dispatch-router 0.1.0
Asks a TypeSafe model which CLI and model should take each agent task, and refuses an agent launch that was not routed. Needs a TypeSafe API key; without one it does nothing. Sends the task text to api.typesafe.ai.
Install
/plugin marketplace add varunmoka28/moka-harness /plugin install dispatch-router@moka-harness
Run both lines inside Claude Code.
Hooks into
- Status line
- Tool calls
- Toasts
- Model tools
Also in varunmoka28/moka-harness
- prompt-enhancer 0.1.3 Rewrite a rough prompt in place using project rules and Jev-ranked skills. Needs a TypeSafe API key; calls are paid. 0
- run-ledger 0.1.2 A pane of estimated API cost per run, model and source plugin, each subagent's status, and Jev's model recommendation beside the model that actually ran. Needs a TypeSafe API key; calls to api.typesafe.ai are paid. 0
- assumption-log 0.1.0 Claude writes down each guess it makes about what you want, and they show up in a side panel as they happen, so you can catch a wrong one early. 0
- collision-guard 0.1.1 Asks before Claude edits a file that something else changed in the last 30 minutes, so two Claude sessions do not overwrite each other's work. 0
- context-guard 0.3.0 Warns you when a Claude Code conversation gets long and every message gets expensive. Can also compact an idle conversation for you, if you switch that on. 0
- cache-clock 0.1.2 Shows above the prompt how many minutes are left before the prompt cache goes cold, with a button to compact the conversation, and under it one green line with what unattended and layman have to say 0
- image-shrinker 0.3.1 macOS only. Shrinks big screenshots before Claude reads them, so long sessions last longer, and tells Claude the scale so clicks still land in the right place. 0
- input-router 0.1.0 Hands large file reads and connector results to a small model first, so Claude gets short notes on what matters for your task plus the path to the full text. Starts off. 0
- read-fence 0.2.0 Stops Claude from opening your skill, rule and plugin folders file by file while you have the fence switched on. Skills still run normally. 0
- skills-az 0.2.3 Shows a list of your slash commands and skills in A to Z order as soon as you type / in the prompt, and narrows it as you keep typing. 0
More status line mods
- jev-auto-mode 0.1.1 A permission layer driven by a JSON policy: allow, ask or deny every tool call (Bash, edits, web, MCP, subagents, skills), every slash command or skill you type, and every skill preloaded into a subagent. Rules decide first (deny > ask > allow, compound Bash commands split); what no rule covers c... 33.9k
- cache-clock 0.1.1 A prompt-cache line under your status line, from Claude Code's own cache figures: time left while warm, hit rate and misses, and how many tokens the next message re-caches once cold. /cache-clock setup adds it. 496
- secrets-veil 0.0.11 Masks secret values in tool results before the model reads them: named vendor variables, value-shape patterns, and high-entropy tokens. No reveal path. 305
- lemo-meter 0.2.0 用量横条:输入框上方显示上下文、5 小时额度、花费和 git 分支;状态栏显示消息编号(已有自己的状态栏时默认关闭);点「检查」才联网查新版本 / Usage meter: context, 5-hour quota, cost and git branch above the prompt; a status line with the message number (off by default if you have your own); checks for updates online only when you press Check 78
- glowup 1.2.0 mod + skill A glow-up for Claude Code: a cockpit pane for changes, subagents and context, an activity band, and shareable themes. 42