coding-agents · Claude Code mod

README

Claude Code mods

Four mods that work together: plan first, then code with each task sent to a model that fits how hard it is, and watch it all happen.

Mod	What it does
`task-planner`	`/plan <goal>` runs an Opus planner agent (read-only) that returns a checklist of focused tasks, each rated easy/medium/hard. The steps appear in a Plan pane.
`coding-agents`	Adds a `coder` subagent and tells the main session to hand each focused coding task to it, one at a time.
`model-router`	Before each `coder` starts, Haiku rates the task and the coder runs on Haiku (easy), Sonnet (medium) or Opus (hard). Falls back to Sonnet if rating fails; a model the session asks for explicitly wins.
`mod-monitor`	A Mods pane: in the desktop app an animated control room (you → session → mods → Haiku/Sonnet/Opus) with messages flying along the wires, busy mods pulsing, running agents linked to their model, and the model mix; in the terminal an emoji/colour version. Hover anything for details.

They need Claude Code on your own computer (terminal claude, or the Code tab of the desktop app). Cloud sessions in the Claude app don't load plugins.

Mods pane in the desktop app

Install

In a Claude Code session:

/plugin install task-planner --marketplace alexatennea/claude-mods
/plugin install coding-agents --marketplace alexatennea/claude-mods
/plugin install model-router --marketplace alexatennea/claude-mods
/plugin install mod-monitor --marketplace alexatennea/claude-mods

Already added the marketplace before a mod existed? Refresh it first: /plugin marketplace update void-mods. After an update to a mod you have, run /plugin update <mod>.

Answer y to add the marketplace the first time, then pick user scope so they're on in every session. Start a new session (or run /reload-plugins) and they're active.

How to use

Open your project and start Claude Code there (cd my-project && claude). Use a wide terminal: panes show beside the conversation from about 144 columns; in a narrower one, open them with the commands below.
Watch: /mods opens the Mods pane.
Plan: /plan add password reset to the login page. The planner (Opus) reads the code and returns numbered steps rated easy/medium/hard; the Plan pane opens with them. Nothing is edited yet.
Review the plan. Ask for changes in plain words ("split step 3", "skip the email step") if needed.
Build: say "go ahead". The session hands each step to a coder. For each one the router asks Haiku to rate it, then the coder runs on Haiku, Sonnet or Opus. In the Mods pane you'll see e.g.: `` model-router → haiku: Task: Add reset route … haiku → model-router: medium session → coding-agents:coder (sonnet): Add reset route coding-agents:coder (sonnet) → session: done in 41s: Changed 2 files … ``
Track progress: /plan-done 2 ticks off step 2; /plan-view reopens the Plan pane.
Check spend: /routing shows how many tasks went to each model.

You don't have to use /plan: asking for any coding work ("fix the failing date test") also goes through coder + router.

Commands

Command	Mod	Does
`/plan <goal>`	task-planner	Plan a goal with the Opus planner
`/plan-view`	task-planner	Open the Plan pane
`/plan-done N`	task-planner	Tick (or untick) step N
`/routing`	model-router	Tasks per model so far
`/mods`	mod-monitor	Open the Mods pane

Configure

model-router options (in /config, or pluginConfigs.model-router.options in settings):

easyModel / mediumModel / hardModel: defaults haiku / sonnet / opus (aliases always mean the latest of each)
classifierModel: default haiku
routedAgents: comma-separated agent types to route, default coding-agents:coder. Add more coding agents here as you build them.

Develop

claude plugin validate model-router
claude plugin test model-router
claude --plugin-dir task-planner --plugin-dir coding-agents --plugin-dir model-router --plugin-dir mod-monitor

Source 1 files

hooks/register.ts 36 lines

1import type { Register } from 'claude-code'
2
3const CODER = 'coding-agents:coder'
4
5const GUIDANCE = `# Delegating coding work
6For implementation work, split it into focused tasks (or follow the current plan's steps) and hand each one to the ${CODER} agent, one task per call, with the files involved and how to check it. Leave the Agent tool's model parameter unset: a router picks the model per task. Make one-line edits yourself. Review each coder's report before starting the next dependent task.`
7
8export const register: Register = on => {
9  const running = new Map<string, string>()
10  const label = () => (running.size === 0 ? undefined : `coders: ${running.size} running`)
11
12  on('prompt.compose', async ($, e, next) => {
13    const composed = await next(e)
14
15    return {
16      sections: [...composed.sections, { id: 'coding-agents:guidance', text: GUIDANCE, scope: 'session' }],
17    }
18  })
19
20  on('agent.spawn', async ($, e, next) => {
21    const started = await next(e)
22    if (e.subagentType === CODER && started.agentId) {
23      running.set(started.agentId, e.description)
24      $.ui.status(label())
25    }
26
27    return started
28  }).catch(($, e, next) => next(e))
29
30  on('turn.complete', async ($, e, next) => {
31    if (e.agentId && running.delete(e.agentId)) $.ui.status(label())
32
33    return next(e)
34  })
35}
36