sia-dashboard
claudeLive SIA dashboard for Claude Code: agents at work, tokens handled by subagents and the estimated saving from cheaper models, project skills and how often they are used, and every SIA call. Needs Claude Code 2.1.287 or later.
Evidence-gated agent workflow and cost-aware multi-agent orchestration. Routes work across cheap/current/strong model tiers, enforces exact file ownership, and requires independent review before integration.
Plugin sia from marketplace sia in GunjanGrunge/SIA_package. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use and it starts local MCP servers. The exact commands are listed below; read them before installing.
siaRun SIA's cost-aware multi-agent workflow only when the user explicitly invokes /sia.
siaRun SIA's cost-aware multi-agent workflow only when the user explicitly requests SIA.
siaRun SIA's cost-aware multi-agent workflow only when explicitly requested.
sia-orchestrateConfigure model tiers and dispatch SIA subagents with budgets, file-ownership safety and independent review. Use when the user says "sia orchestrate", "dispatch SIA agents", "run SIA workers", "configure SIA models", or asks SIA to parallelize implementation work across cheap and strong models.
sia-startSet up SIA in a project and walk it from intake to execution. Use when the user says "start SIA", "set up SIA", "init SIA", "use SIA on this project", "sia status", or asks where SIA is in its workflow or why SIA refuses to prepare tasks.
sia-workflowSIA's workflow contract — learning standing rules from the user's corrections, evidence-gated stages, file-ownership safety, telemetry honesty, and convergence. Use when the user corrects your work or states a lasting preference ("don't do X", "always Y", "that's too long", "call it Z"), when workin
sia-implementerImplements one SIA dispatch operation against an exact, declared file set. Use when the SIA controller dispatches a prepared task for implementation.
sia-reviewerIndependently reviews a completed SIA operation against its brief before integration. Use when the SIA controller dispatches review for an implemented task.
siaruns: python3 -c import glob, os, runpy, sys def usable(p): return bool(p) and '${' not in p and os.path.isfile(os.path.join(p, 'sia_mcp.py')) def version(p): try: return tuple(int(x) for x
python3 "${CLAUDE_PLUGIN_ROOT}/sia_hook.py" session-start
python3 "${CLAUDE_PLUGIN_ROOT}/sia_hook.py" post-tool-use
python3 "${CLAUDE_PLUGIN_ROOT}/sia_hook.py" stop
python3 "${CLAUDE_PLUGIN_ROOT}/sia_hook.py" subagent-start
Live SIA dashboard for Claude Code: agents at work, tokens handled by subagents and the estimated saving from cheaper models, project skills and how often they are used, and every SIA call. Needs Claude Code 2.1.287 or later.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
Use Superset to spawn agents, create workspaces, manage tasks, and schedule automations from Claude Code.
14 skills · 1 command
MiniMax AI skills library for frontend, fullstack, Android, iOS, shader, GIF sticker, document, presentation, spreadsheet, and multimodal media workflows
18 skills
Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflows. This plugin provides configuration guidance (LLM commit messages, project hooks, worktree paths), automatic activity tracking (🤖/💬 indicators in `wt list` showing active Claude sessions), and a `/wt-diff` pane showing each worktree's changes.
2 skills · 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.