Manage Agent Capabilities
Enables, disables and configures agent features through the CLI instead of menus.
Install
npx skills add shareAI-lab/Kode-CLI --skill capabilities-manage -g -a claude-code -y- Repository
- shareAI-lab/Kode-CLI5.2k
- Category
- AI and agents
- Updated
- 6d ago
- License
- Apache-2.0
- Context cost
- Lightabout 630 tokens
- Runs scripts
- No, instructions only
What it does
Kode capability-management playbook: treat features (LSP, statusline, output styles, plugins, notifications) as configurable capabilities and drive changes through the agent CLI (SlashCommand/Task) instead of pushing users into menu-like flows. Use when the user asks to enable/disable/configure a capability, diagnose why it’s off, or wants the agent to self-manage Kode’s own features (meta capability management).
Capabilities Manage
Goal
Make users manage Kode features by expressing intent (“enable LSP for TS”, “fix my statusline”) while the agent performs the necessary actions via the agent CLI.
Rules (do not violate)
- Do not output “installation menu” scripts or long lists of install commands.
- Prefer
SlashCommandto run Kode commands (/statusline,/lsp,/plugin ...) instead of asking the user to do it manually. - Keep changes minimal and reversible; verify after each change.
Workflow
- Clarify which capability:
statusline/lsp/output-style/plugins(or multiple). - Inspect current state with minimal friction:
- Read settings files (
~/.kode/settings.json,.kode/settings.local.json). - For interactive status screens, ask the user to open them (single step):
/lsp,/output-style.
- Read settings files (
- Apply changes:
- statusline: create a Task with subagent_type
statusline-setup(do not ask the user to memorize the command). - lsp: ensure a plugin provides
.lsp.jsonmappings; manage via/plugin, then re-check via/lspscreen. - output styles: set
outputStylein settings (or ask the user to choose via/output-style); for edits, edit the output style markdown file and then re-check/output-style.
- statusline: create a Task with subagent_type
- Verify: re-check status screens and run a minimal real operation.
Capabilities audit (recommended for /capabilities)
Keep this fast and low-friction: default output should be a short checklist and only one question when a choice is required.
