model-router 0.1.0
Picks the model and effort from the first prompt of a session and keeps them for the whole session; gives each subagent its own model and effort by the difficulty of its part.
Install
/plugin marketplace add pedrojr/claude-mods /plugin install model-router@claude-mods
Run both lines inside Claude Code.
Hooks into
- Prompt
- Status line
- Tool calls
- Slash commands
- System prompt
Also in pedrojr/claude-mods
- usage-advisor 0.1.0 Watches how the session spends tokens and shows an icon with the tip count at the end of usage-bar's line. A click, or /advisor, opens an audit: the context a session starts with, the last 10 sessions of the project, a diagnosis, changes to approve one at a time and the three habits that save the... 1
- workspace 0.1.0 One side pane for the session's work: the active agents and sessions on top, the repository's changed files below, and the diff of the file you click at the bottom. 0
- usage-report 0.1.1 Today's usage across every session on the machine: tokens, models, effort, tool calls ok and failed, retries, API errors, sessions and subagents. Open it with /report. 0
- usage-bar 0.6.0 Compact one-line usage: current session and this week, each with percent, a bar and the reset time. 0
- agents-panel 0.3.0 Side pane listing every open Claude Code session on this machine and this session's agents, each with what it is doing now. 0
More prompt mods
- ruflo-ruos 0.1.2 mod + skill Run ruflo swarm agents on your own ruOS cloud desktops via the tenant-authenticated fleet MCP or per-tenant SSH; optional and removable (ADR-405) 81.6k
- pet 0.2.0 A virtual pet above the Claude Code prompt that grows as Claude works: passing tests, commits and edits grant XP and mood, failing tests cost mood, idling drains it; egg → baby → kid → adult → legend. Zero tokens. Split out of cc-arcade (MIT, Seza Akgün). Needs an interactive terminal. 33.4k
- daily.dev 0.19.0 mod + skill Access personalized developer content feeds from daily.dev - the professional network for developers. Surface relevant articles, tutorials, and discussions based on user interests. 20.1k
- plannotator 0.28.62 Interactive Plan Review: Mark up and refine your plans using a UI, easily share for team collaboration, automatically integrates with plan mode hooks. 10.2k
- vsr 0.1.10 mod + skill vSR runs a vLLM Semantic Router decision model (local CPU, local GPU or remote) inside Claude Code: routes subagents by difficulty, escalates when you push back, redacts personal data and secrets, shields against prompt injection, guards risky Bash commands, and checks answers against what Claude... 6.4k