Tokendoctor 让 Claude Code 成本最高降 38%

原标题:Tokendoctor – the same Claude Code for up to 38% less
58AI 研判分

Tokendoctor 是一款本地运行的 Claude Code 成本诊断与优化工具,通过回放用户真实会话定位超额开销并给出可撤销的修复。作者基于六周真实使用测得主线程单请求成本下降 38%,单请求上下文从 412K 降至 219K,但效果高度依赖会话长度与模型配置。

报道正文

本文目录2 个章节

tokendoctor

The same Claude Code for up to 38% less

See what your Claude Code use overpays, fix it, undo it any time. Runs on your machine.

Website · Install · Changelog

Measured on its author's six weeks of real use
Main-thread cost per request at API list prices, the month before against the week after a 400K window and Sonnet for subagents−38%
Context per request412K → 219K
The same sessions replayed at a 400K window: only the window changed−33% of the main thread, −20% of all spend
The slide against a summary, the same day of work (bench)−19% cost, −33% time
A week of work in bench (27 steps), Claude Code as it ships against every fix applied and the slide−11 to −21% cost (medians of 2 and 3 runs; single runs −40% to +17%), all tests pass

There is no one pill. If your sessions rarely pass 400K tokens, the window changes nothing for you; a summary that lands just before you finish can cost more than it saves; your models, effort and work all move the number. So tokendoctor shows you yours first: /tokendoctor:sessions replays your own sessions at smaller windows before anything changes.

<table> <tr> <td width="25%" valign="top"> <strong>See</strong><br> <code>/tokendoctor:sessions</code> replays your own sessions at smaller windows and says what each would have saved, then where the tokens went. </td> <td width="25%" valign="top"> <strong>Fix</strong><br> <code>/tokendoctor:optimize</code> runs 38 checks against the docs and applies the changes you pick, each shown as a diff first. </td> <td width="25%" valign="top"> <strong>Slide</strong><br> <code>/tokendoctor slide on</code>: where Claude Code would summarize, old tool outputs go instead. No pause, the conversation stays word for word. </td> <td width="25%" valign="top"> <strong>Undo</strong><br> <code>/tokendoctor undo</code> lists every change tokendoctor made and puts any one back. No model call, no tokens. </td> </tr> </table>

/tokendoctor : every token by day, model, effort, main thread and each subagent, context size and project. One local file; this is the author's own.

Install

BASH
claude plugin marketplace add localixai/tokendoctor
claude plugin install tokendoctor@tokendoctor

Update with claude plugin marketplace update tokendoctor and claude plugin update tokendoctor@tokendoctor, then restart Claude Code. To try it without installing, clone the repository and run claude --plugin-dir /path/to/tokendoctor.

Use

CommandWhat it does
/tokendoctor:sessions [days]What a smaller window would have saved you (your sessions replayed), then where tokens went over the last 30 days (or days), with findings. Read-only.
/tokendoctor:auditSetting checks by severity, each linked to the docs, a read of your memory and CLAUDE.md, then the usage dashboard. Read-only.
/tokendoctor:dashboard [days]Builds and opens a local dashboard of every session on this machine: spend by day, kind of token, model, reasoning effort, main thread and each subagent type, context size, project and hour, with filters. One HTML file, no network.
/tokendoctor:optimize [focus]Proposes up to five changes from your numbers and applies the ones you pick.
/tokendoctor [name] [value]Shows the main settings, explains one or changes it. No model call, no tokens.
/tokendoctor fix <finding-id>Applies one audit fix after showing it, with a backup of the file.
/tokendoctor undo [n]Lists the changes tokendoctor made, newest first, and puts change n back.

/tokendoctor is answered by the plugin itself, so it costs nothing. Tab completes the names (window, slide, cache, effort, model, subagents, and /tokendoctor all for the rest) and their values; /tokendoctor window 400k applies as typed, /tokendoctor window reset goes back to the default, --project or --local writes there instead of your user settings. A model name must be an alias (opus, sonnet, haiku) or a claude-… id.

optimize changes only settings on the tunable list and /config rows. Every change opens a dialog that shows it and runs only on Apply; with no one to ask, as in a -p run, nothing changes. Hooks and permissions are never on the list.

<details> <summary><strong>From a shell</strong></summary>

The plugin's bin/ directory is on the Bash tool's PATH while it is enabled:

BASH
tokendoctor-audit [--project <dir>] [--json]
tokendoctor-sessions [--days <n>] [--project <dir>] [--by day|week] [--json]
tokendoctor-set --list | <key> <value>|--unset [--scope user|project|local] [--write]
tokendoctor-apply <finding-id> [--scope user|project|local] [--project <dir>] [--write]
tokendoctor-undo [--json] | <n> [--write]
tokendoctor-replay [--days <n>] [--window 200k,400k] [--json]   # what a smaller window would have saved
tokendoctor-org-install [--write] [--uninstall]                # the slide under a Team/Enterprise login (see below)
tokendoctor-selfcheck [--log <file>] [--json]                  # what really loaded, from a debug log (one small Haiku request, or a log you have)
</details> <details> <summary><strong>What it costs to keep installed</strong></summary>

The skills are user-invoked only (disable-model-invocation). claude plugin details tokendoctor@tokendoctor estimates about 235 tokens of always-on cost for the five of them. The plugin has no MCP server. Its hooks module adds the optimize tools (mcp__tokendoctor__*) behind ToolSearch, so only their names are listed until /tokendoctor:optimize loads them. /tokendoctor and the slide run in the hooks module too, with no model call, so they add no tokens. Its one command hook runs tokendoctor-record in the background when a session starts. The hook is async and prints nothing, so it adds no tokens. It appends each finished day's totals to ~/.claude/tokendoctor/history.jsonl, so the trend outlives Claude Code's transcript cleanup.

</details> <details> <summary><strong>The 38 setting checks</strong></summary>

Errors are settings that are wrong or ignored, warnings are likely to cost real money, and info is worth a look. Rules that depend on a Claude Code release are skipped on older versions.

| Finding | Severity | What it catches | | ---

(注:更多技术实现细节与完整 API 文档请查阅原项目 README)