packages/extension-agent/resources/skills/agentcli/SKILL.md
Use this skill to inspect or change ChatLuna agent admin state — skills, sub-agents, tools, MCP servers, MCP tools, or permission rules. The skill edits a working copy of the agent config inside the sandbox; the user must run `chatluna.agent sync` to write changes back to the host instance.
npx skillsauth add chatlunalab/chatluna agentcliInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill ships a CLI that runs inside the sandbox via the bash tool. It
reads and writes a working copy of the agent config materialized next to the
script (config.json in this skill folder). Local edits do not take
effect until the user runs chatluna.agent sync on the host instance.
Run the script through the bash tool:
node "<skill-dir>/bin/agentcli.cjs" <command> [args...]
<skill-dir> is the location reported in the skill prompt (or by
agentcli.cjs --skill-dir). Always quote paths.
node bin/agentcli.cjs show overview
node bin/agentcli.cjs show skills
node bin/agentcli.cjs show skill <name|id>
node bin/agentcli.cjs show subagents
node bin/agentcli.cjs show subagent <selector>
node bin/agentcli.cjs show tools
node bin/agentcli.cjs show tool <name>
node bin/agentcli.cjs show mcp servers
node bin/agentcli.cjs show mcp server <name>
node bin/agentcli.cjs show mcp tools
node bin/agentcli.cjs show mcp tool <name>
# skills
node bin/agentcli.cjs enable skill <name|id...>
node bin/agentcli.cjs disable skill <name|id...>
node bin/agentcli.cjs remove skill <name|id...>
# sub-agents
node bin/agentcli.cjs enable subagent <selector...>
node bin/agentcli.cjs disable subagent <selector...>
node bin/agentcli.cjs remove subagent <selector...>
node bin/agentcli.cjs set subagent <selector...> <tools|skills|mcp|computer> <all|allow|deny|inherit> [items...]
# tools
node bin/agentcli.cjs enable tool <name...> [--main]
node bin/agentcli.cjs disable tool <name...> [--main]
node bin/agentcli.cjs set tool <name...> <enabled|main|chatluna|character|group|private|authority|subagents> <value> [items...]
# mcp
node bin/agentcli.cjs set mcp tool <name...> enabled <bool>
node bin/agentcli.cjs save mcp server <name> json '<json>'
node bin/agentcli.cjs remove mcp server <name...>
Each write rewrites config.json in place and keeps a config.json.bak.
node bin/agentcli.cjs show overview to understand the current state.show ... after the edit.chatluna.agent sync. That
validates the working copy and atomically replaces the live config.skill-creator or sub-agent-creator first. Place those files under the
sandbox skill / sub-agent directories shown by show overview. The same
chatluna.agent sync command flushes them back to the host.show overview.show output is
derived from the working copy of config.json plus a scan of the sandbox
skill / sub-agent directories. Treat it as authoritative for config; for
runtime state, the host chatluna.agent console remains the source of
truth.chatluna.agent sync.tools
Create, edit, convert, or audit ChatLuna sub-agent markdown files. Use when adding a new sub-agent, refining a sub-agent prompt, choosing a sub-agent's goal and output contract, restricting tools, skills, MCP, or computer permissions, pinning or omitting a model, setting maxTurns, placing agents under local `data/chatluna/agents`, writing them into a remote sandbox before `agentcli sync`, or converting Claude or OpenCode agent files into ChatLuna-compatible sub-agents.
testing
Create, edit, improve, or audit AgentSkills. Use when creating a new skill from scratch or when asked to improve, review, audit, tidy up, or clean up an existing skill or SKILL.md file. Also use when editing or restructuring a skill directory (moving files to references/ or scripts/, removing stale content, validating against the AgentSkills spec). Triggers on phrases like "create a skill", "author a skill", "tidy up a skill", "improve this skill", "review the skill", "clean up the skill", "audit the skill".
tools
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (spawn in temp dir), (3) refactoring large codebases, (4) iterative coding that needs file exploration. NOT for: simple one-liner fixes (just edit), reading code (use read tool), thread-bound ACP harness requests in chat (for example spawn/run Codex or Claude Code in a Discord thread; use sessions_spawn with runtime:"acp"), or any work in ~/clawd workspace (never spawn agents here). Claude Code: use --print --permission-mode bypassPermissions (no PTY). Codex/Pi/OpenCode: pty:true required.
tools
Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.