GitHub issue #103376 in anthropics/claude-code, opened 2026-10-19 by EthanRCT, records a report that on Claude Max (20x), the weekly all-models meter went from 0% to 54% in the first 22 hours after the weekly reset, while the reporter's Claude Code token volume in those 22 hours was nearly identical to the same 22 hours of the previous week, when about 6 times that volume moved the meter only to 60%, measured from local transcripts on Claude Code 2.1.299 on macOS 26.6.2.
Verbatim Excerpts from Cited Records
“On Claude Max (20x), the weekly "all models" meter went from 0% to 54% in the first 22 hours after the weekly reset. My Claude Code token volume in those 22 hours was nearly identical to the same 22 hours of the previous week. The previous week, about 6 times that volume moved the meter only to 60%.”
·
anthropics/claude-code (issue 103376 opening body, What's Wrong section)
·
2026-10-19T06:30:55Z
·GitHub Issue ↗
“| This week, first 22h (Oct 18 05:00 to Oct 19 03:16) | 902 | 343K | 7.47M | 299.4M | **0% to 54%** |”
·
anthropics/claude-code (issue 103376 opening body, What's Wrong section)
·
2026-10-19T06:30:55Z
·GitHub Issue ↗
“The only other Claude Code activity on the account is one Remote Control session on my second computer. Its event log shows *less* use this Sunday than the previous Sunday (212 calls and 44.9M cache read, against 697 calls and 120.6M cache read). It started returning `usage_limit_reached` late Sunday, after the shared limit was already consumed.”
·
anthropics/claude-code (issue 103376 opening body, What's Wrong section)
·
2026-10-19T06:30:55Z
·GitHub Issue ↗
“The same token volume should consume about the same share of the weekly limit from week to week. At the prior week's rate, everything I can measure this week should come to roughly 9 to 13%, not 54%.”
·
anthropics/claude-code (issue 103376 opening body, What Should Happen section)
·
2026-10-19T06:30:55Z
·GitHub Issue ↗
Counter-record: Issue remains open with 16 comments as of 2026-11-03; no maintainer response appears in the surveyed thread. Several other reporters corroborated the pattern with the same transcript method: justanotheruseer on 2026-10-19 measured about 30% fewer weighted tokens per 1% of the weekly meter since Oct 16, kreaddis-julien on 2026-10-20 and consolelogreece on 2026-10-25 reported similar drops, and further Max 20x users reported fast drain into late October. One commenter, philogical, corrected his own 2026-10-31 data point on 2026-11-03, showing his apparent 3x drop came from uncounted usage on other surfaces rather than a metering change; that correction covers only his own measurements, not the original report. No maintainer fix or closure decision appears in the surveyed thread. The claim documents only the original report, not a verified current state.
Falsification probe: If issue 103376 is deleted without archive, if the author edits the opening body so the quoted sentences no longer match verbatim, or if the author posts a retraction of the report, this claim drops to Withdrawn.
Audit verification: Verified 100% continuous verbatim substring against official GitHub REST API by
scripts/verify_claim_verbatim.py.