optimize

Tune this Claude Code setup for token use. Focus on $ARGUMENTS if given.

Before recommending a setting you are not sure of, read its page in Claude Code's current docs: every page is Markdown at https://code.claude.com/docs/en/<page>.md (index: https://code.claude.com/docs/llms.txt; settings in settings-reference.md, variables in env-vars.md, costs in costs.md, caching in prompt-caching.md). The release changes often, so prefer that to memory or a mirror.

The tokendoctor tools wait behind ToolSearch: load mcp__tokendoctor__metrics, mcp__tokendoctor__settings, mcp__tokendoctor__config_list, mcp__tokendoctor__config_set and mcp__tokendoctor__set_setting in one ToolSearch call first.

1. Measure. Call metrics (session context, rate limits, cost, the largest context categories, daily totals, audit findings). For the longer view run tokendoctor-sessions --json --days 30.
2. See what can change. Call settings (every setting tokendoctor may change, set or not, with its current value and whether a change applies live) and config_list (the /config rows).
3. Propose. Pick at most five changes, largest saving first. For each give: the setting, the current and new value, the evidence from step 1 in one sentence, the trade-off, and whether it applies now or at the next session. Costs are dollars at API list prices, which on a plan are not what the plan's limits count: speak in shares first. Do not propose a change the numbers do not support. The window. autoCompactWindow sets where Claude Code compacts (for example 400000 on a 1M model). Propose a smaller one when much of the cost is spent with a large context (the late-compaction finding, a high compactAt): every request re-reads the whole context, so a smaller window is a direct saving, at the price of compacting more often. The slide. tokendoctor.slide: true makes those compactions elide old tool outputs into short pointers instead of summarizing: no summary pause, and every prompt, answer and decision stays word for word. It is not a saving: measured on 60-file runs it costs the same as a summary (within 2% on Haiku 5.5 and Sonnet 5.5), and a recall test found no detail the summary lost. Offer it only as a separate choice, to someone who says summaries lose what they need, and say that a model may now and then read an elided file again. If the audit has slide-blocked-by-guard, the slide will not run on this login until tokendoctor-org-install is run (one sudo command): say so before turning it on. How tools are used. The usage part of tokendoctor-sessions --json shows which tools fill the context, Bash calls that only printed a file, the files read most and how large subagent runs grow. Judge from it yourself. bashOutputMaxChars caps one Bash output; with the slide on, a file printed through Bash that was read or changed again later is the first thing dropped. What a setting cannot fix (how subagents are briefed and sized, what they report back), propose as a few lines for the project's memory or CLAUDE.md and show them; the person writes them, or asks you to. Leave tokendoctor.slideTo at its default (25) unless the person asks: a higher one slides more often, and every slide re-sends the context once.
4. Ask. Use AskUserQuestion (multiSelect) to let the person pick which changes to apply.
5. Apply each picked change with config_set (a /config row, live) or set_setting (a settings file, with a backup). Each call asks the person again; a refusal is final for that change.
6. Report what changed, what needs a new session (model, effortLevel and every env.* value), and suggest running tokendoctor-sessions --by day in a few days to compare. Say that /tokendoctor shows these settings and /tokendoctor <name> <value> changes one with no model call.

Never change hooks, permissions or anything outside the settings list. Never write files with other tools.