By Grimblaz
Multi-agent workflow system for Claude Code. Pipeline-based agent orchestration: Issue → Design → Plan → Implement → Review → PR.
Invoke Solution-Designer inline — technical design exploration with 3-pass adversarial challenge.
Invoke Experience-Owner inline — customer framing upstream or CE Gate evidence capture downstream.
Audit or bootstrap ai-first-documentation standards for the current repository. Actions: audit, init, help.
Invoke Code-Conductor in explicit non-hub-mode for a free-text task: route to local code review, GitHub review intake, or specialist dispatch (implementation, tests, docs, etc.) without the hub pipeline.
Run only the defense stage of the Claude adversarial review pipeline against an existing prosecution ledger.
Hub-mode orchestration shell for Claude Code. Use to run an approved plan through implementation, validation, CE Gate, and PR creation.
Adversarial review shell for Claude Code. Use when you need prosecution or defense findings for a code review pipeline.
Review judgment shell for Claude Code. Use when you need a single-shot ruling on prosecution and defense ledgers.
Implementation specialist shell for Claude Code. Use when Code-Conductor needs minimal, plan-driven code changes executed.
Documentation finalization specialist shell for Claude Code. Use when Code-Conductor needs implementation-aligned documentation updates.
Reusable adversarial review methodology for prosecution, defense, design challenge, product-alignment, and proxy review passes. Use when reviewing code, plans, designs, or external review ledgers with evidence-first rigor. DO NOT USE FOR: final judgment ownership, GitHub intake routing, or fix execution decisions (use review-judgment or code-review-intake).
Research-backed standards for documentation in AI-first codebases: context-file architecture (CLAUDE.md, skills, subagents, rules), multi-agent interop, and project-doc organization, with a tiered audit rubric. Use when authoring or auditing CLAUDE.md/AGENTS.md, deciding where guidance belongs, or running a documentation gap analysis. DO NOT USE FOR: post-implementation doc updates (use documentation-finalization) or reference sidecar setup (use project-references).
Structured Given/When/Then scenario authoring with ID traceability and CE Gate coverage gap detection. Use when writing or reviewing BDD scenarios in Agent Orchestra, classifying scenarios as [auto]/[manual], managing scenario ID lifecycle, extracting scenario IDs for CE Gate pre-flight, generating Gherkin .feature files and step definitions for [auto] scenarios (Phase 2), or configuring framework runner dispatch for CE Gate (Phase 2). DO NOT USE FOR: general test strategy (use test-driven-development), or writing example-based unit tests.
Structured Socratic questioning for exploring ideas and solutions. Use when exploring new features, evaluating approaches, or thinking through complex decisions. DO NOT USE FOR: architecture evaluation or SOLID analysis (use software-architecture), UI component design (use frontend-design), or coordinating implementation lanes (use parallel-execution).
VS Code native browser tool behavior for canvas-based games (Phaser 3, etc.). Use when interacting with HTML canvas elements, clicking game objects, verifying canvas state via browser tools, or when `clickElement` fails on canvas. DO NOT USE FOR: React component tests (use ui-testing) or Playwright E2E tests (use webapp-testing).
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
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.
⚠️ GitHub Copilot / VS Code support is frozen and retiring after 2026-08-31. Claude Code is the actively supported path. See COPILOT-DEPRECATION.md for details and the reach-out channel if you depend on Copilot support.
A multi-agent workflow system that orchestrates AI-assisted software development through specialized Claude Code agents. (GitHub Copilot/VS Code: frozen and retiring after 2026-08-31 — see COPILOT-DEPRECATION.md)
Renamed from
copilot-orchestrain v2.0.0. See the migration section below for the one-time steps to switch over.
⚠️ Copilot / VS Code support is frozen and retiring after 2026-08-31. Claude Code is the actively supported path — see Install as Plugin (Claude Code) below. If you depend on the Copilot/VS Code surface, start a GitHub Discussion before the deadline. See COPILOT-DEPRECATION.md for details. Experimental: Agent plugins are available in VS Code 1.110 as an experimental feature. Plugin distribution is the fastest way to get started with no cloning required.
Enable plugins — Add to VS Code user settings (Ctrl+Shift+P → "Open User Settings (JSON)"):
{
"chat.plugins.enabled": true,
"chat.plugins.marketplaces": ["Grimblaz/agent-orchestra"]
}
Install — In the Extensions view (Ctrl+Shift+X), search @agentPlugins agent-orchestra and install.
Use — The 16-agent payload and shared skill library are immediately available in VS Code Chat.
What's included in the repo plugin payload: 16 agents, the shared skill library, and 16 command files under commands/ (/code-conductor, /design, /experience, /orchestrate, /spine-run, /orchestra:spine, /plan, /polish, /raw, /review-github, /setup-references, /orchestra:review, /orchestra:review-lite, /orchestra:review-prosecute, /orchestra:review-defend, /orchestra:review-judge). VS Code currently ignores the plugin commands field; Claude Code and CLI consumers use it.
What requires clone/fork: Instruction files (.github/instructions/) and project templates are not distributed via the plugin — they are auto-discovered by VS Code when you clone or fork the repo. Plugin-distributed hooks are also not active when you only point VS Code at a clone via chat.agentFilesLocations; deterministic SessionStart cleanup and Claude PostToolUse release-hygiene prompts require an actual plugin install.
Claude Code loads agents and skills from .claude-plugin/plugin.json. Install via the built-in marketplace commands:
/plugin marketplace add Grimblaz/agent-orchestra
/plugin install agent-orchestra@agent-orchestra
All 16 agents and the shared skill library are immediately available. The marketplace command registers the source; the install command pulls the plugin into Claude Code's cache. See Documents/Decisions/0002-claude-code-plugin-schema.md for the schema rationale (agents uses an explicit registration whitelist; skills auto-discovers).
This is zero-config for consumer repositories: after marketplace registration and plugin install, Claude Code loads the shared agent bodies and skills from its plugin cache. The repository using the plugin does not need a local agents/ directory.
See Documents/Design/hub-artifact-paths-audit.md for the full hub artifact path catalog.
For what's included in the plugin payload vs. what requires clone/fork, see the Install as Plugin (Claude Code) section above.
Related: see the Releases section in CLAUDE.md for cache invalidation behavior and the audit doc's How to Detect Staleness section for drift detection.
See also: CUSTOMIZATION.md > Script portability for plugin users.
The plugin payload includes all 16 shared agent definitions and the shared skill library. The Claude-specific command and specialist surface is outlined below.
The three upstream agents are first-class Claude Code citizens:
npx claudepluginhub grimblaz/agent-orchestra --plugin agent-orchestraHarness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development