the 5-hour window before any user prompt was processed.

Two clarifying questions:

Is max_tokens: 32000 for generate_session_title intentional? The title visibly returned is a single short sentence; that suggests max_tokens could be ~50–200 instead.
Is the displayed token count in --verbose supposed to be the per-prompt cost or the cumulative session cost? If the latter, the displayed number is essentially correct but misleading; if the former, the aggregation across the three calls is a UI bug.

Also confirming this is now reproduced by @daliovic across multiple versions back to 2.0.64, which suggests the inflated baseline isn't tied to the specific 2.1.110–2.1.117 caching regression covered by the April 23 post-mortem — both of us are seeing this on first turn of a fresh session, which the post-mortem's "thinking blocks dropped on follow-up turns" mechanism wouldn't cause.

Cross-references: #41930 (parent), #38335, #53925, #54410, #54596.

dripcreate · 3 months ago

Update — 2.1.126 doesn't change the cold-cache reading on Windows

Tested same trivial prompt across machines today, all on Max OAuth, Opus 4.7, medium effort, fresh empty directory each time, prompt: "what colour is the sky?".

| Setup | Tokens displayed |
| --- | --- |
| Laptop, Windows, 2.1.123 | 26,793 |
| Laptop, Windows, 2.1.126 (post-update) | 26,821 |
| VPS, Linux, 2.1.126 (recent activity) | 22,147 |

The version bump 2.1.123 → 2.1.126 produced no measurable change on the same Windows laptop. The lower VPS reading appears to be cache-state difference (recent activity = warmer cache), not a CLI fix — the prompt cache is device-specific even on the same Max OAuth identity.

Two related observations from /usage and /stats:

The /usage per-model breakdown reveals the displayed token count conflates four classes: input, output, cache_read, and cache_write. For the same trivial prompt the underlying breakdown is roughly 6 input + ~40 output + ~0–19k cache_read + ~7–26k cache_write depending on cache state. Cache reads cost 0.10× input rate; cache writes cost 1.25×. So the displayed 26,821 tokens actually represents only ~$0.06–0.17 in real billed cost depending on cache hit rate, not ~26k tokens of full-rate input.

The /stats view appears to exclude cache tokens entirely from the headline figure. My account shows Opus 4.7: In: 24 · Out: 432 over the last 7 days despite sending multiple 26k-displayed prompts. Implies Stats is reporting only plain input + output, treating cache reads/writes as separately accounted (consistent with how the pricing actually works).

The mismatch between --verbose (shows everything summed together, alarming 26k+) and /stats (shows just billed input/output, modest) is what drives the felt-cost perception in this issue cluster. A UX fix on either end — either /stats showing cache transparency too, or --verbose excluding cache tokens to match /stats — would largely resolve the reporting around this specific bug surface.

The underlying cold-cache fresh-session cost itself appears stable across 2.1.119 → 2.1.126 (~26k tokens displayed regardless of version). So it's not a regression-still-present so much as a UX-reporting-issue that has been making a stable-but-large baseline feel worse than it is.

Cross-references: #41930, #38335, #53925, #54410, #54596.

dripcreate · 3 months ago

Update — version-by-version comparison reveals residual issue post April 10 fix

Tested the same trivial prompt across multiple Claude Code versions on the same Max OAuth account, with /clear between each test to ensure fresh state. Same Windows machine, same auth, same network conditions.

| Claude Code version | Model | Token count |
| --- | --- | --- |
| 2.1.90 | Opus 4.6 (1M context) | 15,982 |
| 2.1.101 | Opus 4.6 (1M context) | 16,887 |
| 2.1.116 | Opus 4.7 (1M context) | 26,576 |
| 2.1.123 | Opus 4.7 medium | 26,793 |
| 2.1.126 | Opus 4.7 medium | 26,821 |
| 2.1.128 | Opus 4.7 medium | ~26,800 |

Two genuinely interesting findings

1. There's a clear inflection point between 2.1.101 → 2.1.116 — token count jumped from ~17k to ~27k for the same trivial prompt. That's roughly a 60% increase across that version range, which corresponds to the cache regression period (Mar 26 → Apr 10).

2. The April 10 fix appears to have stabilised the regression but NOT restored the pre-March 26 baseline. Post-fix versions (2.1.123, 2.1.126, 2.1.128) still show ~26k tokens for trivial prompts — the same as 2.1.116 (during the bug period). Pre-bug versions (2.1.90, 2.1.101) showed ~16k.

This leaves approximately 10,000 tokens of residual overhead per fresh-session call that wasn't restored by the April 10 fix.

Connection to community-documented residual bugs

The community analysis at Claude diagnosed its own cache bug: a six-month timeline describes residual cache-invalidation mechanisms that persist post-fix:

Resume Trap — --resume / --continue invalidates cached prefix on first turn
Telemetry-disabled trap — silently halves cache lifetime
Billing-word trap — certain conversation content triggers cache invalidation

I have telemetry enabled and don't use --resume for the test runs above, so those traps don't account for my readings. The residual ~10k overhead appears to be present on the simplest possible code path.

Discussion: Hacker News thread.

Two clarifying questions

Was the April 10 fix scope-limited? Specifically, did it address the "thinking blocks dropped on follow-up turns" mechanism described in the post-mortem but leave other cache-invalidation mechanisms in place?

Is the increase from 2.1.101's ~17k to 2.1.116's ~27k baseline considered a regression worth restoring, or is the post-March 26 ~26k count now treated as expected baseline behaviour for Claude Code 2.1.x?

Cross-references: #41930 (parent), #38335, #53925, #54410, #54596.

eunseokOh · 3 months ago

Adding a data point: this manifests on Python claude-agent-sdk 0.1.80 + bundled CLI 2.1.138 with multi-turn chat using resume=<sdkSessionId>. Trivial prompts show consistent ~30K cache_write per turn, ~$0.13 floor cost.

Root cause confirmed via proxy capture (see my comment on #43657): tools and system prefixes are byte-identical across turns, but the messages-array normalization pipeline still produces fresh cache_creation each turn. This is the same family as #43657 / #44045 / #49585.

github-actions[bot] · 2 months ago

Closing for now — inactive for too long. Please open a new issue if this is still relevant.

Showing cached comments. Read the full discussion on GitHub ↗

[BUG] Excessive token usage (~20k–30k tokens) for trivial prompts in Claude Code CLI

Preflight Checklist

What's Wrong?

What Should Happen?

Error Messages/Logs

Steps to Reproduce

Claude Model

Is this a regression?

Last Working Version

Claude Code Version

Platform

Operating System

Terminal/Shell

Additional Information

12 Comments

Update — version-by-version comparison reveals residual issue post April 10 fix

Two genuinely interesting findings

Connection to community-documented residual bugs

Two clarifying questions

Related Claude Code issues

Browse by topic