tokimwc

Clawbus — Development skill for Claude Code

Development community

A minimal protocol turning multiple Claude Code sessions into an observable, auditable agent team.

How to install Clawbus

This entry records only its repository, not the path inside it, so there is no exact command to give. Open tokimwc/clawbus and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Clawbus does

A minimal protocol turning multiple Claude Code sessions into an observable, auditable agent team. Built for the Claude 4.7 Hackathon.

Alternatives in Development

Claude Swap — Switch between multiple Claude Code accounts, with automatic rate-limit rotation, usage dashboard, and paralle 2k ★
Opslane Old — Run multiple Claude Code sessions in parallel 772 ★
Claude Code Agent Farm — A powerful orchestration framework that runs multiple Claude Code (cc) sessions in parallel to systematically 704 ★

README

ClawBus

**A minimal protocol turning multiple Claude Code sessions into an observable, auditable agent team.**

**Claude Code is excellent per session. ClawBus makes cross-session coordination auditable without inventing a new runtime.**

Claude Code is powerful as a single coding agent, but real work usually needs a team — planning, investigation, implementation, review, and human approval. ClawBus defines a minimal protocol and reference implementation so multiple Claude Code / Claude Agent SDK sessions can delegate subtasks, share context, and surface decisions that need human sign-off.

This repository is the submission for **Built with Opus 4.7: a Claude Code Hackathon** (Cerebral Valley × Anthropic, 2026-04-21 – 2026-04-26).

TL;DR for hackathon reviewers

git clone https://github.com/tokimwc/clawbus.git
cd clawbus
npm install
npm run build
export ANTHROPIC_API_KEY=sk-ant-...
npx clawbus demo

You should see:

A Planner agent decompose a toy task (examples/broken-node-project has a bug).
A Worker agent investigate and propose a patch.
A Human Approval Gate pause at the terminal asking you to approve/reject.
On approval, the patch is applied and npx clawbus logs shows the full causal timeline of messages.

Everything runs locally on SQLite. No network calls except to the Anthropic API. See [`docs/judging-guide.md`](docs/judging-guide.md) for a 5-minute review checklist with branches for "no API key" vs "with API key" reviewers.

**No API key handy?** The [judging guide](docs/judging-guide.md) and [`docs/scenarios/`](docs/scenarios/) contain three captured end-to-end runs with full message timelines and costs. The whole protocol fits in two pages — see [`docs/protocol.md`](docs/protocol.md).

**Want the longer argument?** [`docs/manifesto.md`](docs/manifesto.md) explains why we built this and — more importantly — what we deliberately didn't build.