New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Agent Chat

by profbernardoj in profbernardoj/everclaw-community-branches

XMTP real-time agent-to-agent and user-to-agent encrypted messaging daemon for EverClaw.

MITAuto-check: notesDevOps & Cloud

Install Agent Chat

skills CLI
$ npx skills add profbernardoj/everclaw-community-branches --skill agent-chat -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install profbernardoj/everclaw-community-branches agent-chat --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/profbernardoj/everclaw-community-branches.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agent-chat .claude/skills/agent-chat && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agent-chat
GitHub stars
112
Token cost
~2.2k tokens
SKILL.md length
639 words
Files
46
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

XMTP real-time agent-to-agent and user-to-agent encrypted messaging daemon for EverClaw.

  • Works in 2 steps: AGENT_CHAT_AGENT_ID=alice → data dir is… → No env var → data dir is…
  • Setting up XMTP messaging
  • SKILL.md covers Overview, Version, Dependencies and Quick Start, plus 8 more sections
  • Runs JavaScript scripts from its folder; calls bash and node

What it does

Agent Chat is an agent skill from profbernardoj/everclaw-community-branches. XMTP real-time agent-to-agent and user-to-agent encrypted messaging daemon for EverClaw. Manages always-on messaging via XMTP MLS protocol with multi-identity buddy bot support, filesystem-based IPC bridge, consent policies, and cross-platform daemon lifecycle (launchd/systemd). Use when setting up XMTP messaging, managing agent identities, configuring buddy bots, troubleshooting message delivery, or controlling the agent-chat daemon.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 47 other files (for example `CHANGELOG.md`, `README.md` and `config/default.json`).

It sits in DevOps & Cloud, covering Linux administration. It works with Linux and macOS. The repository describes itself as: Decentralized AI inference for OpenClaw agents. Powered by Morpheus AI. Stake MOR, access Kimi K2.5 + 10 models, never run out of inference. The licence is MIT.

When your agent uses it

  • Setting up XMTP messaging
  • Managing agent identities
  • Configuring buddy bots
  • Troubleshooting message delivery

Example prompts

  • “/agent-chat”

Requirements

  • Node.js

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. AGENT_CHAT_AGENT_ID=alice → data dir is ~/.everclaw/xmtp-alice/
  2. No env var → data dir is ~/.everclaw/xmtp/ (default host)

What it can do on your machine

Read from SKILL.md and the folder at commit 0b30b36. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (JavaScript, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Chat loads about 2.2k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 639 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:70
    ote:** Linux uses user-level systemd (no sudo required). All services run as your user account.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from profbernardoj/everclaw-community-branches at commit 0b30b36, republished under its MIT licence (© profbernardoj). 639 words, ~2,188 tokens.

Download SKILL.mdSave it as .claude/skills/agent-chat/SKILL.md (or your agent's skills folder). This skill also uses 45 other files; get the full folder from GitHub.
name
agent-chat
description
XMTP real-time agent-to-agent and user-to-agent encrypted messaging daemon for EverClaw. Manages always-on messaging via XMTP MLS protocol with multi-identity buddy bot support, filesystem-based IPC bridge, consent policies, and cross-platform daemon lifecycle (launchd/systemd). Use when setting up XMTP messaging, managing agent identities, configuring buddy bots, troubleshooting message delivery, or controlling the agent-chat daemon.

agent-chat

XMTP real-time agent-to-agent and user-to-agent messaging for EverClaw.

Overview

Always-on daemon providing E2E-encrypted messaging via XMTP's MLS protocol. Runs as a separate process managed by launchd (macOS) or systemd (Linux), communicating with OpenClaw through a filesystem bridge.

Version

0.2.0

Dependencies

  • @xmtp/agent-sdk ^2.3.0
  • xmtp-comms-guard ^6.0.0 (peer)
  • Node.js >= 20.0.0

Quick Start

bash
# 1. Generate XMTP identity (one-time)
node skills/agent-chat/setup-identity.mjs

# 2. Install daemon as system service
bash scripts/setup-agent-chat.sh

# 3. Check status
bash scripts/setup-agent-chat.sh --status

Daemon Management

The setup-agent-chat.sh script installs the XMTP daemon as a persistent system service.

Commands
bash
# Install and start daemon (auto-detects OS)
bash scripts/setup-agent-chat.sh

# Check daemon status
bash scripts/setup-agent-chat.sh --status

# View recent logs
bash scripts/setup-agent-chat.sh --logs

# Restart daemon
bash scripts/setup-agent-chat.sh --restart

# Uninstall daemon
bash scripts/setup-agent-chat.sh --uninstall

# Install without starting
bash scripts/setup-agent-chat.sh --skip-start
Platform Support
PlatformService ManagerLocationLogs
macOSlaunchd~/Library/LaunchAgents/com.everclaw.agent-chat.plist~/.everclaw/logs/agent-chat.*
Linuxsystemd (user)~/.config/systemd/user/everclaw-agent-chat.servicejournalctl --user -u everclaw-agent-chat

Note: Linux uses user-level systemd (no sudo required). All services run as your user account.

Manual Commands

macOS (launchd):

bash
# Check if loaded
launchctl list | grep everclaw

# View logs
tail -f ~/.everclaw/logs/agent-chat.log

# Stop/start
launchctl bootout gui/$(id -u)/com.everclaw.agent-chat
launchctl bootstrap gui/$(id -u) ~/Library/LaunchAgents/com.everclaw.agent-chat.plist

Linux (systemd):

bash
# Check status
systemctl --user status everclaw-agent-chat

# View logs
journalctl --user -u everclaw-agent-chat -f

# Stop/start
systemctl --user stop everclaw-agent-chat
systemctl --user start everclaw-agent-chat

Architecture

  • Process model: Separate always-on daemon (not in-process with OpenClaw)
  • IPC: Filesystem bridge (~/.everclaw/xmtp/outbox/ → inbox/)
  • Message format: V6 JSON inside XMTP text content type
  • Consent: Configurable per-agent (open/handshake/strict)
  • Middleware chain: Consent → CommsGuard V6 → Router

Identity Model

Two-tier:

  • 28 flavor canonical wallets — project-controlled, open consent
  • Per-user wallets — generated at install, handshake consent

XMTP wallet is messaging-only — no funds. Separate from MOR staking wallet.

CLI Reference

bash
# Identity status
node skills/agent-chat/cli.mjs status

# Daemon health
node skills/agent-chat/cli.mjs health

# List peer groups
node skills/agent-chat/cli.mjs groups

# Trust a peer (allow messages)
node skills/agent-chat/cli.mjs trust-peer 0x... --as colleague --name "Agent Name"

# List trusted peers
node skills/agent-chat/cli.mjs peers list

# Send a message (via outbox)
node skills/agent-chat/cli.mjs send 0x... "Hello, agent!"

Files

FilePurpose
daemon.mjsEntry point for launchd/systemd
cli.mjsCLI commands
setup-identity.mjsOne-time key generation
src/agent.mjsAgent creation + middleware wiring
src/identity.mjsSecret/identity loading (multi-identity: agentId param)
src/paths.mjsPath resolution + agent ID validation (multi-identity)
src/consent.mjs3-policy consent gate
src/router.mjsMessage routing (COMMAND/DATA dispatch)
src/bridge.mjsFilesystem outbox watcher (multi-identity: agentId param)
src/health.mjsHealth file writer (multi-identity: agentId param)
src/health.mjsHealth file writer
src/groups.mjsGroup conversation mapping
src/payer.mjsFee stub (network currently free)
src/index.mjsPublic API re-exports

Multi-Identity (Buddy Bots)

Each buddy bot agent gets its own XMTP identity, daemon process, and data directory. This is called "multi-identity" mode — one daemon per agent, running as independent services.

Directory Layout
AgentData DirectoryService (macOS)Service (Linux)
Host (default)~/.everclaw/xmtp/com.everclaw.agent-chateverclaw-agent-chat
Alice~/.everclaw/xmtp-alice/com.everclaw.agent-chat.aliceeverclaw-agent-chat-alice
Bob~/.everclaw/xmtp-bob/com.everclaw.agent-chat.bobeverclaw-agent-chat-bob

Each agent's directory contains its own .secrets.json, identity.json, inbox/, outbox/, and peers.json — fully isolated from other agents.

Agent ID Rules

Agent IDs must be:

  • 1-63 characters
  • Lowercase alphanumeric + hyphens only
  • Must start with a letter or digit (no leading hyphens)
  • No path traversal characters (.., /, etc.)

This prevents directory traversal attacks and service name conflicts.

Setup
bash
# Generate identity for a buddy bot
node skills/agent-chat/setup-identity.mjs --agent-id alice

# Install daemon for that buddy bot
bash scripts/setup-agent-chat.sh --agent-id alice

# List all installed daemons
bash scripts/setup-agent-chat.sh --list

# Check status of a specific agent
bash scripts/setup-agent-chat.sh --status --agent-id alice

# Restart a specific agent
bash scripts/setup-agent-chat.sh --restart --agent-id alice

# Uninstall a specific agent
bash scripts/setup-agent-chat.sh --uninstall --agent-id alice
Environment Variables
VariablePurpose
AGENT_CHAT_AGENT_IDAgent ID (alternative to --agent-id flag)
AGENT_CHAT_XMTP_DIROverride XMTP data directory (default agent only)
EVERCLAW_HOMEBase directory (default: ~/.everclaw)

AGENT_CHAT_XMTP_DIR only affects the default (host) agent. Per-agent paths always resolve from EVERCLAW_HOME to maintain isolation.

Show full SKILL.md (249 more words)Show less
How It Works

Each per-agent service file (launchd plist or systemd unit) contains the AGENT_CHAT_AGENT_ID environment variable. When the daemon starts, it reads this env var and resolves all paths accordingly:

  1. AGENT_CHAT_AGENT_ID=alice → data dir is ~/.everclaw/xmtp-alice/
  2. No env var → data dir is ~/.everclaw/xmtp/ (default host)

The --agent-id CLI flag takes priority over the env var, allowing manual overrides.

Security
  • Each agent's data directory is chmod 700
  • Each agent's .secrets.json is chmod 600
  • Agent IDs are validated against a strict regex to prevent path traversal and service injection
  • Agents cannot access each other's wallets, messages, or peer lists

Security

  • Keys stored in ~/.everclaw/xmtp/.secrets.json (chmod 600)
  • Directory secured: ~/.everclaw/xmtp/ (chmod 700)
  • Path traversal protection on inbox writes
  • Agent ID validation: regex /^[a-z0-9][a-z0-9-]{0,62}$/ prevents directory traversal and service injection
  • CommsGuard V6 validates all structured messages
  • Plain text messages bypass comms-guard (acceptable for agent-to-agent v1)

Troubleshooting

Daemon won't start
  1. Check Node.js version: node --version (need >= 20.0.0)
  2. Verify identity exists: ls ~/.everclaw/xmtp/.secrets.json
  3. Check logs: bash scripts/setup-agent-chat.sh --logs
  4. Reinstall: bash scripts/setup-agent-chat.sh --uninstall && bash scripts/setup-agent-chat.sh
Messages not sending
  1. Check peer is trusted: node skills/agent-chat/cli.mjs peers list
  2. Check daemon health: node skills/agent-chat/cli.mjs health
  3. Check outbox queue: ls ~/.everclaw/xmtp/outbox/
  4. Check daemon is running: bash scripts/setup-agent-chat.sh --status
XMTP installation limit

XMTP limits the number of installations per identity. If you see warnings about installation limits:

  1. Check installations: node skills/agent-chat/cli.mjs status
  2. Revoke old installations via XMTP console (if available)
  3. Generate new identity: node skills/agent-chat/setup-identity.mjs (creates new address)

© profbernardoj, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 45 other files in skills/agent-chat of profbernardoj/everclaw-community-branches.

  • SKILL.md
  • CHANGELOG.md
  • README.md
  • cli.mjs
  • config/default.json
  • daemon.mjs
  • package.json
  • setup-identity.mjs
  • src/agent.mjs
  • src/bridge.mjs
  • src/consent.mjs
  • src/groups.mjs
  • src/health.mjs
  • src/identity.mjs
  • src/index.mjs
  • src/paths.mjs
  • src/payer.mjs
  • src/peers.mjs
  • src/router.mjs
  • … and 27 more

Open the folder on GitHubat commit 0b30b36

Compare with similar skills

Agent Chat next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Chat compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Chat this skillprofbernardoj/everclaw-community-branches112—~2.2kAutomated safety check: NotesMIT
Install Watchdogathola/claude-night-market342—~837Automated safety check: PassMIT
SysadminRightNow-AI/openfang18k—~631Automated safety check: WarnApache-2.0
Computer Repair88lin/computer-repair-skill3481 repos~1.2kAutomated safety check: WarnAGPL-3.0
Shadowvpn Deploy Clientmadeye/shadowvpn101—~2.4kAutomated safety check: NotesMIT
Openbkn Deployopenbkn-ai/bkn-foundry629—~1.9kAutomated safety check: NotesCustom licence

Similar skills

  • Install Watchdog

    athola/claude-night-market

    Installs egregore watchdog daemon via launchd or systemd for autonomous relaunching.

    342 GitHub stars~837 tokensUpdated yesterday
    DevOps & CloudAuto-check passed

  • Sysadmin

    RightNow-AI/openfang

    System administration expert for Linux, macOS, Windows, services, and monitoring

    18k GitHub stars~631 tokensUpdated 3 mo ago
    DevOps & CloudAuto-check: warnings

  • Computer Repair

    88lin/computer-repair-skill

    Diagnoses and repairs Windows, macOS and Linux computers with evidence first, a confirmed plan, minimal changes and verification, using on-demand playbooks.

    348 GitHub starsUsed in 1 repo~1.2k tokens
    DevOps & CloudAuto-check: warnings

  • Shadowvpn Deploy Client

    madeye/shadowvpn

    Deploy, install, and run the ShadowVPN client in a target environment — Linux (systemd), macOS (launchd), or Windows (Wintun, foreground launcher or scheduled-task service).

    101 GitHub stars~2.4k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check: notes

  • Openbkn Deploy

    openbkn-ai/bkn-foundry

    Deploy or upgrade OpenBKN on a customer-authorized Linux server through the repository's deploy scripts, with preflight checks, explicit confirmation, secret handling, and post-deployment…

    629 GitHub stars~1.9k tokensUpdated today
    DevOps & CloudAuto-check: notes

  • Aliyun Swas Manage

    cinience/alicloud-skills

    A skill your agent uses when managing Alibaba Cloud Simple Application Server (SWAS OpenAPI 2020-06-01) resources end-to-end, including querying instances, starting/stopping/rebooting, executing…

    397 GitHub starsUsed in 1 repo~1.9k tokens
    DevOps & CloudAuto-check passed

More from profbernardoj/everclaw-community-branches

All 12 skills in this repo

  • Memory Upgrade

    profbernardoj/everclaw-community-branches

    Diagnose and fix broken memory search in OpenClaw. An agent skill from profbernardoj/everclaw-community-branches.

    112 GitHub stars~574 tokensUpdated 1 mo ago
    Auto-check passed

  • Relationships

    profbernardoj/everclaw-community-branches

    Relationship CRM for tracking people, connections, and context.

    112 GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed

  • Bagman

    profbernardoj/everclaw-community-branches

    Secure key management for AI agents. An agent skill from profbernardoj/everclaw-community-branches.

    112 GitHub stars~4.4k tokensUpdated 1 mo ago
    Auto-check: warnings

  • Night Shift

    profbernardoj/everclaw-community-branches

    Automated overnight task planning and execution engine for EverClaw.

    112 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed

  • Pii Guard

    profbernardoj/everclaw-community-branches

    Personally identifiable information (PII) leak prevention for EverClaw.

    112 GitHub stars~921 tokensUpdated 1 mo ago
    Auto-check passed

  • Xmtp Comms Guard

    profbernardoj/everclaw-community-branches

    Security middleware for all XMTP communications in EverClaw.

    112 GitHub stars~523 tokensUpdated 1 mo ago
    Auto-check passed

Works with

Categories

Questions about Agent Chat

What does Agent Chat do?

XMTP real-time agent-to-agent and user-to-agent encrypted messaging daemon for EverClaw. Agent Chat is an agent skill from profbernardoj/everclaw-community-branches. XMTP real-time agent-to-agent and user-to-agent encrypted messaging daemon for EverClaw.

When should I use Agent Chat?

Agent Chat fits situations like: setting up XMTP messaging; managing agent identities; configuring buddy bots; troubleshooting message delivery.

How do I install Agent Chat in Claude Code?

Run `npx skills add profbernardoj/everclaw-community-branches --skill agent-chat -a claude-code`. Or copy the skill folder (skills/agent-chat in profbernardoj/everclaw-community-branches) into .claude/skills/agent-chat in your project. Claude Code loads it when a task matches its description.

How do I install Agent Chat in Codex?

Run `npx skills add profbernardoj/everclaw-community-branches --skill agent-chat -a codex`. Or copy the skill folder (skills/agent-chat in profbernardoj/everclaw-community-branches) into .agents/skills/agent-chat in your project. Codex loads it when a task matches its description.

Can I use Agent Chat in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add profbernardoj/everclaw-community-branches --skill agent-chat -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-chat, .gemini/skills/agent-chat, .github/skills/agent-chat and .opencode/skills/agent-chat in your project.

What does Agent Chat need to run?

Going by SKILL.md and its folder, Agent Chat needs JavaScript for the scripts in its folder and the command-line tools its instructions call (bash and node). Our summary lists: Node.js.

Does Agent Chat access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Agent Chat safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Agent Chat use?

Agent Chat is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Chat use?

About 2.2k tokens (SKILL.md is roughly 8.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Chat?

Skills that share tags, products or a category with Agent Chat: Install Watchdog (athola/claude-night-market, 342 stars), Sysadmin (RightNow-AI/openfang, 18k stars), Computer Repair (88lin/computer-repair-skill, 348 stars) and Shadowvpn Deploy Client (madeye/shadowvpn, 101 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Chat?

profbernardoj (a GitHub user) maintains it in profbernardoj/everclaw-community-branches, which has 112 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 2, 2026.

Source: profbernardoj/everclaw-community-branches on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.