Our Claude costs have skyrocketed as frontier models get more expensive and subsidies wind down.
We've been using CC-Ledger to track costs and categorize token spend, so we can better control our usage.
Looking to soon add per-user and per-model budgets. Open to feedback and ideas!
I use Claude Code for deep research, both personal and at work. It was difficult to package these learnings in a format that can be shared with others and also re-used in future sessions.
CC-Wiki is a skill + Quartz-based template that looks at local .claude sessions and builds a rigorous arXiv-like knowledge base, so no context goes to waste.
I use Claude Code for deep research, both personal and at work. It was difficult to package these learnings in a format that can be shared with others and also re-used in future sessions.
CC-Wiki is a skill + Quartz-based template that looks at local .claude sessions and builds a rigorous arXiv-like knowledge base, so no context goes to waste.
I use Claude Code for deep research, both personal and at work. It was difficult to package these learnings in a format that can be shared with others and also re-used in future sessions.
CC-Wiki is a skill + Quartz-based template that looks at local .claude sessions and builds a rigorous arXiv-like knowledge base, so no context goes to waste.
I use Claude Code for deep research, both personal and at work. It was difficult to package these learnings in a format that can be shared with others and also re-used in future sessions.
CC-Wiki is a skill + Quartz-based template that looks at local .claude sessions and builds a rigorous arXiv-like knowledge base, so no context goes to waste.
If you believe Claude will manipulate its own findings in the report (i.e. via the skill), there's also a deterministic script in cc-canary that generates a report without using Claude's input.
Seems to be the case that many users find Claude Code to be the most capable but less trustworthy than its competitors. We're hopeful that tools like cc-canary help users gain that trust back so they can continue to use the best tools on the market.
Looking to soon add per-user and per-model budgets. Open to feedback and ideas!