initxy
UserThe server-side runtime for AI agents. Durable & crash-safe (event-sourced), multi-worker scheduling, per-session sandboxing, human-in-the-loop, provider-neutral. Host agents like Claude Code on your own infra — self-hostable, no vendor lock-in.
Categories
Indexed Skills (10)
refactor-guide
Guidance for safe incremental refactors with a known-exact resource list
commit
Draft a clear git commit for the current changes and commit them
handoff
Compress the current session into a concise handoff document for another agent
init
Survey the codebase and create or refresh a concise CONTEXT.md plus project docs
review
Review the current git diff for correctness and adherence to repo standards
simplify
Clean up the changed code for reuse, simplification, and efficiency, then apply the fixes
verify
Verify a change actually does what it claims by running it and observing behavior
fix-python-test
minimal-patch loop for a failing pytest in a python project
example-command
An example user-invoked skill that demonstrates frontmatter options and the skills/<name>/SKILL.md layout
session-report
Generate an explorable HTML report of Claude Code session usage (tokens, cache, subagents, skills, expensive prompts) from ~/.claude/projects transcripts.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.