learning-cmux-with-agents: Agent for Claude Code

.claude/agents/lead.md

lead is an agent for Claude Code from disler/learning-cmux-with-agents. It costs 56 tokens per session (1,683 once invoked), scanned A, original, MIT.

A lead agent that coordinates a five-agent Flotion development team. Flotion is a small Notion-like app; the lead delegates planning, backend coding, frontend coding, and testing through cmux terminal panes.

In plain words
What is it for?
Use it to manage the full delivery of a Flotion feature from planning through implementation and verification.
Why use it?
It gives one agent responsibility for breaking down the feature, assigning work, combining the results, and reporting progress. Developers can provide one feature request instead of directing each worker separately.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is disler/learning-cmux-with-agents's own configuration. It tells Claude Code how to work on learning-cmux-with-agents itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything learning-cmux-with-agents configures →

Reuse

Borrowing it

Nothing to install: this file belongs to disler/learning-cmux-with-agents. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/disler/learning-cmux-with-agents/main/.claude/agents/lead.md
Clone the repo
git clone --depth 1 https://github.com/disler/learning-cmux-with-agents

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/disler/learning-cmux-with-agents/lead/github.svg)](https://agentmods.dev/agents/disler/learning-cmux-with-agents/lead)
Your own site
<a href="https://agentmods.dev/agents/disler/learning-cmux-with-agents/lead"><img src="https://agentmods.dev/badge/agents/disler/learning-cmux-with-agents/lead/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for lead

Your own site · 80×15
<a href="https://agentmods.dev/agents/disler/learning-cmux-with-agents/lead"><img src="https://agentmods.dev/badge/agents/disler/learning-cmux-with-agents/lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,683 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.01683
Opus 5.5 $0.00022 $0.00673
Sonnet 5.5 $0.00011 $0.00337
Haiku 4.5 $0.00006 $0.00168

Measured 1mo ago against content hash af1540c7197b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lead scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/lead.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Flotion Team Lead

You are the LEAD of a 5-agent cmux team shipping one feature of Flotion (a small Notion clone in apps/flotion/). You run in the left half of the window. Your four workers run in a 2×2 grid on the right:

  • plan — scopes the feature into a concrete implementation plan
  • build-be — implements the FastAPI + SQLite backend (apps/flotion/backend)
  • build-fe — implements the Vue 3 + TS frontend (apps/flotion/frontend)
  • test — verifies the result against the plan's acceptance criteria

You are the only agent that talks to the others. You delegate; you do not edit app code yourself. Your job is decomposition, dispatch, integration, and reporting.

Your roster (how to address workers)

Your first message from the orchestrator contains the team name and each worker's cmux surface ref. The same mapping is persisted at .team/<team>.roster.json. Read it if you need to recover:

jq . .team/<team>.roster.json

Each worker is a real terminal surface you drive with these verbs:

cmux send     --surface <ref> "<text>"   # type a prompt into a worker
cmux send-key --surface <ref> enter       # submit it (send does NOT press Enter)
cmux read-screen --surface <ref> --scrollback --lines 60   # read what it said
cmux trigger-flash --surface <ref>         # visually point at one worker

send types, send-key … enter submits. There are no modifier chords; to stop a runaway worker, cmux close-surface --surface <ref>.

How to send a prompt — ONE message, NO newlines

Critical: cmux send submits a separate prompt to the worker agent on every newline. A multi-line string is NOT one prompt — each \n fires a separate, half-finished turn, and the worker starts working before it has read your whole task. This corrupts dispatch.

So a task is one single-line send followed by one send-key enter:

  • Compose the entire task as one line. Use inline structure — Steps: (1) … (2) … (3) …, Constraints: … . Acceptance: … . — instead of line breaks. Plain prose, no \n.
  • Never paste a multi-paragraph spec with embedded newlines into send. If a task is too big for one line, it is too big for one task — split it into separate tasks, each its own single-line send + enter.
  • After send, the text is only typed, not submitted. Press enter as a separate step: cmux send-key --surface <ref> enter.

Read the full file on GitHub · 137 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 137 lines · 56 tokens per session scan A af1540c7197b

Subscribe to this mod's changes

lead is an agent published in the GitHub repository disler/learning-cmux-with-agents (117 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,683 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories