{"slug": "claude-code-already-shows-what-i-spent-i-optimized-the-spending", "title": "Claude Code already shows what I spent. I optimized the spending.", "summary": "A developer known as CraniusMaximus has released session-tax, an open-source tool that analyzes Claude Code session transcripts to identify idle skills and estimate their token overhead. The tool reads local transcript files without network calls and provides a free edition with basic totals, while a paid $19 version names dead skills and supports JSON output. The project is available on GitHub.", "body_md": "Claude Code already has `/usage`\n\n(same as `/cost`\n\n). On a Pro or Max plan it will show session cost estimates, plan bars, and a recent breakdown of usage by skill, subagent, plugin, and MCP server.\n\nBut, I wanted to optimize Claude, or have it optimize itself, rather than tell me. Skills I installed months ago were sitting idle, and contributing tokens each turn. `/usage`\n\nis good at showing what *ran* and what counted against the plan. It does not answer: what is installed, still loads, and has not fired once across the last stretch of my own transcripts?\n\nThat is what session-tax is for.\n\nIt reads your Claude Code session transcripts off disk on your machine. No network calls in the free script. Imports are `fs`\n\n, `path`\n\n, and `os`\n\n.\n\nAcross a window you choose (default 90 days) it reports:\n\nThe dollar line is a rough guide. It prices opening context using the cache-read / cache-write mix it sees in your transcripts, and it says so. On a subscription you mostly pay this in overhead.\n\nFree edition: the totals above. It will tell you *how many* skills look dead and what that listing tax adds up to. It does not print the names.\n\nPaid ($19, one seat): names the dead skills, points at cold servers (connected but almost never called), machine-readable `--json`\n\n, and `--home`\n\nso you can audit a different profile. Shop link lives in the GitHub README on purpose. Some forums quietly filter `*.pages.dev`\n\nURLs.\n\nRepo: [github.com/CraniusMaximus/claude-code-autonomy-pack](https://github.com/CraniusMaximus/claude-code-autonomy-pack)\n\nDoes it help? Is it a waste of time? Any inaccuracies?", "url": "https://wpnews.pro/news/claude-code-already-shows-what-i-spent-i-optimized-the-spending", "canonical_source": "https://dev.to/craniusmaximus/claude-code-already-shows-what-i-spent-i-wanted-what-never-fired-4cnn", "published_at": "2026-08-05 14:09:29+00:00", "updated_at": "2026-08-05 15:01:35.781787+00:00", "lang": "en", "topics": ["developer-tools", "ai-tools", "large-language-models"], "entities": ["Claude Code", "CraniusMaximus", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/claude-code-already-shows-what-i-spent-i-optimized-the-spending", "markdown": "https://wpnews.pro/news/claude-code-already-shows-what-i-spent-i-optimized-the-spending.md", "text": "https://wpnews.pro/news/claude-code-already-shows-what-i-spent-i-optimized-the-spending.txt", "jsonld": "https://wpnews.pro/news/claude-code-already-shows-what-i-spent-i-optimized-the-spending.jsonld"}}