agent-orchestration plugins

146 tagged agent-orchestration, measured the same way as everything else here.

Browse within: github-workflow 36llm-workflow 36Autonomous Agents 10Multi-Agent 10a2a 7

planwright

73

inkatze/planwright

Plugin Claude Code

Autopilot for spec-driven development. The human signs off and merges; planwright flies the spec. Scales to a multi-spec fleet: an agentic software factory on Claude Code primitives.

3 4d ago A tokens not measured original MIT

orchestrate

75

Zihao-Wu06/claude-code-orchestrate

Plugin Claude Code

Multi-model orchestration for Claude Code: the session model leads as tech-lead orchestrator, routing work across model-pinned executors (deep-reasoner/Opus, fast-worker/Sonnet, scout/Haiku) and a cross-vendor Codex peer — with a first-match routing table, delegation contracts, budget modes, an escalation ladder, and…

3 1mo ago A tokens not measured

a

76

chafoo/anchored

Plugin Claude Code

Verification gate for AI work — one run file, one independent validator, evidence-gated close. CLI-only transport via the anchored binary over Bash, no MCP. Slash commands: /a:run /a:setup.

3 1mo ago A tokens not measured original MIT

claude-bridge

78

michalekz/claude-bridge

Plugin Claude Code

Multi-chat orchestration for Claude Code. File-based inbox, peer messaging, peerchatread, peerchatsearch, enhanced listsessions, context-usage monitoring (peercontextstatus + wake-time guard), idle-beep notification, bundled role skills. v0.10.0-rc: optional control-plane daemon for peer lifecycle (spawn/stop/re.

3 4d ago A tokens not measured original MIT

secondmate

79

eshwarvijay/secondmate

Plugin Claude Code

Your agent writes the code, a different model tries to break it, and only what survives ships. Cross-model, edit-locked review with a machine-readable verdict, gated merges, durable decisions, stuck-loop and timeout guards, and read-only reasoning one-shots. Harness-neutral.

3 6d ago A tokens not measured original MIT

promptsmith

80

emtcmca/promptsmith

Plugin Claude Code

Prompt & context engineering for agents — /sharpen rough requests, /forge-agent reusable system prompts, /lens to review through expert lenses (or grade a prompt against a rubric with --grade), and /orchestrate multi-domain builds across a 20-agent specialist gallery. Eval-backed. Zero dependencies, no API keys, model.

2 1mo ago A tokens not measured original Apache-2.0

specdd

81

mnyok9939/specdd

Plugin Claude Code

Spec-driven development orchestrator. Turns vague feature requests into production-grade specs before code is written.

2 3d ago A tokens not measured original MIT

holocron

82

atuljha23/holocron

Plugin Claude Code

A Jedi council for your codebase: 14 role-specialist agents, 24 domain commands (a11y, perf, QA, security, threat-modeling, SRE, ADR, cost tracking, MCP auditing), 11 skills including token economy, and a SQLite-backed learning crystal that compounds your corrections across sessions.

2 4mo ago A tokens not measured original MIT

specdd

83

unboundinnov/specdd

Plugin Claude Code

Spec-driven development orchestrator. Turns vague feature requests into production-grade specs before code is written.

2 3mo ago A tokens not measured copy · 100% MIT

Ghosteken/agent-harness

Plugin Claude Code

Production-grade engineering skills and agents for AI coding assistants — covering the full software development lifecycle from spec to ship.

2 16d ago A tokens not measured original MIT

agent-harness

85

Ghosteken/agent-harness

Plugin Claude Code

Production-grade engineering skills and agents for AI coding assistants, covering the full software development lifecycle from spec to ship.

2 16d ago A tokens not measured original MIT

supervisor

86

ma-nucho-pro/supervisor-claude-plugin

Plugin Claude Code

Strict multi-agent Supervisor for Claude Code: web-grounded anti-hallucination, expert coding/frontend implementation, independent judges, adversarial review, and final Stop release gate.

2 18d ago A tokens not measured

claude-code-pm

87

hunterg325/claude-code-pm

Plugin Claude Code

Autonomous Project Manager for Claude Code. Orchestrates parallel worker sessions to execute Linear tasks through a structured lifecycle: fetch, assign, implement, verify, review, merge.

2 5mo ago A tokens not measured original MIT

supervisor

88

ma-nucho-pro/supervisorLLM-plugin

Plugin Claude Code

Universal Supervisor adapter for Claude Code: web-grounded research, expert code/frontend work, 27 independent specialists, adversarial review, correction loops, and an independent Stop release judge.

2 18d ago A tokens not measured

claude-army

90

pablocaeg/claude-army

Plugin Claude Code

Analyzes any project and creates orchestrated teams of specialized Claude Code agents. Studies codebase patterns, PR review history, and testing conventions to produce agents grounded in the actual project.

2 5mo ago A tokens not measured original MIT

matilha

91

danilods/matilha-skills

Plugin Claude Code

You lead. Agents hunt. A cognitive + methodological harness for building complex AI-assisted projects — 11 phase-gated core skills, composition layer with plugin-namespace detection, SessionStart hook for cross-workspace activation, and 7 companion packs shipping 128 skills across UX, growth, agent architecture…

2 3mo ago A tokens not measured original MIT

odin-scp

92

bradheitmann/odin-sentinel

Plugin Claude Code

Operate and improve SCP governance for multi-agent teams: self-bootstrap and teardown of federated pods, generic role topology, EXEC PM / TEAM PM / ODIN separation, boot receipts, terminal locator identity, delegation receipts, terminal/CMUX delivery proof, heartbeat cadence, branch-visible claims, adversarial QA…

2 5d ago A tokens not measured original MIT

david-skills

93

edwardyen724-g/david-vscode

Plugin Claude Code

David's built-in skills — create-agent, create-job, create-dashboard — bundled with the David VS Code extension and auto-loaded into every David-spawned agent's Claude Code session via --plugin-dir.

2 2mo ago A tokens not measured original MIT

agent-stack

95

ssheleg/agent-stack

Plugin Claude Code

Four skills: agent-orchestrator — tool-calling loops, pipelines with checkpoints, provider routing with fallback, memory architecture, plus the wallet side of reselling LLM access; agent-evals — run/trace/thread evals, LLM judges, and fixtures grown from production; agent-interop — MCP servers and clients, A2A agent…

2 2d ago A tokens not measured original MIT