session-orchestrator

data-ai MCP Server

Turn ad-hoc Claude Code / Codex / Cursor sessions into a repeatable loop — research → plan → wave-execute → close. Parallel sub-agents, inter-wave quality gates, dual GitHub+GitLab integration, F2 Memory + Persona-Panel + gsd-Pattern Adoption. 37 skills · 18 commands · 13 agents · 7360 tests.

Verified
data-aidata-ai
3 views34 stars3 forksv3.9.0MIT

Why This Matters

Discovered via github-topic:mcp and last synced 3mo ago.

Verified
Source
github-topic:mcp
Stars
34
Last synced
3mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
19
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (19)

Area

Features adopted

OS

macOS, Linux, **Windows (native)**

Routing

`model:` frontmatter routing on 36 SKILL.md (opus / sonnet / haiku / inherit); `Skill(name:*)` permission wildcards on 5 worker agents

AskUserQuestion

Native tool

dispatches

AG[Agents<br/>13 typed sub-agents] AG -.->

Fixed

Fixed

cyan

green

Capability

Session Orchestrator

red

magenta tools: Read, Grep, Glob, Bash # comma-separated string OR JSON array; both accepted --- ``` **Critical:** `description` must be a single-line inline string, not a YAML block scalar (`>` or `

purple

orange

Manual

Partial

Axis

session-orchestrator

reads

SK[Skills<br/>40 user-facing] COORD -->

sonnet

opus

None

None

Feature

Claude Code

Validation

`$schema` validation (schemastore.org) on both manifests + CI gate

Full

Full

writes

METRIC[.orchestrator/metrics/<br/>sessions · learnings · events] ``` ## Components **Skills (40 user-facing).** Lifecycle: `session-start`, `session-plan`, `wave-executor`, `session-end`, `quality-gates`, `using-orchestrator`. Authoring: `skill-creator`, `mcp-builder`, `hook-development`, `frontmatter-guard`. Planning & discovery: `plan`, `discovery`, `repo-audit`, `brainstorm`, `write-executable-plan`, `debug`, `claude-md-drift-check`, `grill`. Architecture: `architecture`, `domain-model`, `ubiquitous-language`. Cross-session: `evolve`, `convergence-monitoring`, `memory-cleanup`, `sunset-review`. Vault & docs: `vault-sync`, `vault-mirror`, `daily`, `docs-orchestrator`. Ecosystem: `bootstrap`, `gitlab-ops`, `gitlab-portfolio`, `ecosystem-health`, `mode-selector`, `autopilot`. Testing: `test-runner`, `playwright-driver`, `peekaboo-driver`. Content review: `persona-panel`. Visualization: `tmux-layout` (opt-in, operator side-channel — ADR-0007). **Commands (20).** `/session`, `/go`, `/close`, `/discovery`, `/plan`, `/evolve`, `/bootstrap`, `/harness-audit`, `/autopilot`, `/autopilot-multi`, `/repo-audit`, `/test`, `/memory-cleanup`, `/portfolio`, `/brainstorm`, `/debug`, `/persona-panel`, `/grill`, `/sunset-review`, `/templates-ack`. **Agents (13 typed sub-agents).** `code-implementer`, `test-writer`, `ui-developer`, `db-specialist`, `security-reviewer`, `session-reviewer`, `docs-writer`, `architect-reviewer`, `qa-strategist`, `analyst`, `ux-evaluator`, `dialectic-deriver`, `memory-proposal-collector`. **Hook event types (10).** `SessionStart` (banner + init), `SessionEnd` (close events), `PreToolUse/Edit