model-router 0.6.0
BenAI copy of claude-code-templates' Jev Model Router (MIT), changed to use Haiku in place of Jev. Haiku reads each subagent task at agent.spawn and answers in JSON with a tier and a confidence from 0 to 1; a task moves to a cheaper model only when that confidence is at least minDowngradeConfiden...
claude-code-templates, changes by BenAI
0 on michaelzwiener/claude-mods
Install
/plugin marketplace add michaelzwiener/claude-mods /plugin install model-router@token-saving-mods
Run both lines inside Claude Code.
Hooks into
- Prompt
- Status line
- Slash commands
Also in michaelzwiener/claude-mods
-
helper-desk
0.4.1
Helper Desk: a purple task progress bar above the prompt that moves as each to-do item is done, and a side pane with one live card per subagent
Ben AI in Panes, updated
0
-
chat-inventory
0.2.0
A side pane, In this chat, that lists the to-do list, connectors, context files and skills this chat used
Ben AI in Panes, updated
0
-
input-router
0.3.1
Big files and connector results are read by Haiku first; Claude gets short notes and a path to the full thing. A side pane shows each hand-off to Haiku live. /input-router full lets the next one through whole
Ben AI in Panes, updated
0
-
effort-optimizer
0.1.0
Reads each prompt, picks the effort level it needs with Ben's four-question framework, and offers Switch to that level, or sets it by itself in auto mode
Ben AI in Prompt, updated
0
-
cache-clock
0.3.0
Counts down until the chat's prompt cache goes cold, above the prompt. When a big chat goes cold, offers a handoff to a fresh chat. Keep warm pings the cache in the background so it does not go cold
Ben AI in Prompt, updated
0
-
handoff
0.1.0
At 250k tokens, offers Refresh: writes a handoff of the whole chat, shows the steps with progress bars, then copies it or starts a new chat with it. Logs every run to ~/.claude/handoffs/handoff.log and saves a draft first
Ben AI in Usage & cost, updated
0
-
research-router
0.3.0
Keeps web research out of the main chat: Haiku shortens Claude's own big search results, and /research-router has a cheap worker or subagents read real pages and give Claude a short brief with sources
Ben AI in Panes, updated
0
-
efficient-browser-use
0.2.0
Cheaper browser tasks: shrinks every screenshot Claude takes while it drives a browser, or has Haiku describe it in words. /efficient-browser full lets one full-size screenshot through
Ben AI in Prompt, updated
0
-
mods
0.2.0
A Mods pane that finds every mod on this Mac by itself, turns each one on or off in every chat, and opens the side-pane ones
Ben AI in Panes, updated
0
-
savings-proof
0.2.0
/savings opens the Savings Proof pane: every token the other mods saved, with today's and this chat's totals
Ben AI in Usage & cost, updated
0
More usage & cost mods
-
token-weather
0.1.0
A live forecast of the context window, drawn above the prompt.
deepseek-ai in Usage & cost, updated
279.9k
-
token-optimizer
5.13.51
mod + skill
Audit, fix, and monitor Claude Code context window usage. Find the ghost tokens.
Alex Greenshpun in Usage & cost, updated
2.6k
-
token-run
0.1.3
A fully local ASCII runner game for Claude Code request failures and short breaks
YeonwooSung in Usage & cost, updated
868
-
artifact-dashboard
0.1.0
A one-line summary of the project's shared Kanban artifact above the prompt, read through Claude's own ArtifactData tool
Danny McAteer in Usage & cost, updated
801
-
context-bar
0.1.5
Your context window as a stacked bar above the prompt, a color per category, with token counts and the compaction point. /context-bar shows or hides it.
Hamza Zafar in Usage & cost, updated
473