Opus, Sonnet, or opusplan? Answer 5 questions to find out

Yes - it's the exact AND-gate (plan, scope, spec, safety, history) from UsageCut's own model-router feasibility plan, the same checklist a non-intercepting coach hook would run on every turn. This wizard just runs it once, by hand, so you can see the logic before installing anything.

No Claude Code hook can set the next turn's model - the complete hook-output schema (verified against v2.1.191) has no model field on any event. The only way to rewrite it transparently is intercepting the API call, and that would also lose money: cache reads are 94% of billed tokens, and switching models forces an uncached re-read that erases the savings - modeled honestly, per-turn routing comes out to -122%.

Both are cache-safe, no-proxy mechanisms for different situations. A subagent runs in its own separate cache, so it's the answer when you're delegating a bounded step. opusplan switches on permission mode automatically - Opus in plan mode, Sonnet in execution - once you're executing an approved plan in your main session, with no extra config.

Because a downgrade only holds when every AND-gate condition is confirmed true - ambiguity resolves to Opus by design, since a wrong downgrade can poison the rest of a session. The wizard mirrors that: skipping a question fails it, same as answering no.

Yes. The scan and every fix are free - no card, no subscription, no signup. You only give an email if you want the optimization plan and one-command undo sent to your inbox.

The scan runs entirely on your machine. It never uploads your code, never reads your API key, and never sends your prompts or conversations anywhere. Only anonymous summary counts leave, and only if you choose to share them.

It reads your local setup and session history to find waste - idle MCP servers loaded into every session, an oversized CLAUDE.md re-sent on every request, duplicate file reads, and bloated tool output - then trims it losslessly, so each session carries less context and you hit your limit far less often.

ClockedCode is the curated, conflict-free Claude Code setup from the same maker. UsageCut makes your current setup leaner; ClockedCode makes it genuinely better - a set of hand-picked tools, specialist agents, and a tuned CLAUDE.md, installed in one paste.

Developers who use Claude Code daily and want a setup that is powerful out of the box instead of spending hours researching and wiring up plugins, agents, and MCP servers themselves.

A vetted, conflict-free bundle of hand-picked tools, specialist agents, and a tuned CLAUDE.md - everything installed together in one paste, with no setup archaeology.

Yes. ClockedCode is a one-time purchase with an instant download - no subscription and no recurring fees.

Yes. It installs alongside what you already have and is fully reversible. Run UsageCut first to clean your current setup, then add ClockedCode to level it up.