Comprehensive AI liteagents kit (subagents, skills/commands) for Claude Code, Opencode, Ampcode, and Droid
This repository also configures its own agents. See what liteagents tells them →
Command Claude Code
Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes.
Command Claude Code
Reorg a docs corpus, split an oversized doc, search it, keep pages current, index them.
Command Claude Code needs its repo
Conduct design interviews, generate UI variations, and collect live click-to-annotate feedback that streams into the session so edits land without leaving the browser. Use when the user wants rapid iterative UI refinement, not just batched feedback.
Command Claude Code
Refactor and optimize [code].
Command Claude Code
Verify, write the CHANGELOG, cut a version — then hand the release sequence back.
Command Claude CodeCodex
Consolidate stashes + friction into project memory.
Command Claude Code
Security audit — recurring six, injection, auth, trust boundaries.
Command Claude Code
Stash session context [name].
Command Claude Code
Generate and run tests [file].
Command Claude Code
Review a branch before merge.
Command Claude Code
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
Command Claude Code
Verify what you delivered since the last self-review with real runs, and review its structure.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: