cd /news/ai-tools/show-hn-lanes-simple-claude-coordina… · home topics ai-tools article
[ARTICLE · art-117836] src=github.com ↗ pub= topic=ai-tools verified=true sentiment=· neutral

Show HN: Lanes, simple Claude coordination that exploits 0.1x cache-read pricing

A developer known as adam-s released Lanes, a proof-of-concept for coordinating multiple Claude Code chats through a shared message file, exploiting Anthropic's 0.1x cache-read pricing to reduce costs. The system lets an orchestrator chat split tasks among worker chats that watch the file, with support for Codex and git worktrees for parallel coding. The project is hosted on GitHub under adam-s/lanes.

read2 min views1 publishedSep 1, 2026
Show HN: Lanes, simple Claude coordination that exploits 0.1x cache-read pricing
Image: Michielbdejong (auto-discovered)

A Claude Code chat will keep a file watch running (like tail -f

) if you ask, and wake up when a new line arrives. So several chats watching the same file can send messages to each other.

Cache reads cost 0.1x (10%) of the normal token price. A chat that has already read the code is cheap to wake up again. Subagents start with an empty cache every time, so launching them over and over is expensive, even for small tasks.

This proof of concept combines the two ideas into agent lanes. Each chat joins a shared message file with the comms skill. One chat is the orchestrator, the rest are workers. You can also give workers a specialty, like reviewer or UI.

lanes-demo-edit-v1-fast-web.mp4 #

  • Open three Claude Code chats in this repo.
  • In the first, type /comms main

. - In the second, /comms child claude-1

. In the third,/comms child claude-2

. - Tell main what to build. It splits the work into tasks, sends them out, verifies the results, and sends the next ones.

If two workers write code at the same time, give each its own git worktree.

Codex can join a lane too (for example /comms child codex-1

), but you have to explicitly tell it not to close the chat, or it ends the session instead of watching the file.

In the file, the task

and done

above are one line each. Shown here pretty-printed:

{
  "from": "main",
  "to": "worker",
  "at": "2026-09-01T01:28:13Z",
  "type": "task",
  "task": "usage-dashboard",
  "text": "Build the dashboard view. Your tree: ../lanes-dashboard."
}
{
  "from": "worker",
  "to": "main",
  "at": "2026-09-01T01:32:42Z",
  "type": "done",
  "task": "usage-dashboard",
  "text": "Committed 724d2d6. Ran node --test: 27 pass, 0 fail."
}

The rules the agents follow are in AGENTS.md. Why each rule exists is in .agents/reference/protocol.md.

── more in #ai-tools 4 stories · sorted by recency
── more on @adam-s 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-lanes-simple…] indexed:0 read:2min 2026-09-01 ·