git404hub

what is agent-handover-protocol fr?

teloz1870/agent-handover-protocol — explained in plain English

Analysis updated 2026-07-25

0JavaScriptAudience · developerComplexity · 2/5Setup · easy

tl;dr

A set of rules that lets two AI coding agents collaborate on the same codebase safely by communicating through git files and commits, with a human approving all major decisions.

vibe map

mindmap
  root((repo))
    What it does
      Agents talk via git files
      Human owns decisions
      Seven-section protocol
    How it works
      Labeled messages with end markers
      Handover and report templates
      Claims are input not facts
    Tooling
      Claude Code skill
      Codex CLI section
      Optional local timeline viewer
    Use cases
      Two-agent collaboration
      Bug catching between agents
      Safe handoff workflows

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

what do people make with this?

VIBE 1

Run two AI coding agents on the same project without them overwriting each other's work.

VIBE 2

Catch bugs introduced by one agent by having a second agent review and test the code.

VIBE 3

Maintain a clear audit trail of agent-to-agent handovers through versioned git files.

VIBE 4

Enforce human approval on scope changes while letting agents handle mechanical work autonomously.

what's the stack?

JavaScriptGitClaude CodeCodex CLI

how it stacks up fr

teloz1870/agent-handover-protocol00kaku/gallery-slider-block0xkinno/vellum
Stars00
LanguageJavaScriptJavaScriptJavaScript
Last pushed2021-05-19
MaintenanceDormant
Setup difficultyeasyeasyhard
Complexity2/52/54/5
Audiencedevelopergeneraldeveloper

Figures from each repo's GitHub metadata at analysis time.

how do i run it?

Difficulty · easy time til it works · 30min

Requires understanding the protocol file and configuring your AI agent tools (Claude Code or Codex CLI) to follow it, but no external infrastructure is needed.

The license for this repository is not specified in the available documentation.

in plain english

This repository defines a set of rules for letting two AI coding agents work in the same code repository without stepping on each other. The idea is simple: instead of agents talking through chat windows or screen interactions, they communicate through git files and commits. A human owner sits at the decision points, approving scope changes and anything that cannot be undone. The creator tested this setup while shipping a real product, a WooCommerce plugin with its licensing backend. Over a week of use, each agent caught bugs the other had introduced. One caught a checksum verification that silently skipped across separate requests. The other caught a provider deduplication that ate deliberately re-sent receipts. Before publishing, the author also tested whether an agent would blindly follow a wrong instruction from its peer. In trap scenarios with false bug claims and harmful fixes, the agent refused each trap on its own, rerunning tests and leaving other agents' files alone. The core argument is that AI agents cannot guess unstated conventions. Which files belong to which agent, what a report must contain, which decisions belong to the human, and what marks the end of a round all need to be written down explicitly. The repository ships that written contract as a short seven-section protocol file. It also includes a Claude Code skill, a Codex CLI section, and templates for handover and report files. An optional local viewer renders handovers and the commit log as a timeline, but it only reads and never writes. Three rules anchor the system. Every machine message must be labeled with its sender and a clear end marker. Git is the communication bus, with handovers and reports stored as versioned, diffable files rather than screen-scraped UI text. And the human owns the forks: scope changes and irreversible actions stop at the owner, while mechanical work within approved scope can loop freely. The standing discipline is that claims are input, not facts. Agents must reproduce before acting and refute with evidence. Modified files that are not yours are foreign, even when unlabeled.

prompts (copy fr)

prompt 1
Set up the agent-handover-protocol in my repo: create the protocol file, handover template, and report template, and tell me where each should live.
prompt 2
I have two AI agents working on my codebase. Write a handover file following the agent-handover-protocol so Agent A can pass scope and context to Agent B safely.
prompt 3
Using the agent-handover-protocol rules, review this git commit from another agent and write a report file that either reproduces the claimed bug or refutes it with evidence.
prompt 4
Configure Claude Code and Codex CLI to follow the agent-handover-protocol so they communicate only through git files and stop for human approval on scope changes.

Frequently asked questions

what is agent-handover-protocol fr?

A set of rules that lets two AI coding agents collaborate on the same codebase safely by communicating through git files and commits, with a human approving all major decisions.

What language is agent-handover-protocol written in?

Mainly JavaScript. The stack also includes JavaScript, Git, Claude Code.

What license does agent-handover-protocol use?

The license for this repository is not specified in the available documentation.

How hard is agent-handover-protocol to set up?

Setup difficulty is rated easy, with roughly 30min to a first successful run.

Who is agent-handover-protocol for?

Mainly developer.

peek the repo → explain another one

This repo across BitVibe Labs

double-check against the repo, no cap.