subagent-model-router 0.6.0
Modified copy of an MIT-licensed Jev model router that uses 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 minDowngradeConfidence. Logs every p...
Kazim AliInstall
/plugin marketplace add rome2o/tokenpower-claude /plugin install subagent-model-router@tokenpower-claude
Run both lines inside Claude Code.
Hooks into
- Prompt
- Status line
- Slash commands
Also in rome2o/tokenpower-claude
-
mcp-schema-auditor
0.1.0
/mcp-cost shows how many tokens each MCP server's tool definitions cost in every request, ranked, and suggests which to disable with /mcp
Kazim Ali in Usage & cost, updated
1
-
context-bloat-auditor
0.1.0
/context-audit lists the always-loaded items that cost the most tokens (CLAUDE.md files, memory, skills, agents), flags big items and duplicate names, and never reads the contents of your files
Kazim Ali in Usage & cost, updated
1
-
context-meter
0.1.0
A live band above the prompt: what fills the context window by category, how close it is to compaction, this session's cost as Claude reports it, and today's tokens saved by the other mods
Kazim Ali in Usage & cost, updated
1
-
compaction-pruner
0.1.0
Off by default. When you compact, shortens old large tool results with simple local rules and keeps the original text (secrets masked) in a folder you can open. It deletes nothing and makes no network or model calls
Kazim Ali in Panes, updated
1
-
large-file-reader
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
Kazim Ali in Panes, updated
1
-
effort-level-switcher
0.1.0
Reads each prompt, picks the effort level it needs with a four-question framework, and offers Switch to that level, or sets it by itself in auto mode
Kazim Ali in Prompt, updated
1
-
prompt-cache-timer
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
Kazim Ali in Prompt, updated
1
-
context-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
Kazim Ali in Usage & cost, updated
1
-
web-research-saver
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
Kazim Ali in Panes, updated
1
-
browser-screenshot-compressor
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
Kazim Ali in Prompt, updated
1
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