hcom-agent-messaging
Connects independent AI coding agents to enable them to communicate, watch, and spawn tasks.
Install
mkdir -p .claude/skills/hcom-agent-messaging && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19415" && unzip -o skill.zip -d .claude/skills/hcom-agent-messaging && rm skill.zipInstalls to .claude/skills/hcom-agent-messaging
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Multi-agent communication for AI coding tools. Agents message, watch, and spawn each other across terminals. Use when setting up hcom, troubleshooting delivery, or writing multi-agent scripts.Key capabilities
- →Message between AI agents in real-time
- →Observe agent transcripts, file edits, and terminal screens
- →Subscribe to agent status changes and events
- →Spawn, fork, resume, and kill agents across terminals
- →Bundle context for agent handoffs
How it works
It connects isolated terminal sessions via hooks and a shared database, allowing agents to communicate, monitor, and control each other's execution.
Inputs & outputs
When to use hcom-agent-messaging
- →Messaging between agents
- →Observing agent terminal activity
- →Forking tasks to sub-agents
- →Coordinating multi-agent workflows
About this skill
hcom — multi-agent communication for AI coding tools
AI agents running in separate terminals are isolated. hcom connects them via hooks and a shared database so they can message, watch, and spawn each other in real-time.
Start an agent with hcom in front, then prompt normally.
Use hcom to:
- coordinate multi-agent pipelines
- run different AI CLIs as each other's subagents
- avoid copy-pasting
uv tool install hcom
hcom claude # or: hcom gemini, hcom codex, hcom opencode, hcom kilo, hcom pi, hcom omp, hcom agy, hcom cursor, hcom kimi, hcom copilot, hcom qoder, hcom grok, hcom hermes
hcom # TUI dashboard
Quickstart:
# terminal 1
hcom claude
# terminal 2
hcom codex
Prompt normally — e.g. review what claude did and send it fixes
what humans can do
tell any agent:
send a message to claude
when codex goes idle send it the next task
watch gemini's file edits, review each and send feedback if any bugs
fork yourself to investigate the bug and report back
find which agent worked on terminal_id code, resume them and ask why it sucks
what agents can do
Message each other in real time: mid-turn or wake immediately when idle
Observe each other: status, transcripts, file edits, live terminal screens, command history.
Subscribe and notify on status changes, file edits, collisions, specific events. React automatically.
Spawn, fork, resume, kill in any terminal emulator or headless.
run hcom --help for full command syntax and flags.
Works with Claude Code, Gemini CLI, Codex, OpenCode, Kilo Code, Pi, Oh My Pi, Antigravity, Cursor, Kimi, Copilot, Qoder CLI, Grok Build, Hermes Agent, and other tools
setup
When this skill is invoked, first run:
hcom status
If hcom status works: run hcom list
If hcom list shows "Your name: <name>" where <name> is not "(not participating)": congratulations!
If running hcom status returns "command not found", install first:
uv tool install hcom
See the hcom README for other install options.
If hcom status shows a list of CLI tools and you are not any of them, run hcom start to connect to hcom.
If you've just installed hcom now or if hcom list shows "Your name: (not participating)" and you are a tool in the hcom status list of CLI tools:
Relaunch into hcom properly for automatic message delivery and full hcom functionality. User should exit and run hcom <tool>.
Or if you know your sessionID/ses_/thread_name: user can exit and run hcom r <session-id> to resume you inside hcom. See hcom r --help.
troubleshooting
"hcom not working"
hcom status # check installation
hcom hooks status # check hooks specifically
hcom relay status # check cross-device relay
still broken?
hcom reset all # backup config/db + reset it
hcom claude # fresh start
still broken after that?
git clone https://github.com/aannoo/hcom.git
cd hcom
Read code and figure out what is going on.
sandbox / permission issues
Use project-local hcom state when the normal hcom directory is unavailable:
HCOM_DIR=$PWD/.hcom hcom <tool>
files
| what | location |
|---|---|
| database | ~/.hcom/hcom.db |
| config | ~/.hcom/config.toml |
| env | ~/.hcom/env |
| logs | ~/.hcom/.tmp/logs/ |
| user scripts | ~/.hcom/scripts/ |
more info
hcom --help
hcom <command> --help
hcom run docs --scripts # script authoring info
Github: https://github.com/aannoo/hcom
When not to use it
- →Using sleep commands in scripts
- →Hardcoding agent names in scripts
- →Running headless agents without cleanup traps
Prerequisites
Limitations
- →Requires hooks for automatic delivery
- →Messages can leak across workflows without thread isolation
- →Orphaned headless agents run indefinitely without proper cleanup
How it compares
It enables cross-terminal agent orchestration that is otherwise impossible due to terminal isolation.
Compared to similar skills
hcom-agent-messaging side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| hcom-agent-messaging (this skill) | 0 | 3mo | Review | Advanced |
| agent-protocol | 1 | 4mo | No flags | Intermediate |
| messaging-agents | 0 | 6mo | Review | Intermediate |
| agent-collective-intelligence-coordinator | 0 | 8mo | No flags | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
agent-protocol
alirezarezvani
Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.
messaging-agents
letta-ai
Send messages to other agents on your server. Use when you need to communicate with, query, or delegate tasks to another agent.
agent-collective-intelligence-coordinator
ruvnet
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator
agent-mesh-coordinator
ruvnet
Agent skill for mesh-coordinator - invoke with $agent-mesh-coordinator
llm-b-comms
Ilenburg1993
>-
ralph2ralph
eqtylab
P2P chat between Claude Code instances using real-a2a. Use when chatting with other Claudes, joining a P2P room, or communicating agent-to-agent.