structurizr
claudecodexEnterprise C4 modeling with Structurizr DSL — indexed language reference, CLI/MCP tooling, 32 skills, validation gates, pattern catalog, and cookbook recipes.
32 skills · 12 commands · 1 agent · 1 MCP server
Parallel multi-session Claude orchestration. Spawn agents on tickets, run them in parallel git worktrees, watch a dashboard, get push notifications when reviews land or merges happen. Hierarchical authorization (ADR-0001) lets parent agents delegate to children safely.
Plugin fleet from marketplace bytedesk in ByteDeskAI/bytedesk-marketplace. Commands read from the repo's manifest — 2 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
chainDependency-aware multi-stage orchestration of parallel sessions. Spawn stage 1 in parallel; the always-on rules engine then spawns stage 2 once stage 1 is all done, stage 3 once stage 2 is done, and so on. The skill itself returns immediately — chains survive the chat session ending. Use when the us
cleanupFind sessions in the multi-session command center whose PRs have already merged on GitHub, and kill+cleanup each (with confirmation). Closes the loop on "spawn → ship → tidy up" without manual bookkeeping. Use when the user says "fleet cleanup", "/fleet:cleanup", "kill the merged sessions", "tidy up
reviewSpawn a dedicated reviewer session for a given session's open PR. The reviewer agent reads the diff, posts inline + summary review comments on GitHub, then exits. Works two ways — invoked by you in chat against any open PR, or invoked autonomously by an implementer session (auto-detects parent and t
setup-cliInstall thin wrappers in ~/.local/bin/ so the fleet plugin's public CLIs (claude-sessions, claude-sessions-web, spawn-claude-feature) are callable from the user's interactive zsh / bash, not just from the Claude Code tool host. The wrappers resolve to the latest installed plugin version at exec time
spawnSpawn one or many parallel Claude agents on Jira tickets, with full-auto mode and Jira-aware prompt construction. Single-ticket form replaces a manual bytedesk-feature-start when you already know the ticket; multi-ticket form fires N sessions in parallel ("kick off the whole sprint"). Use when the u
fleetChat-friendly snapshot of the multi-session Claude command center. Shows every running agent grouped by state (working / needs-input / error / done / idle), with branch, last activity, and a one-line peek at what each is currently doing. Use when the user asks "what's my fleet doing", "fleet status"
tournamentSpawn N variant agents on the same Jira ticket, each with a different strategy hint, then auto-spawn a judge that reads all the resulting PRs and merges the best one. Recursive orchestration — implements the variants pattern from the Multi-Session Claude roadmap (#5.1). Use when the user says "fleet
waitBlock until one or more sessions reach a target state (default done). Closes the no-event-callback gap in the multi-session system — anything that needs to react when an agent finishes uses this. Use when the user says "fleet wait", "/fleet:wait", "wait until BDP-N is done", "wait for these to finis
${CLAUDE_PLUGIN_ROOT}/hooks/pr-merge-guard.sh
${CLAUDE_PLUGIN_ROOT}/hooks/event-emitter.sh
Enterprise C4 modeling with Structurizr DSL — indexed language reference, CLI/MCP tooling, 32 skills, validation gates, pattern catalog, and cookbook recipes.
32 skills · 12 commands · 1 agent · 1 MCP server
Takes over Claude Code's task system — native task calls, approved plans, decisions and commits mirrored into a git-tracked markdown store at .bytedesk/task-management/. One store per project shared across git worktrees, claim-based parallel work with node_modules sharing, an MCP server, and a live dashboard.
27 skills · 1 MCP server · hooks
Design craft skills: motion and animation, Apple platform design, awwwards-grade frontend, prototyping, composition, and image generation. Split out of the old design-system plugin; carries no ByteDesk design content.
20 skills · 4 agents
Source-neutral design-pattern advisor with Markdown catalog, MCP tooling, smell scans, and architecture decision support.
6 skills · 11 commands · 1 agent · 1 MCP server · hooks
ByteDesk core implementation lifecycle — TDD engineer, feature start, PR-ready, worktree operator, architect, grounding, integration branches.
9 skills · 9 agents
Operator skills for the ByteDesk remote gateway, including /remote-gateway-login (local yaml or --url/--method/--username/--password) and the gateway-logs and gateway-profiling diagnosis skills.
17 skills
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Agentic QE (external: maintained in proffesor-for-testing/agentic-qe, pinned to v3.15.17): a quality-engineering fleet with 11 QE agents, 9 skills, 9 commands, the agentic-qe MCP server pinned to the plugin version, and the aqe-mod guard that refuses destructive operations on AQE learning data
9 skills · 9 commands · 11 agents · 1 MCP server
Skill: add headroom-ai compress() to a Python or TypeScript app to cut LLM input tokens (tool outputs, logs, JSON, chat history). No API key.
1 skill
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
Claude Code native multi-agent orchestration with intelligent model routing across agents and skills. Zero learning curve. Maximum power.
85 skills · 20 commands · 19 agents · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.