What is handoff-mesh?

A durable handoff system for setups where multiple coding agents pass work to one another through shared folders and status reports.

Use it to assign work between agents, track open handoffs, verify completion, and retain a history in an Obsidian vault.

It keeps handoffs searchable, surfaces unfinished work, archives old messages, and records whether the receiving agent completed the task.

handoff-mesh — Skill for Claude Code and Codex by Gentech-Labs

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Gentech-Labs/genTech-agent-kit --skill handoff-mesh

Clone the repo

git clone --depth 1 https://github.com/Gentech-Labs/genTech-agent-kit

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/handoff-mesh.svg)](https://agentmods.dev/skills/gentech-labs/gentech-agent-kit/handoff-mesh)

Your own site

<a href="https://agentmods.dev/skills/gentech-labs/gentech-agent-kit/handoff-mesh"><img src="https://agentmods.dev/badge/skills/gentech-labs/gentech-agent-kit/handoff-mesh.svg" alt="Measured on agentmods" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,107 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.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.02107
Opus 5	$0.00036	$0.01053
Sonnet 5	$0.00014	$0.00421
Haiku 4.5	$0.00007	$0.00211

Measured 7d ago against content hash fd17b1a0ee79, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

handoff-mesh 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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/handoff-watcher.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/handoff-mesh/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff Mesh — Communication Layer for Multi-Agent Setups

When to Use

You run more than one agent (multi-agent strategy) and they need to hand work to each other.
An agent finishes something and another agent (or a human) needs to pick it up.
You want a durable, searchable coordination layer — not just real-time chat.
You want to know, at a glance, what handoffs are open and whether they got done.

What This Is

A full-mesh handoff system built on the vault (Obsidian) — the durable brain. Any agent can drop a handoff into any other agent's inbox. A watcher surfaces open handoffs hourly. Nightly maintenance archives old ones. And a completion-reporting loop closes the deal: the agent that reads a handoff reports back what it did before it's marked resolved.

This is the storage + verification half of agent communication. Real-time channels (Buzz, Telegram) are the talking half; this is the remembering and proving half. They complement each other — the vault stays the source of truth.

The Layout

01-HANDOFFS/
    INBOX/
        <group>/                    ← one receive folder per agent/group
            <YYYY-MM-DD>-<topic>.md ← a handoff note for that agent
            _archive/               ← resolved notes (auto-moved, purged weekly)
    <from>-to-<to>/                 ← optional explicit sender→receiver folders

The Protocol (4 steps — the loop)

Step 1 — SEND: drop a handoff into the target's inbox

Write <date>-<topic>.md into the target group's INBOX/<group>/ folder. Format:

# <topic>
**From:** <agent/group>
**To:** <group>
**Date:** <YYYY-MM-DD>
**Status:** open

## What's needed
<what the receiving agent should do>

## Context / files
<any links or paths>

Commit + push (or ob sync).

Step 2 — WATCH: surface open handoffs automatically

Run the watcher hourly (or on each agent's wake-up). It scans every inbox lane and reports any note still Status: open (not resolved, not archived).

python3 handoff-watcher.py [vault_path]

Silent when clear — only pings when there's actually something to do.
Quiet overnight — schedule it for waking hours only (e.g. 7 AM–11 PM ET).
Wire it as a no_agent cron (pure script, zero tokens) so it's cheap.

Read the full file on GitHub · 177 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/handoff-watcher.py 6.5 KB runs code

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.

7d ago First seen · 177 lines · 71 tokens per session scan A fd17b1a0ee79

Subscribe to this mod's changes

handoff-mesh is a skill published in the GitHub repository Gentech-Labs/genTech-agent-kit (0 stars, last pushed 15d ago), licensed MIT. It adds 71 tokens to every session and 2,107 once invoked, about $0.0004 per session on Opus 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 2026-08-31.

Building agents Multi-Agent communication coordination handoff inbox mesh vault

frontier-orchestrator-openaccp

Run a bounded OpenACCP Frontier lane. Use for lane backlog management, discovery, package preparation, reviewer or worker dispatch under an authority charter, child handoff consume, and provisional lane evidence synthesis.

0fuk/OpenACCP · 49 tokens

primary-orchestrator-openaccp

Run delegated-final-authority OpenACCP coordination. Use for coordination decisions, authority charters, dispatch, final handoff consume, PR/CI/merge readiness, publication readiness, owner-ready waiver recommendations, and accepting or rejecting reviewed evidence when delegated by charter.

0fuk/OpenACCP · 60 tokens

handoff-mesh