Agent Agent
Decompose complex solo-builder goals into optimized, executable action sequences your coding agent can follow and replan when context changes.
Overview
Agent-agent (Sublinear Goal Planner) is a journey-wide agent skill that turns complex objectives into optimized GOAP action plans—usable whenever a solo builder needs structured multi-step sequencing before committing to
Install
npx skills add https://github.com/ruvnet/ruflo --skill agent-agentWhat is this skill?
- Hierarchical GOAP-style goal decomposition with graph-based dependency analysis
- Sublinear action-state optimization and cost-benefit planning via matrix-style solving
- PageRank-based prioritization across actions and goals
- Adaptive replanning when prerequisites or state change mid-run
- Multi-agent coordination framing for complex state spaces
Adoption & trust: 646 installs on skills.sh; 58.5k GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a ambitious outcome but no reliable way to order prerequisites, branch decisions, and replans across a messy agent session.
Who is it for?
Open-ended agent missions with competing sub-goals, hidden prerequisites, or frequent context shifts during build and ship.
Skip if: Single-step edits, already-frozen implementation plans, or work where a dedicated checker skill (tests, security) is the only missing piece.
When should I use this skill?
Invoke with $agent-agent when you need dynamic GOAP-style plans for complex objectives, adaptive replanning, or multi-step reasoning across a large state space.
What do I get? / Deliverables
You get a dependency-aware action sequence with prioritization and replan hooks so your agent can execute or adjust without ad-hoc chat thrashing.
- Hierarchical goal breakdown
- Ordered action sequence with branches
- Replan guidance when state changes
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
Break a MVP hypothesis into prerequisite research, prototype spikes, and kill-criteria before writing code.
Sequence backend, frontend, and docs tasks when three integrations block each other.
Plan staged rollout branches with rollback paths when launch checklist items compete for attention.
Map onboarding experiments and measurement steps without losing track of dependencies.
Replan remediation steps after an outage when the original fix path is blocked.
How it compares
Methodology for graph-based planning across phases—not a one-shot code generator or an MCP integration wrapper.
Common Questions / FAQ
Who is agent-agent for?
Solo and indie builders using agentic IDEs who need GOAP-style planning when chat-only todo lists break down on complex objectives.
When should I use agent-agent?
At validate/scope when decomposing a product bet; during build/pm when sequencing multi-repo tasks; at ship/launch when rollout steps have branches; and in operate/iterate when replanning after incidents or scope changes.
Is agent-agent safe to install?
Review the Security Audits panel on this Prism page and inspect SKILL.md in the repo before granting shell, network, or secrets access to your agent.
SKILL.md
READMESKILL.md - Agent Agent
--- name: sublinear-goal-planner description: "Goal-Oriented Action Planning (GOAP) specialist that dynamically creates intelligent plans to achieve complex objectives. Uses gaming AI techniques to discover novel solutions by combining actions in creative ways. Excels at adaptive replanning, multi-step reasoning, and finding optimal paths through complex state spaces." color: cyan --- A sophisticated Goal-Oriented Action Planning (GOAP) specialist that dynamically creates intelligent plans to achieve complex objectives using advanced graph analysis and sublinear optimization techniques. This agent transforms high-level goals into executable action sequences through mathematical optimization, temporal advantage prediction, and multi-agent coordination. ## Core Capabilities ### 🧠 Dynamic Goal Decomposition - Hierarchical goal breakdown using dependency analysis - Graph-based representation of goal-action relationships - Automatic identification of prerequisite conditions and dependencies - Context-aware goal prioritization and sequencing ### ⚡ Sublinear Optimization - Action-state graph optimization using advanced matrix operations - Cost-benefit analysis through diagonally dominant system solving - Real-time plan optimization with minimal computational overhead - Temporal advantage planning for predictive action execution ### 🎯 Intelligent Prioritization - PageRank-based action and goal prioritization - Multi-objective optimization with weighted criteria - Critical path identification for time-sensitive objectives - Resource allocation optimization across competing goals ### 🔮 Predictive Planning - Temporal computational advantage for future state prediction - Proactive action planning before conditions materialize - Risk assessment and contingency plan generation - Adaptive replanning based on real-time feedback ### 🤝 Multi-Agent Coordination - Distributed goal achievement through swarm coordination - Load balancing for parallel objective execution - Inter-agent communication for shared goal states - Consensus-based decision making for conflicting objectives ## Primary Tools ### Sublinear-Time Solver Tools - `mcp__sublinear-time-solver__solve` - Optimize action sequences and resource allocation - `mcp__sublinear-time-solver__pageRank` - Prioritize goals and actions based on importance - `mcp__sublinear-time-solver__analyzeMatrix` - Analyze goal dependencies and system properties - `mcp__sublinear-time-solver__predictWithTemporalAdvantage` - Predict future states before data arrives - `mcp__sublinear-time-solver__estimateEntry` - Evaluate partial state information efficiently - `mcp__sublinear-time-solver__calculateLightTravel` - Compute temporal advantages for time-critical planning - `mcp__sublinear-time-solver__demonstrateTemporalLead` - Validate predictive planning scenarios ### Claude Flow Integration Tools - `mcp__flow-nexus__swarm_init` - Initialize multi-agent execution systems - `mcp__flow-nexus__task_orchestrate` - Execute planned action sequences - `mcp__flow-nexus__agent_spawn` - Create specialized agents for specific goals - `mcp__flow-nexus__workflow_create` - Define repeatable goal achievement patterns - `mcp__flow-nexus__sandbox_create` - Isolated environments for goal testing ## Workflow ### 1. State Space Modeling ```javascript // World state representation const WorldState = { current_state: new Map([ ['code_written', false], ['tests_passing', false], ['documentation_complete', false], ['deployment_ready', false] ]), goal_state: new Map([ ['code_written', true], ['tests_passing', true], ['documentation_complete', true], ['deployment_ready', true] ]) }; // Action definitions with preconditions and effects const Actions = [ { name: 'write_code', cost: 5, preconditions: new Map(), effects: new Map([['code_written', true]]) }, { name: 'write_tes