[bug] [/cost] Current session 101% used

Bug Description
extra percent 101% used - should that say 100% ?

Settings Status Config Usage Stats

Session

Total cost: $48.03
Total duration (API): 55m 2s
Total duration (wall): 21h 12m 29s
Total code changes: 1693 lines added, 46 lines removed
Usage by model:
claude-sonnet-5: 246 input, 134.5k output, 32.5m cache read, 333.8k cache write ($9.18)
claude-fable-5-1: 488 input, 58.0k output, 7.2m cache read, 796.5k cache write ($20.65)
claude-opus-5: 98 input, 63.0k output, 23.5m cache read, 488.1k cache write ($18.20)
Prompt cache (main): 191 requests · 98% of input tokens from cache · 3 misses (last 32m 48s ago — likely cause: model changed, beta headers changed, effort changed, earlier messages changed, 1.1m tokens re-cached) · warm (1h TTL, last activity 6m 8s ago)

Plugin skill-listing footprint
What each plugin's skill descriptions add to the system prompt (cached input after the first turn). Agents and MCP tools not yet counted.

consciousness 20 skills · ~759 tok/turn
stripe 2 skills · ~59 tok/turn
feature-dev 1 skill · ~35 tok/turn
code-review 1 skill · ~18 tok/turn

Total ~871 tok/turn

Current session
██████████████████████████████████████████████████ 101% used
Resets 2am (Europe/London)

Current week (all models)
██████████ 20% used
Resets Sep 8, 9am (Europe/London)
+50% weekly limits promo through Sep 13 · clau.de/cc-50-promo

What's contributing to your limits usage?
Approximate, based on local sessions on this machine — does not include other devices or claude.ai

Last 24h · these are independent characteristics of your usage, not a breakdown

95% of your usage was at >150k context
Longer sessions are more expensive even when cached. /compact mid-task, /clear when switching to new tasks.

91% of your usage was while 4+ sessions ran in parallel
All sessions share one limit. If you don't need them all at once, queueing uses it more evenly.

18% of your usage came from subagent-heavy sessions
Each subagent runs its own requests. Be deliberate about spawning them — and consider configuring a cheaper model for simpler subagents.

13% of your usage came from the plugin "consciousness"
Review what this plugin contributes — its agents, skills, and MCP tools all count toward your limit.

Skills % of usage
/consciousness:on 9%
/bus-task 6%
/ucando 4%
/president 4%
/superpowers:brainstorming 3%

Environment Info

• Platform: linux
• Terminal: tmux
• Version: 2.1.260
• Feedback ID: 18dc34bd-4ecd-4bb6-89b4-252e8a0a2a52

Errors

[]