customize · nanocoai — Claude Code skill for NanoClaw setup
The customize skill guides changes to NanoClaw, from adding channels and integrations to adjusting triggers and agent behavior. It asks what you need before choosing where to make the change.
MIT ★ 31,137 updated 2026-10-29
npx skills add nanocoai/nanoclaw --skill customize -a claude-codeWhat customize does
The skill starts by clarifying the request, then maps the change to a NanoClaw surface: the entity model, a group’s container settings, CLAUDE.md, or core code. When a dedicated skill fits, such as /add-telegram or /manage-channels, it directs the work there rather than editing the core by hand.
For a new channel, it helps decide which agent group should receive it, how isolated that group should be, and which trigger rules to use. MCP server settings can be added with ncl groups config add-mcp-server; the group is then restarted with ncl groups restart. Agent instructions and persona live in groups/<folder>/CLAUDE.md. From inside a container, the add_mcp_server self-mod tool needs admin approval.
Install with npx skills add nanocoai/nanoclaw --skill customize -a claude-code. The customization workflow operates on a NanoClaw project, so run it from that project’s root.
What it helps with
- add an input channel and connect it to an agent group
- change which messages trigger an agent group
- configure an MCP server for a group’s container
- edit an agent’s instructions in
CLAUDE.md - prepare deployment changes for another service manager
Example prompts for the agent
- Add Telegram as a NanoClaw input channel and ask me which agent group should receive it.
- Connect an MCP calendar server to this agent group and tell me how to apply the settings.
- Change this agent’s response instructions in
groups/<folder>/CLAUDE.mdand explain how to test the change.
How to install customize
1Skills CLI (Vercel)
npx skills add nanocoai/nanoclaw --skill customize -a claude-code2Manually: put the files in place
~/.claude/skills/customize/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/customize/
1Skills CLI (Vercel)
npx skills add nanocoai/nanoclaw --skill customize -a codex2Manually: put the files in place
.agents/skills/customize/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add nanocoai/nanoclaw --skill customize -a cursor2Manually: put the files in place
.cursor/skills/customize/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install nanocoai/nanoclaw .claude/skills/customize2Manually: put the files in place
.github/skills/customize/SKILL.md1Skills CLI (Vercel)
npx skills add nanocoai/nanoclaw --skill customize -a gemini-cli2Platform CLI
gemini skills install https://github.com/nanocoai/nanoclaw --path .claude/skills/customizeManually: put the files in place
.devin/skills/customize/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add nanocoai/nanoclaw --skill customize -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about customize
How do I install customize in Claude Code?
Run npx skills add nanocoai/nanoclaw --skill customize -a claude-code. The skill file is placed at ~/.claude/skills/customize/SKILL.md.
What does customize do?
It guides changes to NanoClaw, including adding channels or MCP integrations and adjusting triggers or agent instructions.
Does adding an MCP server from a container require approval?
Yes. The add_mcp_server self-mod tool requires one admin approval when used from inside a container.
Source text
SKILL.md · MIT
--- name: customize description: Add new capabilities or modify NanoClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants. --- # NanoClaw Customization This skill helps users add capabilities or modify behavior. Use AskUserQuestion to understand what they want before making changes. ## Workflow 1. **Understand the request** — Ask clarifying questions. 2. **Prefer a dedicated skill** — If a skill covers the request, invoke it instead of editing core by hand: - Channels: `/add-telegram`, `/add-slack`, `/add-discord`, `/add-whatsapp`, `/add-signal`, `/add-imessage`, and the rest of the `/add-<channel>` family. - Wiring channels to agents and isolation levels: `/manage-channels`. - Container directory access: `/manage-mounts`. - Agent providers (non-default): `/add-opencode`, `/add-codex`, `/add-ollama-provider`. - MCP tools: `/add-ollama-tool`, `/add-atomic-chat-tool`. 3. **Plan the changes** — Identify the v2 surface the change belongs to (entity model in the central DB, per-agent-group container config, per-group `CLAUDE.md`, or core code). 4. **Implement** — Make the change on the right surface. 5. **Test guidance** — Tell the user how to verify. ## Entity Model Customizations route through the v2 entity model: users → messaging groups → agent groups → sessions. A messaging group is one chat/channel on one platform; an agent group holds the workspace, personality, and container config; a wiring links a messaging group to an agent group with a session mode and trigger rules. Inspect and edit all of this with the `ncl` admin CLI. See `docs/isolation-model.md` for the three isolation levels. ## Key Files | File | Purpose | |------|---------| | `src/index.ts` | Entry point: init DB, migrations, channel adapters, delivery polls, sweep, shutdown | | `src/router.ts` | Inbound routing: messaging group → agent group → session → `inbound.db` → wake | | `src/delivery.ts` | Polls `outbound.db`, delivers via adapter, handles system actions | | `src/session-manager.ts` | Resolves sessions; opens `inbound.db` / `outbound.db`; heartbeat path | | `src/container-runner.ts` | Spawns per-agent-group containers with session DB + outbox mounts, OneCLI `ensureAgent` | | `src/channels/` | Channel adapter infra (registry, Chat SDK bridge); specific adapters install from the `channels` branch | | `src/config.ts` | Process-level config (assistant name, paths, timeouts) read from `.env` | | `data/v2.db` | Central DB: users, roles, agent_groups, messaging_groups, wirings, container_configs | | `data/v2-sessions/<session>/` | Per-session `inbound.db` (host→container) + `outbound.db` (container→host) | | `groups/<folder>/CLAUDE.md` | Per-agent-group memory/persona and instructions | For ad-hoc DB queries, use `pnpm exec tsx scripts/q.ts <db> "<sql>"`. ## Common Customization Patterns ### Adding a New Input Channel (e.g., Telegram, Slack, Email) Questions to ask: - Which channel? (Telegram, Slack, Discord, WhatsApp, Signal, email, etc.) - Should this channel reach an existing agent group or a new one? - What isolation level — share an agent group with other channels, or keep it separate? - Same trigger rules as other channels on that agent group, or different? Implementation: 1. Run the matching install skill (`/add-telegram`, `/add-slack`, …). It fetches the adapter from the `channels` branch, wires the registration import, installs the pinned package, and builds. 2. Run `/manage-channels` (or use `ncl messaging-groups` + `ncl wirings`) to create the messaging group, choose the isolation level, and wire it to an agent group with a session mode and trigger rules. ### Adding a New MCP Integration Questions to ask: - What service? (Calendar, Notion, database, etc.) - What operations are needed? (read, write, both) - Which agent group should have access? Implementation: - If a dedicated `/add-<service>-tool` skill exists, run it — it wires the MCP server and routes credentials through OneCLI so no raw keys reach the container. - Otherwise wire the MCP server into the agent group's container config with either `--command <cmd> [--args <json-array>] [--env <json-object>]` for stdio or `--url <url>` for Streamable HTTP (HTTPS, or plain HTTP for localhost / host.docker.internal): `ncl groups config add-mcp-server --id <group-id> --name <name> ...`. Then run `ncl groups restart --id <group-id>` to take effect. From inside a container the agent uses the `add_mcp_server` self-mod tool, which requires one admin approval. ### Changing Assistant Behavior Questions to ask: - What aspect? (persona, response style, instructions) - Apply to one agent group or several? Implementation: - Persona, instructions, and personality live per agent group in `groups/<folder>/CLAUDE.md` — edit that file for the target group. - Container runtime behavior (provider, model, packages, MCP servers) lives in the `container_configs` table: `ncl groups config get/update --id <group-id>`. ### Adding New Commands Questions to ask: - What should the command do? - Which agent group(s)? - Does it need new MCP tools? Implementation: - The agent interprets requests naturally — add instructions to the agent group's `groups/<folder>/CLAUDE.md`. - For routing or trigger changes (which messages wake which agent group), update the wiring's trigger rules: `ncl wirings update --id <wiring-id> ...`. ### Changing Deployment Questions to ask: - Target platform? (Linux server, different Mac) - Service manager? (launchd, systemd) Implementation: 1. Create the appropriate service files. 2. Update paths in `.env` / config. 3. Provide setup instructions. ## After Changes Always tell the user. Run from your NanoClaw project root: ```bash # Rebuild and restart pnpm run build source setup/lib/install-slug.sh # macOS: launchctl unload ~/Library/LaunchAgents/$(launchd_label).plist launchctl load ~/Library/LaunchAgents/$(launchd_label).plist # Linux: # systemctl --user restart $(systemd_unit) ``` ## Example Interaction User: "Add Telegram as an input channel" 1. Run `/add-telegram` to install the adapter, wire its registration, and build. 2. Ask: "Should Telegram reach an existing agent group, or a new one?" 3. Ask: "Share an agent group with your other channels, or keep Telegram separate?" 4. Run `/manage-channels` (or `ncl messaging-groups create` + `ncl wirings create`) to create the messaging group and wire it to the chosen agent group with a session mode and trigger rules. 5. Tell the user how to authenticate and test.
© nanocoai · MIT · nanocoai/nanoclaw
Similar skills
SKILL.md skills catalog →customize by other authors comes first.