VividKit Crystal clear AI coding
VI
Choose Your Setup Get Started with AgentKit Continue with ClaudeKit Migrate from ClaudeKit to AgentKit Clean cutover from ClaudeKit What Is AgentKit? How AgentKit Works AgentKit Kits, Skills, Agents & Hooks AgentKit Runtime Support AgentKit Desktop App AgentKit Configuration AgentKit CLI Quick Reference AgentKit Skills Cheatsheet AgentKit Workflows AgentKit Statusline Update AgentKit CLI & Kits AgentKit Helper Clean reinstall of AgentKit AgentKit Troubleshooting What is ClaudeKit? ClaudeKit CLI Guide Command Finder Commands Cheat Sheet Workflow Recipes CLI Quick Reference Claude Mechanics Permission Modes ClaudeKit Hooks Coexistence ClaudeKit x Codex CK → Other coding tools How ClaudeKit Works Inside ClaudeKit Finding Your Unknowns Session Recovery Fix from Logs UI/UX Guide Accounts Switcher IDE Config Remote Control Codex App System Diagramming UI Review Gate Promotions Support VividKit

Quick Ref / Command

Engineer Kit

/ak:repomix

AI-ready repo context

Pack local, remote, or third-party repositories into AI-friendly XML, Markdown, JSON, or plain-text context with token counts and security checks.

01

Assess requirements

02

Configure filters

03

Execute packaging

04

Validate output

Rule 01

Package only the repository context the next AI task truly needs

Rule 02

Use include and ignore patterns to keep large codebases focused

Rule 03

Token counts are a delivery gate for the target model context

Rule 04

Security checks and manual output review happen before sharing

Rule 05

Remote repositories can be packed for analysis without cloning

Execution Map

Core lanes from input to output, aligned with the command's real execution path.

01

Start

Input, scope, route

  1. 1 Assess requirements Identify the local path or remote repository, the intended AI analysis or audit, the output format, and sensitive-data concerns.
  2. 2 Configure filters Set include and ignore patterns, decide whether to respect .gitignore, and enable comment removal only when it helps the target task.
02

Work

Agent / skill execution

  1. 3 Execute packaging Run Repomix locally or with `npx repomix --remote`, choose `--style xml|markdown|plain|json`, and write or copy the output file.
  2. 4 Validate output Review the generated file, token counts, security warnings, and target model context limits before delivery.
03

Verify

Gate, review, validation

  1. 5 Deliver context Provide the packaged file, token count summary, selected filters, and any omitted areas, warnings, or security caveats.

Syntax, arguments, subcommands

How to invoke the skill: syntax, positional arguments, shared options, then each subcommand with its own syntax and outcome.

Syntax

/ak:repomix [path] [--style xml|markdown|plain|json]

Arguments

[path]

Repository path

Local repository or folder to pack. Omit it to package the active working directory; use remote options only when the source is not local.

/ak:repomix packages/auth --style markdown

Shared options

--style xml|markdown|plain|json

Output style

Selects XML, Markdown, JSON, or plain text. It changes the bundle format, not the source files being included. Other Repomix CLI switches come from live CLI help, not this skill argument-hint.

/ak:repomix . --style markdown

Sample Prompt

Concrete invocations for each flag, subcommand, mode, or route available in the live workflow.

Default codebase snapshot Recommended 
/ak:repomix . --style xml
Use when:
Use when the whole current repository should become AI-readable context for analysis or planning.
Expected:
Assesses sensitivity and target use, runs a standard XML pack, reviews token counts and security warnings, then returns the output file with caveats.
Markdown pack 
/ak:repomix packages/auth --style markdown
Use when:
Use when a single package should become readable Markdown context instead of XML.
Expected:
Packs only the requested path as Markdown, reviews the generated file and token summary, and reports security warnings before sharing.

Handled Scope

  • AI-friendly repository snapshots
  • Remote repository packaging
  • Include and ignore pattern design
  • Token-count tree analysis
  • Secretlint-backed security checks
  • Comment removal and output formatting

Next