Execution Stack — Forge + Scout + Ranker + Prism + Closer
Execution Stack — Forge + Scout + Ranker + Prism + Closer
The Execution Stack is Tier 2 — five specialists that do real work under governance oversight
Five specialists. One execution layer. Strategy becomes shipped work.
The Execution Stack is Tier 2 — five purpose-built agents that cover every stage of the execution pipeline. Research, evaluation, prioritization, decomposition, implementation. Each agent a specialist. Together, a complete autonomous workforce that runs under your Governance layer's authority.
One combined install. A coordinated pipeline from first signal to final deliverable.
Five agents. Every execution function covered.
🔍 Scout — Research & Intelligence Agent ($39 standalone)
Deep competitive analysis, technology evaluations, market scans, Porter's Five Forces — with proper citations. Scheduled weekly digests or on-demand deep dives delivered to your Telegram/WhatsApp. Stop Googling.
⚒️ Forge — Implementation Agent ($49 standalone)
Writes production code, deploys systemd services, manages dependencies, runs builds. Every deployment logged and auditable under Sentinel oversight. The agent that ships.
📊 Ranker — Evaluation & Prioritization Agent ($39 standalone)
Scores options, ranks priorities, breaks ties with structured analysis. Prevents your agent system from stalling on decisions. Clear recommendations with documented reasoning.
🔷 Prism — Decomposition Agent ($39 standalone)
Takes complex objectives and breaks them into clean, actionable task sequences. Every project decomposed into steps your execution agents can actually run. No ambiguous handoffs.
🤝 Closer — Conversion & Completion Agent ($39 standalone)
Drives tasks to completion. Monitors open loops, follows up on stalled work, closes out deliverables. The agent that makes sure "started" becomes "done."
What you get: combined install, coordinated pipeline
- 5 complete agent packages — SOUL.md, skills/, TOOLS.md, install/uninstall/verify for each
- install-all.sh — installs all five in the correct dependency order
- Combined pipeline guide — how to wire the execution layer so agents hand off to each other correctly
- Governance integration docs — pre-configured to run under Sentinel/Auditor oversight
Install in 4 steps
- Download the ZIP
cd ~/.openclaw/agents && unzip execution-stack.zip./install-all.sh- Tell your Chief of Staff: "Route research to Scout, decomposition to Prism, implementation to Forge"
Works with Claude 3.5/4 or GPT-5. Designed to run under the Governance Stack — Sentinel can veto any action, Auditor validates every output. Governance recommended before deploying this stack.
Execution without drift.
Five specialists in a coordinated pipeline means no lost context between stages, no ambiguous handoffs, no stalled work. Scout finds the signal. Ranker prioritizes it. Prism decomposes it. Forge ships it. Closer closes it. Everything logged. Everything auditable. The full Tier 2 execution layer in one package.
Requires Governance Stack for full bounded operation. Get everything with the Full Constitutional Stack ($299 — best value).
New to HiveDeck? Step-by-step install guide →