kit-extensions
A guide and workflow for building custom Go-based extensions for the Kit framework.
Install
mkdir -p .claude/skills/kit-extensions && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11233" && unzip -o skill.zip -d .claude/skills/kit-extensions && rm skill.zipInstalls to .claude/skills/kit-extensions
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Guide for creating Kit extensions. Use when the user asks to build, create, or modify a Kit extension, add a custom tool, slash command, widget, keyboard shortcut, editor interceptor, tool renderer, or hook into any Kit lifecycle event.Key capabilities
- →Build custom slash commands
- →Add custom tools
- →Create UI widgets
- →Hook into editor lifecycle
How it works
It provides a framework for creating single-file Go extensions that hook into Kit's lifecycle events.
Inputs & outputs
When to use kit-extensions
- →Build custom slash commands
- →Add new tools to the Kit environment
- →Create UI widgets for the editor
- →Hook into editor lifecycle events
About this skill
Kit Extensions Development Guide
Kit extensions are single-file Go programs interpreted at runtime by Yaegi. They hook into Kit's lifecycle, register custom tools and slash commands, display widgets, intercept editor input, render tool output, register and switch color themes, and more.
Extensions can be distributed via git repositories using kit install. Repos can contain single extensions or collections of multiple extensions.
This file is the entry point. It gives the structure, a minimal example, and the constraints you must never miss. Detailed material lives in the references/ directory (see Reference files below). Read only the reference files that apply to your task.
Extension Structure
Every extension must export a package main with an Init(api ext.API) function:
//go:build ignore
package main
import "kit/ext"
func Init(api ext.API) {
// Register event handlers, tools, commands, etc.
}
The //go:build ignore tag prevents go build from compiling the file directly.
Extension Locations
Extensions are auto-loaded from these directories:
/usr/share/kit/extensions/*.go(system-wide, single files)/usr/share/kit/extensions/*/main.go(system-wide, subdirectories)~/.config/kit/extensions/*.go(user, single files)~/.config/kit/extensions/*/main.go(user, subdirectories).kit/extensions/*.go(project-local, single files).kit/extensions/*/main.go(project-local, subdirectories)
Or loaded explicitly:
kit -e path/to/extension.go
kit --extension path/to/extension.go
Import Path
Extensions import the Kit API as "kit/ext". The full standard library is available plus os/exec for subprocess spawning.
API Overview
The Init function receives an ext.API object for registering handlers, and event handlers receive an ext.Context with runtime capabilities.
api.On*— subscribe to one of 30 lifecycle events (OnSessionStart,OnToolCall,OnAgentEnd, ...). Seereferences/lifecycle-events.md.api.RegisterTool/RegisterCommand/RegisterShortcut/RegisterOption— add LLM tools,/slashcommands, key bindings, and config options. Seereferences/tools-commands-shortcuts.md.ctx.*— runtime capabilities: print output, inject messages, widgets, header/footer, prompts, overlays, editor interceptor, session data/state, model and tool management, LLM completions, themes. Seereferences/context-api.md.api.RegisterToolRenderer/api.RegisterMessageRenderer— custom rendering of tool calls and messages. Seereferences/renderers.md.
Minimal Working Example
A tool, a slash command, and an event handler in one file:
//go:build ignore
package main
import (
"time"
"kit/ext"
)
var toolCalls int // package-level vars hold state across callbacks
func Init(api ext.API) {
api.RegisterTool(ext.ToolDef{
Name: "current_time",
Description: "Get the current date and time",
Parameters: `{"type":"object","properties":{}}`,
Execute: func(input string) (string, error) {
return time.Now().Format(time.RFC3339), nil
},
})
api.RegisterCommand(ext.CommandDef{
Name: "echo",
Description: "Echo back the provided text",
Execute: func(args string, ctx ext.Context) (string, error) {
ctx.PrintInfo("You said: " + args)
return "", nil
},
})
api.OnToolCall(func(e ext.ToolCallEvent, ctx ext.Context) *ext.ToolCallResult {
toolCalls++
return nil // nil = allow; return &ext.ToolCallResult{Block: true, Reason: "..."} to block
})
}
Run it with kit -e my-ext.go. Validate syntax with kit extensions validate.
Critical Yaegi Constraints (condensed — never skip)
Yaegi silently miscompiles some valid Go. Failures do not show an error; the code just does nothing. The full version with complete examples is in references/yaegi-constraints.md.
1. No named function references in struct fields or handler arguments
A named function assigned to a struct field (or passed directly as an argument) returns zero values across the interpreter boundary. Always use anonymous closure literals:
// WRONG - will silently return zero values:
func myHandler(key, text string) ext.EditorKeyAction { ... }
ctx.SetEditor(ext.EditorConfig{HandleKey: myHandler})
// CORRECT - use anonymous closure:
ctx.SetEditor(ext.EditorConfig{
HandleKey: func(key, text string) ext.EditorKeyAction { return myHandler(key, text) },
})
This applies to ALL struct fields that take function values: ToolDef.Execute, CommandDef.Execute, EditorConfig.HandleKey, EditorConfig.Render, ToolRenderConfig.RenderHeader, ToolRenderConfig.RenderBody, etc.
2. No comma-separated case lists in a tagless switch
In switch { case a, b, c: } Yaegi evaluates only the first expression. Join the conditions with || into one case expression, or use an if/else chain. A switch WITH a tag (switch n { case 1, 2, 3: }) is fine.
// WRONG - only the first condition is ever checked:
case r >= 'a' && r <= 'z', r >= 'A' && r <= 'Z', r >= '0' && r <= '9':
// CORRECT:
case (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9'):
3. No interfaces across the boundary
All extension-facing API types are concrete structs, never interfaces. Yaegi crashes on interface wrapper generation.
4. Package-level variables for state
Yaegi supports package-level variables captured in closures. This is the standard way to maintain state across event callbacks (var callCount int at file scope, then mutate inside handlers).
Other Rules You Must Know
- Return
nilto pass through. EveryOn*handler that returns a*Resultpointer treatsnilas "no change". Return a non-nil pointer only to modify or block. - Slash commands and shortcut handlers run in their own goroutine. They can block on
ctx.PromptSelect, I/O, orexec.Commandsafely. - Do not bind
ctrl+cas a shortcut (rejected at load). Prefer modifier combinations over bare keys. e.StopReason == "error"is the error check inOnAgentEnd. Do NOT compare against"completed"for success.- Tool
Parametersis a JSON Schema string. Theinputargument toExecuteis the JSON-encoded parameters from the LLM. - Use rune counts (
len([]rune(s))) not byte length when aligning widget text that contains box-drawing or multi-byte characters.
Reference files
Read the file that matches the task. Paths are relative to this skill's root directory.
| File | Read it when you need... |
|---|---|
references/lifecycle-events.md | The full list of all 30 events (session, agent turn, tool, tool-call streaming, input, streaming, model, UI, context filtering, session control, custom events), their fields, and return types. |
references/tools-commands-shortcuts.md | Registering tools (including ExecuteWithContext with cancellation/progress), slash commands with tab-completion, keyboard shortcuts (key-name normalization and reserved keys), and options. |
references/context-api.md | The complete ext.Context API: output, message injection, widgets, header/footer, status bar, prompts, overlays, editor interceptor, terminal size, thinking level, UI visibility, session data/state, model and tool management, LLM completions, TUI suspension, themes, application control, context fields. |
references/renderers.md | Custom tool renderers (RenderHeader / RenderBody) and message renderers. |
references/yaegi-constraints.md | The full Yaegi constraints section with complete code examples for each pitfall. |
references/common-patterns.md | Recipes: tool call blocking, system prompt injection, background processing with SendMessage, ephemeral context injection, live widget updates, custom theme with slash command, spawning Kit as a sub-agent. |
references/testing-and-distribution.md | The pkg/extensions/test harness and assertions, CLI testing commands, and distributing extensions via git repositories (kit install, repo structure, README template, storage locations). |
references/plan-mode-example.md | A complete, end-to-end extension (Plan Mode) that combines shortcuts, widgets, tool blocking, and state. |
references/bridged-sdk-apis.md | Bridged SDK capabilities: conversation tree navigation, skill loading, template parsing, model resolution, model pricing. |
Key Files for Reference
internal/extensions/api.go— Complete API type definitionsinternal/extensions/runner.go— Event dispatch and state managementinternal/extensions/loader.go— Yaegi interpreter setupinternal/extensions/symbols.go— All types exported to extensionspkg/extensions/test/— Testing package with harness, mocks, and assertionsexamples/extensions/tool-logger_test.go— Complete test exampleexamples/extensions/— 25+ working example extensions
When not to use it
- →When Kit is not the target environment
Prerequisites
Limitations
- →Requires Go
- →Dependent on Kit API
How it compares
It allows for deep integration into the editor lifecycle, unlike standard plugin systems.
Compared to similar skills
kit-extensions side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| kit-extensions (this skill) | 0 | 3mo | Review | Advanced |
| command-development | 16 | 10mo | Review | Intermediate |
| skill-forge | 11 | 10mo | Review | Intermediate |
| codex-skill | 12 | 6mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
command-development
anthropics
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
skill-forge
WilliamSaysX
Automated skill creation workshop with intelligent source detection, smart path management, and end-to-end workflow automation. This skill should be used when users want to create a new skill or convert external resources (GitHub repositories, online documentation, or local directories) into a skill. Automatically fetches, organizes, and packages skills with proactive cleanup management.
codex-skill
feiskyer
Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interactive automation mode for hands-off task execution without approval prompts.
agent-factory
alirezarezvani
Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns
subagent-driven-development
davila7
Use when executing implementation plans with independent tasks in the current session
peekaboo
openclaw
Capture and automate macOS UI with the Peekaboo CLI.