Multi-sampled test-time compute plugin for DeepSeek Harness: parallel planning, internal voting, and a plan/execute/review workflow

Flywheel — Loop Engineering orchestrator (Go). Deterministic orchestrator driving Plan/Execute/Review agent loops from frozen on-disk contracts. Platform binaries ride optionalDependencies (@ckanner/flywheel-<os>-<arch>).

CLI-based multi-agent coding orchestrator — plan, execute, review on top of any coding agent

The Straw Hat crew of AI agents and skills: brainstorm, plan, execute, checkpoint, quality, gates, review, security, self-healing. Installs into Claude Code, opencode, Copilot, Gemini, Codex, Cursor, Kimi, pi, Windsurf, Cline, Kilo, Antigravity.

Multi-agent orchestration for Kiro — plan, execute, and review with specialized AI agents

Jervis Installing core engine — detect, plan, execute project workflows.

The Ring-0 agentic orchestration core (ADR-0044): the intent→plan→execute→observe loop, the Planner + ToolInvoker ports, and a deterministic rule-based planner. A first-party app expresses a goal; the loop plans which tools compose to satisfy it and runs

Human-agent collaboration framework — discover, plan, execute

비개발자 산출물 작업 setup wizard + PRD→Plan→Execute→Review 4단계 파이프라인 하네스 (5-skill)

⚡🦀 Structured operating methodology for AI agents. Plan → Execute → Review → Report → Template.

The three.ws agent engine: a plan/execute decision loop with human-approval gates, a seven-layer GuardChain (security blacklist, intervention, capability, permission, trade guard, spend envelope, x402 budget), a tamper-evident hash-chained action ledger,

A build system for AI agents — Plan. Execute. Verify. Fix. Ship.

Three-layer closed-loop engineering skill for AI coding agents (plan-execute / acceptance-redesign / human-review). Installs into 40+ SKILL.md-compatible hosts: claude, codex, opencode, cursor, gemini, copilot, droid, zcode, antigravity, and more.

MAQ master orchestrator — a token-efficient, agent-agnostic supervisor CLI that sits on top of any worker CLI (AI or not) via a Scout -> Plan -> Execute -> Verify pipeline.

Start and drive large projects as a map of tickets on GitHub Issues. Map-based onboarding + a discuss→plan→execute→verify engine, all on the Issues. Installs the trailhead skill, commands, and hooks into your agent's config dir.

Portable AI-agent workflow skills (plan → execute → land → learn) for Claude Code & Codex — grilling, TDD, diagnosis, two-axis code review, cross-model Codex review, design & domain-modeling, plus a skill router (ask-matt). npx init/update/diff/uninstall.

A DeepSeek Harness plugin bundle that reimplements opengsd-core (Git Ship Done) as a host-plane plugin set, replacing the default agent-loop behavior with the GSD phase loop (Discuss -> UI design -> Plan -> Execute -> Verify -> Ship). Includes checkpoint-

A team-based project orchestration system for Claude Code. Research, design, plan, execute, verify — with coordinated agent teams.

OpenCode plugin for multi-step mission orchestration — plan, execute, and validate goals across sessions

dsh ⇄ Paseo integration bundle: an enhanced ACP bridge exposing DeepSeek Harness (dsh) agents to Paseo with auto-discovered model catalog, plan/execute modes, thinking levels, and native dsh slash commands.