Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

feat: add ruflo-goals plugin β€” GOAP planning, deep research, horizon tracking

Reuven851f3ed4ce28
diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json
index 3b965dc425..f11146bc19 100644
--- a/.claude-plugin/marketplace.json
+++ b/.claude-plugin/marketplace.json
@@ -100,6 +100,11 @@
"name": "ruflo-plugin-creator",
"source": "./plugins/ruflo-plugin-creator",
"description": "Scaffold, validate, and publish new Claude Code plugins with proper structure"
+ },
+ {
+ "name": "ruflo-goals",
+ "source": "./plugins/ruflo-goals",
+ "description": "Long-horizon goal planning, deep research orchestration, and adaptive replanning using GOAP"
}
]
}
diff --git a/README.md b/README.md
index f7f0d64e8b..2071521ffd 100644
--- a/README.md
+++ b/README.md
@@ -51,7 +51,7 @@ Install Ruflo as a native Claude Code plugin -- adds skills, commands, agents, a
```
<details>
-<summary><strong>All 19 plugins</strong></summary>
+<summary><strong>All 20 plugins</strong></summary>
| Plugin | What it adds |
|--------|-------------|
@@ -74,6 +74,7 @@ Install Ruflo as a native Claude Code plugin -- adds skills, commands, agents, a
| **ruflo-testgen** | Test gap detection, TDD workflow, tester agent |
| **ruflo-docs** | Doc generation, drift detection, docs-writer agent |
| **ruflo-plugin-creator** | Scaffold, validate, and publish new plugins |
+| **ruflo-goals** | GOAP planning, deep research, long-horizon tracking |
</details>
@@ -108,7 +109,7 @@ claude mcp add ruflo -- npx -y @claude-flow/cli@latest
| 🧠 **Self-Learning** | SONA neural patterns, ReasoningBank, trajectory learning |
| πŸ’Ύ **Vector Memory** | HNSW-indexed AgentDB with 150x-12,500x faster search |
| ⚑ **Background Workers** | 12 auto-triggered workers (audit, optimize, testgaps, etc.) |
-| 🧩 **Plugin Marketplace** | 19 native Claude Code plugins + 20 npm plugins |
+| 🧩 **Plugin Marketplace** | 20 native Claude Code plugins + 20 npm plugins |
| πŸ”Œ **Multi-Provider** | Claude, GPT, Gemini, Cohere, Ollama with smart routing |
| πŸ›‘οΈ **Security** | AIDefence, input validation, CVE remediation, path traversal prevention |
diff --git a/plugins/ruflo-goals/.claude-plugin/plugin.json b/plugins/ruflo-goals/.claude-plugin/plugin.json
new file mode 100644
index 0000000000..e512f59a68
--- /dev/null
+++ b/plugins/ruflo-goals/.claude-plugin/plugin.json
@@ -0,0 +1,12 @@
+{
+ "name": "ruflo-goals",
+ "description": "Long-horizon goal planning, deep research orchestration, and adaptive replanning using GOAP algorithms",
+ "version": "0.1.0",
+ "author": {
+ "name": "ruvnet",
+ "url": "https://github.com/ruvnet"
+ },
+ "homepage": "https://github.com/ruvnet/ruflo",
+ "license": "MIT",
+ "keywords": ["ruflo", "goals", "goap", "research", "planning", "deep-research", "long-horizon"]
+}
diff --git a/plugins/ruflo-goals/README.md b/plugins/ruflo-goals/README.md
new file mode 100644
index 0000000000..2717c85d50
--- /dev/null
+++ b/plugins/ruflo-goals/README.md
@@ -0,0 +1,34 @@
+# ruflo-goals
+
+Long-horizon goal planning, deep research orchestration, and adaptive replanning.
+
+## Install
+
+```
+/plugin marketplace add ruvnet/ruflo
+/plugin install ruflo-goals@ruflo
+```
+
+## Features
+
+- **Goal planning**: GOAP-based action planning with precondition analysis and cost optimization
+- **Deep research**: Multi-source research orchestration (web, memory, codebase, patterns)
+- **Horizon tracking**: Persistent objectives across sessions with milestone checkpoints
+- **Research synthesis**: Evidence-graded reports with contradiction resolution
+
+## Commands
+
+- `/goals` -- List active horizons, check progress, view research
+
+## Skills
+
+- `deep-research` -- Orchestrate multi-phase research campaigns
+- `goal-plan` -- Create and execute GOAP action plans
+- `horizon-track` -- Track objectives across sessions with drift detection
+- `research-synthesize` -- Synthesize findings into structured reports
+
+## Agents
+
+- `goal-planner` -- GOAP specialist with A* planning and trajectory learning
+- `deep-researcher` -- Multi-source research with evidence grading
+- `horizon-tracker` -- Cross-session objective tracking with drift detection
diff --git a/plugins/ruflo-goals/agents/deep-researcher.md b/plugins/ruflo-goals/agents/deep-researcher.md
new file mode 100644
index 0000000000..a29fe93c02
--- /dev/null
+++ b/plugins/ruflo-goals/agents/deep-researcher.md
@@ -0,0 +1,15 @@
+---
+name: deep-researcher
+description: Multi-source research specialist that gathers, cross-references, and synthesizes information from web, codebase, memory, and pattern databases
+model: sonnet
+---
+
+You are a deep research specialist. You investigate topics thoroughly by:
+1. Checking existing knowledge in memory and pattern databases
+2. Searching the web for current information
+3. Analyzing relevant source code and documentation
+4. Cross-referencing findings across sources
+5. Grading evidence quality (high/medium/low)
+6. Producing structured synthesis reports
+
+Store all findings in the `research` memory namespace. Flag contradictions explicitly.
diff --git a/plugins/ruflo-goals/agents/goal-planner.md b/plugins/ruflo-goals/agents/goal-planner.md
new file mode 100644
index 0000000000..4b51e0609a
--- /dev/null
+++ b/plugins/ruflo-goals/agents/goal-planner.md
@@ -0,0 +1,16 @@
+---
+name: goal-planner
+description: GOAP specialist that creates optimal action plans using A* search through state spaces, with adaptive replanning and trajectory learning
+model: sonnet
+---
+
+You are a Goal-Oriented Action Planning (GOAP) specialist. You use A* search to find optimal paths through state spaces and create executable plans.
+
+Your methodology:
+1. Assess current state and define goal state
+2. Inventory available actions with preconditions, effects, and costs
+3. Search for the cheapest action sequence that transforms current into goal state
+4. Execute with continuous monitoring β€” replan when actions fail or conditions change
+5. Record trajectories for learning via hooks_intelligence tools
+
+Always produce plans with concrete success criteria, cost estimates, and fallback strategies.
diff --git a/plugins/ruflo-goals/agents/horizon-tracker.md b/plugins/ruflo-goals/agents/horizon-tracker.md
new file mode 100644
index 0000000000..1cb7cbb462
--- /dev/null
+++ b/plugins/ruflo-goals/agents/horizon-tracker.md
@@ -0,0 +1,14 @@
+---
+name: horizon-tracker
+description: Long-horizon objective tracker that persists progress across sessions with milestone checkpoints and drift detection
+model: sonnet
+---
+
+You are a long-horizon objective tracker. You manage objectives that span multiple sessions by:
+1. Defining milestones with concrete completion criteria
+2. Recording session check-ins and check-outs in memory
+3. Detecting drift (scope creep, timeline slip, approach obsolescence)
+4. Persisting state across conversations via the horizons memory namespace
+5. Recommending course corrections when progress deviates from plan
+
+At session start, always recall the current horizon state. At session end, always update it.
diff --git a/plugins/ruflo-goals/commands/goals.md b/plugins/ruflo-goals/commands/goals.md
new file mode 100644
index 0000000000..cbc57671d5
--- /dev/null
+++ b/plugins/ruflo-goals/commands/goals.md
@@ -0,0 +1,11 @@
+---
+name: goals
+description: List active horizons, check goal progress, and view research findings
+---
+
+Show goal and research status:
+
+1. Call `mcp__claude-flow__memory_search` with namespace `horizons` and query `*` to list active horizons
+2. For each horizon, show: objective, current milestone, progress %, target date, drift status
+3. Call `mcp__claude-flow__memory_search` with namespace `research-synthesis` to list completed research reports
+4. Show a summary table of horizons and research state
diff --git a/plugins/ruflo-goals/skills/deep-research/SKILL.md b/plugins/ruflo-goals/skills/deep-research/SKILL.md
new file mode 100644
index 0000000000..21018a0eb2
--- /dev/null
+++ b/plugins/ruflo-goals/skills/deep-research/SKILL.md
@@ -0,0 +1,42 @@
+---
+name: deep-research
+description: Orchestrate multi-phase deep research with web search, memory retrieval, pattern matching, and synthesis into structured findings
+allowed-tools: mcp__claude-flow__memory_store mcp__claude-flow__memory_search mcp__claude-flow__memory_search_unified mcp__claude-flow__agentdb_hierarchical-store mcp__claude-flow__agentdb_hierarchical-recall mcp__claude-flow__agentdb_pattern-search mcp__claude-flow__agentdb_pattern-store mcp__claude-flow__neural_predict mcp__claude-flow__hooks_intelligence_pattern-search mcp__claude-flow__hooks_intelligence_pattern-store mcp__claude-flow__task_create mcp__claude-flow__task_list mcp__claude-flow__task_summary Bash WebSearch WebFetch Read Write
+---
+
+# Deep Research
+
+Orchestrate multi-phase deep research campaigns that gather, cross-reference, and synthesize information from multiple sources.
+
+## When to use
+
+When you need to investigate a complex topic thoroughly β€” spanning web sources, codebase patterns, stored memory, and external documentation β€” and produce a structured synthesis.
+
+## Steps
+
+1. **Define research scope** β€” break the question into 3-7 sub-questions that together answer the main question
+2. **Search existing knowledge** β€” call `mcp__claude-flow__memory_search_unified` and `mcp__claude-flow__agentdb_pattern-search` to check what's already known
+3. **Web research** β€” use `WebSearch` and `WebFetch` to gather external information for each sub-question
+4. **Codebase analysis** β€” use `Bash` (grep/find), `Read` to examine relevant source files
+5. **Cross-reference** β€” compare findings across sources, identify agreements and contradictions
+6. **Store findings** β€” call `mcp__claude-flow__memory_store` with namespace `research` for each key finding
+7. **Store patterns** β€” call `mcp__claude-flow__agentdb_pattern-store` for reusable patterns discovered
+8. **Synthesize** β€” produce a structured research report with:
+ - Executive summary (2-3 sentences)
+ - Key findings (bulleted)
+ - Evidence quality assessment (high/medium/low per finding)
+ - Open questions remaining
+ - Recommended next steps
+
+## Research depth levels
+
+- **Quick** β€” memory search + 1-2 web queries, 2-3 minutes
+- **Standard** β€” memory + web + codebase scan, 5-10 minutes
+- **Deep** β€” all sources + cross-referencing + pattern storage, 15-30 minutes
+- **Exhaustive** β€” deep + spawn sub-agents for parallel research threads, 30+ minutes
+
+## Memory namespaces
+
+- `research` β€” raw findings keyed by topic
+- `research-synthesis` β€” completed synthesis reports
+- `research-sources` β€” source URLs and references
diff --git a/plugins/ruflo-goals/skills/goal-plan/SKILL.md b/plugins/ruflo-goals/skills/goal-plan/SKILL.md
new file mode 100644
index 0000000000..91fd31c9d8
--- /dev/null
+++ b/plugins/ruflo-goals/skills/goal-plan/SKILL.md
@@ -0,0 +1,58 @@
+---
+name: goal-plan
+description: Create and execute Goal-Oriented Action Plans (GOAP) with precondition analysis, cost optimization, and adaptive replanning
+allowed-tools: mcp__claude-flow__task_create mcp__claude-flow__task_list mcp__claude-flow__task_status mcp__claude-flow__task_assign mcp__claude-flow__task_update mcp__claude-flow__task_complete mcp__claude-flow__task_summary mcp__claude-flow__memory_store mcp__claude-flow__memory_search mcp__claude-flow__neural_predict mcp__claude-flow__workflow_create mcp__claude-flow__workflow_execute mcp__claude-flow__workflow_status mcp__claude-flow__hooks_intelligence_trajectory-start mcp__claude-flow__hooks_intelligence_trajectory-step mcp__claude-flow__hooks_intelligence_trajectory-end Bash Read Write Edit
+---
+
+# Goal Plan
+
+Create and execute intelligent plans using Goal-Oriented Action Planning (GOAP).
+
+## When to use
+
+When you have a complex objective that requires multiple steps, has dependencies between steps, and may need adaptive replanning as conditions change.
+
+## Steps
+
+1. **Define goal state** β€” what does "done" look like? List concrete success criteria
+2. **Assess current state** β€” what's true now? What assets, code, infrastructure exist?
+3. **Identify gap** β€” what must change between current and goal state?
+4. **Inventory actions** β€” list available actions with:
+ - Preconditions (what must be true before this action)
+ - Effects (what becomes true after this action)
+ - Cost estimate (time, complexity, risk)
+5. **Generate plan** β€” find the optimal action sequence using A* through the state space
+6. **Record trajectory** β€” call `mcp__claude-flow__hooks_intelligence_trajectory-start` to begin tracking
+7. **Create tasks** β€” call `mcp__claude-flow__task_create` for each action in the plan
+8. **Execute** β€” work through tasks in dependency order:
+ - Before each action: verify preconditions still hold
+ - After each action: verify effects achieved
+ - Record each step via `mcp__claude-flow__hooks_intelligence_trajectory-step`
+9. **Monitor & replan** β€” if an action fails or produces unexpected results:
+ - Reassess current state
+ - Recalculate optimal path from new state
+ - Update remaining tasks
+10. **Complete trajectory** β€” call `mcp__claude-flow__hooks_intelligence_trajectory-end`
+11. **Store successful plan** β€” call `mcp__claude-flow__memory_store` with namespace `goap-plans`
+
+## Plan output format
+
+```
+Goal: [concrete objective]
+Current State: [key facts]
+Plan Cost: [estimated effort]
+Steps:
+ 1. [action] β€” precondition: [X], effect: [Y], cost: [Z]
+ 2. [action] β€” precondition: [Y], effect: [W], cost: [Z]
+ ...
+Risk Factors: [what could force a replan]
+Fallback: [alternative approach if primary path fails]
+```
+
+## Replanning triggers
+
+- Action fails (precondition no longer met)
+- Unexpected side effects detected
+- New information changes goal definition
+- Cost exceeds threshold
+- External dependency becomes unavailable
diff --git a/plugins/ruflo-goals/skills/horizon-track/SKILL.md b/plugins/ruflo-goals/skills/horizon-track/SKILL.md
new file mode 100644
index 0000000000..201aa8ac76
--- /dev/null
+++ b/plugins/ruflo-goals/skills/horizon-track/SKILL.md
@@ -0,0 +1,60 @@
+---
+name: horizon-track
+description: Track long-horizon objectives across multiple sessions with milestone checkpoints, progress persistence, and drift detection
+allowed-tools: mcp__claude-flow__memory_store mcp__claude-flow__memory_search mcp__claude-flow__memory_list mcp__claude-flow__memory_retrieve mcp__claude-flow__task_list mcp__claude-flow__task_summary mcp__claude-flow__progress_check mcp__claude-flow__progress_summary mcp__claude-flow__agentdb_hierarchical-store mcp__claude-flow__agentdb_hierarchical-recall mcp__claude-flow__hooks_intelligence_pattern-store mcp__claude-flow__session_save mcp__claude-flow__session_restore Bash Read Write
+---
+
+# Horizon Track
+
+Track long-running objectives that span multiple sessions, days, or weeks.
+
+## When to use
+
+When an objective is too large for a single session β€” multi-week features, research programs, migration projects, or any work that requires persistent progress tracking across conversations.
+
+## Steps
+
+1. **Initialize horizon** β€” define the objective, target date, and 3-7 milestones
+2. **Store horizon** β€” call `mcp__claude-flow__memory_store` with namespace `horizons` and key `horizon-[name]`:
+ ```json
+ {
+ "objective": "...",
+ "created": "2026-04-28",
+ "targetDate": "2026-05-15",
+ "milestones": [
+ {"id": "m1", "name": "...", "criteria": "...", "status": "pending"},
+ {"id": "m2", "name": "...", "criteria": "...", "status": "pending"}
+ ],
+ "currentMilestone": "m1",
+ "sessions": []
+ }
+ ```
+3. **Session check-in** β€” at the start of each session:
+ - Recall horizon: `mcp__claude-flow__memory_retrieve` key `horizon-[name]` namespace `horizons`
+ - Review milestone status
+ - Assess drift (are we still on track?)
+ - Plan this session's contribution
+4. **Work and record** β€” as work progresses:
+ - Update milestone status
+ - Record session summary
+ - Store intermediate findings
+5. **Session check-out** β€” at the end of each session:
+ - Update horizon state in memory
+ - Record what was accomplished
+ - Note blockers or scope changes
+ - Estimate remaining effort
+6. **Milestone completion** β€” when a milestone is done:
+ - Verify completion criteria met
+ - Store learned patterns via `mcp__claude-flow__hooks_intelligence_pattern-store`
+ - Advance to next milestone
+7. **Drift detection** β€” flag when:
+ - Progress rate suggests target date will be missed
+ - Scope has grown beyond original definition
+ - Dependencies have changed
+ - Approach needs fundamental rethinking
+
+## Memory namespaces
+
+- `horizons` β€” active horizon definitions and state
+- `horizon-sessions` β€” per-session summaries keyed by `[horizon]-[date]`
+- `horizon-learnings` β€” patterns and insights discovered during the horizon
diff --git a/plugins/ruflo-goals/skills/research-synthesize/SKILL.md b/plugins/ruflo-goals/skills/research-synthesize/SKILL.md
new file mode 100644
index 0000000000..69d059f837
--- /dev/null
+++ b/plugins/ruflo-goals/skills/research-synthesize/SKILL.md
@@ -0,0 +1,61 @@
+---
+name: research-synthesize
+description: Synthesize research findings from memory into structured reports with evidence grading, contradiction resolution, and actionable recommendations
+allowed-tools: mcp__claude-flow__memory_search mcp__claude-flow__memory_search_unified mcp__claude-flow__memory_list mcp__claude-flow__memory_retrieve mcp__claude-flow__memory_store mcp__claude-flow__agentdb_context-synthesize mcp__claude-flow__agentdb_pattern-search mcp__claude-flow__neural_predict Bash Read Write
+---
+
+# Research Synthesize
+
+Synthesize accumulated research findings into actionable reports.
+
+## When to use
+
+After running deep-research (one or multiple times), when you need to pull together findings from memory into a coherent synthesis with recommendations.
+
+## Steps
+
+1. **Gather findings** β€” search across research namespaces:
+ - `mcp__claude-flow__memory_search` namespace `research` for raw findings
+ - `mcp__claude-flow__memory_search` namespace `research-sources` for references
+ - `mcp__claude-flow__agentdb_pattern-search` for discovered patterns
+ - `mcp__claude-flow__agentdb_context-synthesize` for AI-assisted context building
+2. **Grade evidence** β€” for each finding, assess:
+ - **High**: Multiple independent sources agree, directly observed, reproducible
+ - **Medium**: Single credible source, indirectly supported, plausible
+ - **Low**: Anecdotal, single unverified source, speculative
+3. **Resolve contradictions** β€” when findings conflict:
+ - Identify the specific claim in tension
+ - Compare evidence quality
+ - Check recency (newer data may supersede)
+ - Note unresolved contradictions explicitly
+4. **Predict relevance** β€” call `mcp__claude-flow__neural_predict` to score which findings are most relevant to the original goal
+5. **Structure report**:
+ - Executive summary (2-3 sentences answering the original question)
+ - Key findings (ranked by evidence quality)
+ - Methodology (what sources were checked)
+ - Limitations (what wasn't checked, what remains uncertain)
+ - Recommendations (concrete next actions)
+ - References (source links and memory keys)
+6. **Store synthesis** β€” call `mcp__claude-flow__memory_store` namespace `research-synthesis` with the full report
+
+## Output format
+
+```
+# [Research Topic] β€” Synthesis Report
+
+## Summary
+[2-3 sentence answer]
+
+## Key Findings
+1. [Finding] β€” Evidence: High/Medium/Low
+2. [Finding] β€” Evidence: High/Medium/Low
+
+## Contradictions
+- [Claim A] vs [Claim B]: [resolution or "unresolved"]
+
+## Recommendations
+1. [Action] β€” because [reasoning]
+
+## Sources
+- [key]: [description]
+```