By elimydlarz
Maximum continuous integration for multi-agent coding — every edit is committed and pushed to trunk immediately
Tools for working with Claude Code: parallel agent coordination, test-driven development, living documentation, and shared coding rules.
Add the plugin marketplace:
claude plugin marketplace add elimydlarz/claude-code-plugins
Then install what you need:
| Tool | Install | What it does |
|---|---|---|
| trunk-sync | npm i -g trunk-sync && trunk-sync install | Auto-commit every edit to trunk — run multiple agents in parallel |
| contree | claude plugin install contree@susu-eng (Claude Code) — Codex CLI: install from this repo via /plugins | Test trees as living requirements — TDD with auto-synced specs in CLAUDE.md |
| openclaw-notifier | claude plugin install openclaw-notifier@susu-eng | Notify OpenClaw when a subagent completes a task |
git log v3.8.3..HEAD -- trunk-sync/ ':!trunk-sync/dist/' # review and draft notes
./scripts/publish-trunk-sync.sh patch --notes-file notes.md # or minor, major
Builds, tests (unit + e2e), bumps version, publishes to npm, pushes to GitHub, and cuts a GitHub release from the supplied notes file. Both distribution channels (npm package + marketplace plugin) updated together. The --notes-file is required; running without it prints the exact git log command for the previous tag.
MIT
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub elimydlarz/claude-code-plugins --plugin trunk-syncTest trees as living requirements — TDD with auto-synced specifications in CLAUDE.md
Continuous self-referential AI loops for interactive iterative development, implementing the Ralph Wiggum technique. Run Claude in a while-true loop with the same prompt until task completion.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses