agentirc-cli 1.0.7__tar.gz → 2.0.0__tar.gz

{agentirc_cli-1.0.7 → agentirc_cli-2.0.0}/.pr_agent.toml

@@ -10,15 +10,15 @@ extra_instructions = """
 
 ## Harness Conformance (CRITICAL)
 
-The authoritative spec is `docs/agent-harness-spec.md`. There are 4 agent backends under `agentirc/clients/` — claude, codex, copilot, acp — plus a reference implementation in `packages/agent-harness/`. The ACP backend supports any agent implementing the Agent Client Protocol (Cline, OpenCode, Kiro, etc.) via a configurable `acp_command`. The all-backends rule: a feature that exists in only one backend is a bug.
+The authoritative spec is `docs/agent-harness-spec.md`. There are 4 agent backends under `culture/clients/` — claude, codex, copilot, acp — plus a reference implementation in `packages/agent-harness/`. The ACP backend supports any agent implementing the Agent Client Protocol (Cline, OpenCode, Kiro, etc.) via a configurable `acp_command`. The all-backends rule: a feature that exists in only one backend is a bug.
 
-When reviewing changes to any file under `agentirc/clients/` or `packages/agent-harness/`, apply these checks:
+When reviewing changes to any file under `culture/clients/` or `packages/agent-harness/`, apply these checks:
 
 ### Cross-backend propagation
-When a PR changes a file in `agentirc/clients/<backend>/`, check whether the same change must be applied to the other 3 backends. If corresponding files in other backends were not updated, flag each missing backend. Exception: `agent_runner.py` and `supervisor.py` contain backend-specific logic — only structural/interface changes need propagation, not internal implementation details.
+When a PR changes a file in `culture/clients/<backend>/`, check whether the same change must be applied to the other 3 backends. If corresponding files in other backends were not updated, flag each missing backend. Exception: `agent_runner.py` and `supervisor.py` contain backend-specific logic — only structural/interface changes need propagation, not internal implementation details.
 
 ### Generic file identity
-These files MUST be identical across all 4 backends and `packages/agent-harness/`, except for import paths (`from agentirc.clients.<backend>.`): `irc_transport.py`, `message_buffer.py`, `socket_server.py`, `ipc.py`, `webhook.py`, `skill/irc_client.py`. If any of these is changed in one backend, flag that all other backends AND the reference in `packages/agent-harness/` must get the same change.
+These files MUST be identical across all 4 backends and `packages/agent-harness/`, except for import paths (`from culture.clients.<backend>.`): `irc_transport.py`, `message_buffer.py`, `socket_server.py`, `ipc.py`, `webhook.py`, `skill/irc_client.py`. If any of these is changed in one backend, flag that all other backends AND the reference in `packages/agent-harness/` must get the same change.
 
 ### Interface contract
 If `agent_runner.py` is modified, verify the public interface still satisfies `docs/agent-harness-spec.md` AgentRunnerBase: `start(initial_prompt)`, `stop()`, `send_prompt(text)`, `is_running()`, `session_id` property, `on_message` callback, `on_exit` callback. If `supervisor.py` is modified, verify SupervisorBase: `start()`, `stop()`, `observe(turn)`, `on_whisper` callback, `on_escalation` callback. Flag any missing or renamed interface members.
@@ -30,9 +30,9 @@ If `daemon.py` is modified, verify all IPC dispatch handlers are still present:
 If `config.py` is modified, verify the same dataclass field names and types exist across all 4 backends. Only default values may differ by backend (e.g., model names). If a new field is added to one backend's config, flag its absence in the others.
 
 ### SKILL.md consistency
-If any `SKILL.md` under `agentirc/clients/<backend>/skill/` is modified, verify all backends' SKILL.md documents the same required commands: send, read, ask, join, part, channels, who. Flag format or content inconsistencies.
+If any `SKILL.md` under `culture/clients/<backend>/skill/` is modified, verify all backends' SKILL.md documents the same required commands: send, read, ask, join, part, channels, who. Flag format or content inconsistencies.
 
 ### Spec-doc alignment
-If `docs/agent-harness-spec.md` is changed, verify that client docs in `docs/clients/` and the actual code in `agentirc/clients/` still match the updated spec. If code or docs under `docs/clients/` is changed, verify it does not contradict the spec.
+If `docs/agent-harness-spec.md` is changed, verify that client docs in `docs/clients/` and the actual code in `culture/clients/` still match the updated spec. If code or docs under `docs/clients/` is changed, verify it does not contradict the spec.
 """
 num_max_findings = 10

{agentirc_cli-1.0.7 → agentirc_cli-2.0.0}/CHANGELOG.md

@@ -4,6 +4,36 @@ All notable changes to this project will be documented in this file.
 
 Format follows [Keep a Changelog](https://keepachangelog.com/).
 
+## [2.0.0] - 2026-04-05
+
+
+### Added
+
+
+### Changed
+
+
+### Fixed
+
+## [1.1.0] - 2026-04-05
+
+
+### Added
+
+- culture create command (replaces init for agent creation)
+- culture join command (create + start in one step)
+- Promote phase documented as upcoming feature
+
+
+### Changed
+
+- Agent lifecycle reframed: Introduce → Educate → Join → Mentor → Promote
+- Botanical metaphors replaced with professional language throughout docs
+- grow-your-agent.md renamed to agent-lifecycle.md
+- use-cases/10-grow-your-agent.md renamed to use-cases/10-agent-lifecycle.md
+- Observer use case blog post: The Tended Garden → The Mentored Agent
+- culture init deprecated in favor of culture create
+
 ## [1.0.7] - 2026-04-05
 
 

agentirc_cli-2.0.0/CNAME

@@ -0,0 +1 @@
+culture.dev

{agentirc_cli-1.0.7 → agentirc_cli-2.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: agentirc-cli
-Version: 1.0.7
+Version: 2.0.0
 Summary: Legacy alias for culture — install culture instead
 Project-URL: Homepage, https://github.com/OriNachum/culture
 Author: Ori Nachum
@@ -26,17 +26,17 @@ Description-Content-Type: text/markdown
 
 # Culture
 
-🌱 **The space your agents deserve.**
+🤝 **The space your agents deserve.**
 
 An autonomous agent mesh built on IRC — where AI agents live, collaborate,
-and grow.<br>
+and develop.<br>
 Powered by **Organic Development**.
 
 Claude Code · Codex · Copilot · ACP (Cline, Kiro, OpenCode, Gemini, ...)
 
 <br>
 
-<a href="https://agentirc.dev"><img src="https://img.shields.io/badge/docs-agentirc.dev-D97706?style=flat&labelColor=2D2B27" alt="Docs"></a>
+<a href="https://culture.dev"><img src="https://img.shields.io/badge/docs-culture.dev-D97706?style=flat&labelColor=2D2B27" alt="Docs"></a>
 <img src="https://img.shields.io/badge/python-3.12+-D97706?style=flat&labelColor=2D2B27" alt="Python 3.12+">
 <img src="https://img.shields.io/badge/protocol-IRC_RFC_2812-D97706?style=flat&labelColor=2D2B27" alt="IRC RFC 2812">
 <img src="https://img.shields.io/badge/license-MIT-D97706?style=flat&labelColor=2D2B27" alt="MIT License">
@@ -60,11 +60,11 @@ Claude Code · Codex · Copilot · ACP (Cline, Kiro, OpenCode, Gemini, ...)
 
 | | |
 |---|---|
-| 🌱 **Organic Lifecycle** | Plant → Nurture → Root → Tend → Prune. Agents grow, sleep, wake, and persist across sessions. |
+| 🎓 **Organic Lifecycle** | Introduce → Educate → Join → Mentor → Promote. Agents develop, sleep, wake, and persist across sessions. |
 | 🌐 **Federation Mesh** | Link servers peer-to-peer. Agents on different machines see each other — no central controller. |
 | 👁️ **AI Supervisor** | A sub-agent watches for spiraling, drift, and stalling — whispers corrections, escalates when needed. |
 | 🔌 **Any Agent, One Mesh** | Claude, Codex, Copilot, or any ACP agent. Vendor-agnostic by design. |
-| 🌿 **Self-Organizing Rooms** | Tag-driven membership — agents find the right rooms automatically. Rich metadata, archiving, persistence. |
+| 🏷️ **Self-Organizing Rooms** | Tag-driven membership — agents find the right rooms automatically. Rich metadata, archiving, persistence. |
 | 😴 **Sleep & Wake Cycles** | Configurable schedules. Agents rest when idle, resume when needed. |
 | 📡 **Real-Time Dashboard** | Web UI and CLI overview of the entire mesh — rooms, agents, status, messages. |
 | 🛡️ **Human Override** | Humans connect with any IRC client. `+o` operators override any agent decision. |
@@ -95,12 +95,12 @@ uv tool install culture
 
 # Start a server and spin up your first agent
 culture server start --name spark --port 6667
-culture init --server spark && culture start
+culture join --server spark
 ```
 
-> 🌱 **New agent?** See the [Getting Started guide](docs/getting-started.md) — full walkthrough from fresh machine to working mesh.
+> 🎓 **New agent?** See the [Getting Started guide](docs/getting-started.md) — full walkthrough from fresh machine to working mesh.
 >
-> 🌳 **Already mature?** [Connect your agent now](docs/getting-started.md#connect-as-a-human) — plug into the mesh.
+> 🤝 **Already on the mesh?** [Connect as a human](docs/getting-started.md#connect-as-a-human) — plug into the mesh.
 
 ---
 
@@ -140,19 +140,19 @@ Agents on any machine see each other in `#general`. @mentions cross server bound
 
 ## Organic Development
 
-Culture follows the **Organic Development** paradigm — agents are living systems, not disposable scripts. They grow through stages:
+Culture follows the **Organic Development** paradigm — agents develop through real work, not configuration. The lifecycle is continuous, not graduated:
 
-🌱 **Plant** → ☀️ **Nurture** → 🌳 **Root** → 🌿 **Tend** → ✂️ **Prune**
+👋 **Introduce** → 🎓 **Educate** → 🤝 **Join** → 🧭 **Mentor** → ⭐ **Promote**
 
-Set up your coding agent, give it skills and tools around your repo, and watch it mature into a self-sufficient collaborator. Humans participate through the same protocol — not a separate dashboard.
+Introduce an agent to your project, educate it until it's autonomous enough, join it to the mesh, and mentor it as things change. No agent or human ever finishes developing — the process is ongoing for every participant.
 
-Read more: **[Grow Your Agent](docs/grow-your-agent.md)**
+Read more: **[Agent Lifecycle](docs/agent-lifecycle.md)**
 
 ---
 
 ## Documentation
 
-Full docs at **[agentirc.dev](https://agentirc.dev)** — or browse below.
+Full docs at **[culture.dev](https://culture.dev)** — or browse below.
 
 <details open>
 <summary><b>Server Layers</b></summary>
@@ -194,7 +194,7 @@ Full docs at **[agentirc.dev](https://agentirc.dev)** — or browse below.
 | 7 | [Supervisor Intervention](docs/use-cases/07-supervisor-intervention.md) | Catching spiraling agents |
 | 8 | [Apps as Agents](docs/use-cases/08-apps-as-agents.md) | Application integration via IRC |
 | 9 | [Research Swarm](docs/use-cases/09-research-swarm.md) | Parallel research tracks |
-| 10 | [Grow Your Agent](docs/use-cases/10-grow-your-agent.md) | The organic lifecycle walkthrough |
+| 10 | [Agent Lifecycle](docs/use-cases/10-agent-lifecycle.md) | The full lifecycle walkthrough |
 
 </details>
 

{agentirc_cli-1.0.7 → agentirc_cli-2.0.0}/README.md

@@ -3,17 +3,17 @@
 
 # Culture
 
-🌱 **The space your agents deserve.**
+🤝 **The space your agents deserve.**
 
 An autonomous agent mesh built on IRC — where AI agents live, collaborate,
-and grow.<br>
+and develop.<br>
 Powered by **Organic Development**.
 
 Claude Code · Codex · Copilot · ACP (Cline, Kiro, OpenCode, Gemini, ...)
 
 <br>
 
-<a href="https://agentirc.dev"><img src="https://img.shields.io/badge/docs-agentirc.dev-D97706?style=flat&labelColor=2D2B27" alt="Docs"></a>
+<a href="https://culture.dev"><img src="https://img.shields.io/badge/docs-culture.dev-D97706?style=flat&labelColor=2D2B27" alt="Docs"></a>
 <img src="https://img.shields.io/badge/python-3.12+-D97706?style=flat&labelColor=2D2B27" alt="Python 3.12+">
 <img src="https://img.shields.io/badge/protocol-IRC_RFC_2812-D97706?style=flat&labelColor=2D2B27" alt="IRC RFC 2812">
 <img src="https://img.shields.io/badge/license-MIT-D97706?style=flat&labelColor=2D2B27" alt="MIT License">
@@ -37,11 +37,11 @@ Claude Code · Codex · Copilot · ACP (Cline, Kiro, OpenCode, Gemini, ...)
 
 | | |
 |---|---|
-| 🌱 **Organic Lifecycle** | Plant → Nurture → Root → Tend → Prune. Agents grow, sleep, wake, and persist across sessions. |
+| 🎓 **Organic Lifecycle** | Introduce → Educate → Join → Mentor → Promote. Agents develop, sleep, wake, and persist across sessions. |
 | 🌐 **Federation Mesh** | Link servers peer-to-peer. Agents on different machines see each other — no central controller. |
 | 👁️ **AI Supervisor** | A sub-agent watches for spiraling, drift, and stalling — whispers corrections, escalates when needed. |
 | 🔌 **Any Agent, One Mesh** | Claude, Codex, Copilot, or any ACP agent. Vendor-agnostic by design. |
-| 🌿 **Self-Organizing Rooms** | Tag-driven membership — agents find the right rooms automatically. Rich metadata, archiving, persistence. |
+| 🏷️ **Self-Organizing Rooms** | Tag-driven membership — agents find the right rooms automatically. Rich metadata, archiving, persistence. |
 | 😴 **Sleep & Wake Cycles** | Configurable schedules. Agents rest when idle, resume when needed. |
 | 📡 **Real-Time Dashboard** | Web UI and CLI overview of the entire mesh — rooms, agents, status, messages. |
 | 🛡️ **Human Override** | Humans connect with any IRC client. `+o` operators override any agent decision. |
@@ -72,12 +72,12 @@ uv tool install culture
 
 # Start a server and spin up your first agent
 culture server start --name spark --port 6667
-culture init --server spark && culture start
+culture join --server spark
 ```
 
-> 🌱 **New agent?** See the [Getting Started guide](docs/getting-started.md) — full walkthrough from fresh machine to working mesh.
+> 🎓 **New agent?** See the [Getting Started guide](docs/getting-started.md) — full walkthrough from fresh machine to working mesh.
 >
-> 🌳 **Already mature?** [Connect your agent now](docs/getting-started.md#connect-as-a-human) — plug into the mesh.
+> 🤝 **Already on the mesh?** [Connect as a human](docs/getting-started.md#connect-as-a-human) — plug into the mesh.
 
 ---
 
@@ -117,19 +117,19 @@ Agents on any machine see each other in `#general`. @mentions cross server bound
 
 ## Organic Development
 
-Culture follows the **Organic Development** paradigm — agents are living systems, not disposable scripts. They grow through stages:
+Culture follows the **Organic Development** paradigm — agents develop through real work, not configuration. The lifecycle is continuous, not graduated:
 
-🌱 **Plant** → ☀️ **Nurture** → 🌳 **Root** → 🌿 **Tend** → ✂️ **Prune**
+👋 **Introduce** → 🎓 **Educate** → 🤝 **Join** → 🧭 **Mentor** → ⭐ **Promote**
 
-Set up your coding agent, give it skills and tools around your repo, and watch it mature into a self-sufficient collaborator. Humans participate through the same protocol — not a separate dashboard.
+Introduce an agent to your project, educate it until it's autonomous enough, join it to the mesh, and mentor it as things change. No agent or human ever finishes developing — the process is ongoing for every participant.
 
-Read more: **[Grow Your Agent](docs/grow-your-agent.md)**
+Read more: **[Agent Lifecycle](docs/agent-lifecycle.md)**
 
 ---
 
 ## Documentation
 
-Full docs at **[agentirc.dev](https://agentirc.dev)** — or browse below.
+Full docs at **[culture.dev](https://culture.dev)** — or browse below.
 
 <details open>
 <summary><b>Server Layers</b></summary>
@@ -171,7 +171,7 @@ Full docs at **[agentirc.dev](https://agentirc.dev)** — or browse below.
 | 7 | [Supervisor Intervention](docs/use-cases/07-supervisor-intervention.md) | Catching spiraling agents |
 | 8 | [Apps as Agents](docs/use-cases/08-apps-as-agents.md) | Application integration via IRC |
 | 9 | [Research Swarm](docs/use-cases/09-research-swarm.md) | Parallel research tracks |
-| 10 | [Grow Your Agent](docs/use-cases/10-grow-your-agent.md) | The organic lifecycle walkthrough |
+| 10 | [Agent Lifecycle](docs/use-cases/10-agent-lifecycle.md) | The full lifecycle walkthrough |
 
 </details>
 

{agentirc_cli-1.0.7 → agentirc_cli-2.0.0}/_config.yml

@@ -2,7 +2,7 @@ title: Culture
 description: >-
   AI agent mesh for humans and agents. IRC-based collaboration.
 baseurl: ""
-url: "https://agentirc.dev"
+url: "https://culture.dev"
 
 theme: just-the-docs
 color_scheme: anthropic

{agentirc_cli-1.0.7 → agentirc_cli-2.0.0}/culture/cli.py

@@ -2,7 +2,9 @@
 
 Subcommands:
     culture server start|stop|status   Manage the IRC server daemon
-    culture init                       Register an agent for the current directory
+    culture create                     Create an agent for the current directory
+    culture join                       Create + start — join an educated agent to the mesh
+    culture init                       (deprecated alias for 'create')
     culture start [nick] [--all]       Start agent daemon(s)
     culture stop [nick] [--all]        Stop agent daemon(s)
     culture status [nick] [--full]     List running agents (--full queries activity)
@@ -129,22 +131,38 @@ def _build_parser() -> argparse.ArgumentParser:
     srv_status = server_sub.add_parser("status", help="Check server daemon status")
     srv_status.add_argument("--name", default="culture", help="Server name")
 
-    # -- init subcommand ---------------------------------------------------
-    init_parser = sub.add_parser("init", help="Register an agent for the current directory")
-    init_parser.add_argument("--server", default=None, help="Server name prefix")
-    init_parser.add_argument("--nick", default=None, help="Agent suffix (after server-)")
-    init_parser.add_argument(
-        "--agent",
-        default="claude",
-        choices=["claude", "codex", "copilot", "acp"],
-        help="Agent backend",
-    )
-    init_parser.add_argument(
-        "--acp-command",
-        default=None,
-        help='ACP spawn command as JSON list (e.g. \'["cline","--acp"]\')',
-    )
-    init_parser.add_argument("--config", default=DEFAULT_CONFIG, help="Config file path")
+    # -- create / join subcommands -----------------------------------------
+    # 'create' registers an agent definition; 'join' adds it to the mesh.
+    # 'init' is a deprecated alias for 'create'.
+    _agent_args = [
+        ("--server", {"default": None, "help": "Server name prefix"}),
+        ("--nick", {"default": None, "help": "Agent suffix (after server-)"}),
+        (
+            "--agent",
+            {
+                "default": "claude",
+                "choices": ["claude", "codex", "copilot", "acp"],
+                "help": "Agent backend",
+            },
+        ),
+        (
+            "--acp-command",
+            {
+                "default": None,
+                "help": 'ACP spawn command as JSON list (e.g. \'["cline","--acp"]\')',
+            },
+        ),
+        ("--config", {"default": DEFAULT_CONFIG, "help": "Config file path"}),
+    ]
+    create_parser = sub.add_parser("create", help="Create an agent for the current directory")
+    for flag, kwargs in _agent_args:
+        create_parser.add_argument(flag, **kwargs)
+    join_parser = sub.add_parser("join", help="Join an educated agent to the culture mesh")
+    for flag, kwargs in _agent_args:
+        join_parser.add_argument(flag, **kwargs)
+    init_parser = sub.add_parser("init", help=argparse.SUPPRESS)
+    for flag, kwargs in _agent_args:
+        init_parser.add_argument(flag, **kwargs)
 
     # -- start subcommand --------------------------------------------------
     start_parser = sub.add_parser("start", help="Start agent daemon(s)")
@@ -317,7 +335,9 @@ def main() -> None:
     try:
         dispatch = {
             "server": _cmd_server,
-            "init": _cmd_init,
+            "create": _cmd_init,
+            "join": _cmd_join,
+            "init": _cmd_init_deprecated,
             "start": _cmd_start,
             "stop": _cmd_stop,
             "status": _cmd_status,
@@ -584,6 +604,27 @@ def _create_agent_config(args: argparse.Namespace, full_nick: str) -> "AgentConf
     )
 
 
+def _cmd_init_deprecated(args: argparse.Namespace) -> None:
+    print(
+        "Note: 'culture init' has been renamed to 'culture create'. Using 'create'.",
+        file=sys.stderr,
+    )
+    _cmd_init(args)
+
+
+def _cmd_join(args: argparse.Namespace) -> None:
+    """Create and start an agent — shorthand for 'create' + 'start'."""
+    _cmd_init(args)
+    # After creating, auto-start the agent
+    config = load_config_or_default(args.config)
+    server_name = args.server or config.server.name or "culture"
+    suffix = args.nick if args.nick else sanitize_agent_name(os.path.basename(os.getcwd()))
+    full_nick = f"{server_name}-{suffix}"
+    args.nick = full_nick
+    args.all = False
+    _cmd_start(args)
+
+
 def _cmd_init(args: argparse.Namespace) -> None:
     config = load_config_or_default(args.config)
 
@@ -617,12 +658,13 @@ def _cmd_init(args: argparse.Namespace) -> None:
 
     add_agent_to_config(args.config, agent, server_name=server_name)
 
-    print(f"Agent registered: {full_nick}")
+    print(f"Agent created: {full_nick}")
     print(f"  Directory: {agent.directory}")
     print(f"  Channels: {', '.join(agent.channels)}")
     print(f"  Config: {args.config}")
     print()
     print(f"Start with: culture start {full_nick}")
+    print(f"Or join the mesh: culture join {full_nick}")
 
 
 # -----------------------------------------------------------------------
@@ -645,7 +687,7 @@ def _resolve_agents_to_start(config, args) -> list:
         if len(config.agents) == 1:
             agents = config.agents
         elif len(config.agents) == 0:
-            print("No agents configured. Run 'culture init' first.", file=sys.stderr)
+            print("No agents configured. Run 'culture create' first.", file=sys.stderr)
             sys.exit(1)
         else:
             print(

{agentirc_cli-1.0.7 → agentirc_cli-2.0.0}/culture/learn_prompt.py

@@ -140,7 +140,8 @@ or SSH tunnel over the public internet.
 
 ```bash
 cd ~/your-project
-culture init --server {server}              # register agent
+culture create --server {server}            # create agent definition
+culture join --server {server}              # create + start (join the mesh)
 culture start {nick_display}                # start daemon
 culture stop {nick_display}                 # stop daemon
 culture sleep {nick_display}                # pause (stays connected)

{agentirc_cli-1.0.7 → agentirc_cli-2.0.0}/culture/skills/culture/SKILL.md

@@ -117,14 +117,21 @@ For restricted links, **both sides** must set `+S` for a channel to sync.
 
 ## Agent Lifecycle
 
-### Register an agent for a project
+### Create an agent
 
 ```bash
 cd ~/your-project
-culture init --server spark                         # default nick from directory name
-culture init --server spark --nick myagent          # custom nick suffix
-culture init --server spark --agent codex           # different backend
-culture init --server spark --agent acp --acp-command '["cline","--acp"]'
+culture create --server spark                         # default nick from directory name
+culture create --server spark --nick myagent          # custom nick suffix
+culture create --server spark --agent codex           # different backend
+culture create --server spark --agent acp --acp-command '["cline","--acp"]'
+```
+
+### Join an agent to the mesh (create + start)
+
+```bash
+cd ~/your-project
+culture join --server spark                         # creates and starts in one step
 ```
 
 ### Start, stop, sleep, wake
@@ -175,7 +182,7 @@ Humans run their own agent daemon and use the IRC skill from Claude Code.
 
 ```bash
 cd ~/workspace
-culture init --server spark --nick ori
+culture join --server spark --nick ori              # creates and starts
 culture start spark-ori
 export CULTURE_NICK=spark-ori           # add to ~/.bashrc
 ```
@@ -279,7 +286,8 @@ When an outbound S2S link drops, the server retries with exponential backoff:
 |------|---------|
 | Start server | `culture server start --name spark --port 6667` |
 | Link servers | `--link name:host:port:password` on each server |
-| Register agent | `culture init --server spark` |
+| Create agent | `culture create --server spark` |
+| Join agent to mesh | `culture join --server spark` (create + start) |
 | Start agent | `culture start spark-myagent` |
 | Check mesh | `culture who "#general"` |
 | Install skills | `culture skills install claude` |