model-escalator
by Alessandro Tozzi · ★ 2 · updated 16 days ago
0
Run cheap models in parallel and escalate only when they get stuck: nudge, senior consult, hot model swap. Measures savings and learns the right model per task.
Install
/plugin marketplace add atozzi-dev/model-escalator/plugin install model-escalator@model-escalatorThen run /reload-plugins or start a new session. Requires Claude Code 2.1.287+.
What it hooks into
From an automated scan with claude plugin validate, not a security review. Mods run with your permissions; read the code before installing.
- Events
session.startcommand.runui.renderui.closeagent.spawntool.callturn.stepturn.completesession.end- API calls
$.clock.after$.clock.every$.clock.now$.clock.sleep$.command.register$.env.get$.model.classify$.model.complete$.process.run$.session.append$.session.surfaces$.session.usage$.state.get$.state.set$.store.delete$.store.get$.store.set$.tool.register$.ui.close$.ui.invalidate$.ui.log$.ui.open$.ui.panes$.ui.resolve$.ui.status$.ui.toast- Draws
Pane- Can see
subagent spawnsmcp__model-escalator__ask_for_help callsevery tool call- Reach
- level 2 of 3 runs processesdrives Claudereads env varsreads mod statepersists statedraws
Origin
- How it got here
- Automated scan of public GitHub repos, via the CC0 dataset awesome-claude-code-mods (scan of ).
- Repository
- github.com/atozzi-dev/model-escalator
- Path in repo
plugin- Source commit
cc5d526the exact code the scan read- Author
- Alessandro Tozzi @atozzi-dev
- License
- MIT
- First published
- Last pushed
- First listed here
Name and description come from the mod's own manifest. We link to the code; we don't host it, and it stays under its author's license.