diff --git a/examples/templates/README.md b/examples/templates/README.md
index f289946563..13ec72ac65 100644
--- a/examples/templates/README.md
+++ b/examples/templates/README.md
@@ -44,3 +44,4 @@ uv run python -m exports.my_research_agent --input '{"topic": "..."}'
 |----------|-------------|
 | [deep_research_agent](deep_research_agent/) | Interactive research agent that searches diverse sources, evaluates findings with user checkpoints, and produces a cited HTML report |
 | [tech_news_reporter](tech_news_reporter/) | Researches the latest technology and AI news from the web and produces a well-organized report |
+| [oss_contributor_accelerator](oss_contributor_accelerator/) | Discovers high-leverage GitHub issues for a contributor and generates an execution-ready contribution brief with PR drafts |
diff --git a/examples/templates/oss_contributor_accelerator/DEMO.md b/examples/templates/oss_contributor_accelerator/DEMO.md
new file mode 100644
index 0000000000..b6acd12e2c
--- /dev/null
+++ b/examples/templates/oss_contributor_accelerator/DEMO.md
@@ -0,0 +1,41 @@
+# Demo Script (10-15 minutes)
+
+Use this to show the template's value quickly.
+
+## 1) Setup
+
+```bash
+./quickstart.sh
+```
+
+## 2) Copy template to exports
+
+```bash
+cp -r examples/templates/oss_contributor_accelerator exports/oss_contributor_accelerator
+```
+
+## 3) Run in TUI
+
+```bash
+hive run exports/oss_contributor_accelerator --tui
+```
+
+## 4) Suggested demo input
+
+- Repo: `aden-hive/hive`
+- Skills: `Python, agent frameworks, test automation, docs`
+- Time: `6 hours/week`
+- Preference: `quick win with meaningful impact`
+
+## 5) Success signal
+
+Agent should produce:
+- ranked shortlist of 8 issues
+- user-selected 1-3 issues
+- `contribution_brief.md` with implementation + tests + PR draft text
+
+## 6) What to share with reviewers
+
+- Brief screenshot/video of issue ranking
+- Final contribution_brief.md artifact
+- One concrete issue picked and implemented from the brief
diff --git a/examples/templates/oss_contributor_accelerator/README.md b/examples/templates/oss_contributor_accelerator/README.md
new file mode 100644
index 0000000000..def94ce9b2
--- /dev/null
+++ b/examples/templates/oss_contributor_accelerator/README.md
@@ -0,0 +1,65 @@
+# OSS Contributor Accelerator
+
+**Version**: 1.0.0  
+**Type**: Multi-node agent template
+
+## Overview
+
+Find high-leverage issues in an OSS repo and generate an execution-ready contribution brief.
+
+This template is designed for contributors who want to ship meaningful PRs quickly:
+
+1. Collect contributor context (skills, time, preferences)
+2. Discover and rank issues from GitHub
+3. Let the user pick 1-3 targets
+4. Generate a markdown brief with implementation plan, test strategy, and PR drafts
+
+## Architecture
+
+Execution flow:
+
+```text
+intake -> issue-scout -> selection -> contribution-pack
+```
+
+### Nodes
+
+1. **intake** (client-facing)
+   - Collects repo + contributor context
+   - Output: `repo_context`
+
+2. **issue-scout**
+   - Uses GitHub APIs to shortlist/rank 8 issues
+   - Output: `shortlisted_issues`
+   - Tools: `github_get_repo`, `github_list_issues`, `github_get_issue`
+
+3. **selection** (client-facing)
+   - Presents ranked issues and captures user selection
+   - Output: `selected_issues`
+
+4. **contribution-pack** (client-facing, terminal)
+   - Generates `contribution_brief.md`
+   - Includes implementation plan, tests, PR title/body drafts, maintainer update draft
+   - Tools: `save_data`, `append_data`, `serve_file_to_user`
+
+## Goal Criteria
+
+- High-impact issue shortlist
+- Strong contributor-to-issue fit
+- Actionable implementation and test plans
+- PR-ready draft quality
+
+## Usage
+
+```bash
+# Copy template to exports
+cp -r examples/templates/oss_contributor_accelerator exports/my_oss_agent
+
+# Run
+uv run python -m exports.my_oss_agent run
+```
+
+## Notes
+
+- Requires GitHub credentials for GitHub tools.
+- Designed with human-in-the-loop selection before deep planning.
diff --git a/examples/templates/oss_contributor_accelerator/__init__.py b/examples/templates/oss_contributor_accelerator/__init__.py
new file mode 100644
index 0000000000..36ea7f7b70
--- /dev/null
+++ b/examples/templates/oss_contributor_accelerator/__init__.py
@@ -0,0 +1,5 @@
+"""OSS Contributor Accelerator template."""
+
+from .agent import OSSContributorAcceleratorAgent, default_agent
+
+__all__ = ["OSSContributorAcceleratorAgent", "default_agent"]
diff --git a/examples/templates/oss_contributor_accelerator/__main__.py b/examples/templates/oss_contributor_accelerator/__main__.py
new file mode 100644
index 0000000000..2438308c8c
--- /dev/null
+++ b/examples/templates/oss_contributor_accelerator/__main__.py
@@ -0,0 +1,90 @@
+"""CLI entry point for OSS Contributor Accelerator."""
+
+import asyncio
+import json
+import logging
+import sys
+
+import click
+
+from .agent import default_agent
+
+
+def setup_logging(verbose=False, debug=False):
+    """Configure logging."""
+    if debug:
+        level, fmt = logging.DEBUG, "%(asctime)s %(name)s: %(message)s"
+    elif verbose:
+        level, fmt = logging.INFO, "%(message)s"
+    else:
+        level, fmt = logging.WARNING, "%(levelname)s: %(message)s"
+    logging.basicConfig(level=level, format=fmt, stream=sys.stderr)
+    logging.getLogger("framework").setLevel(level)
+
+
+@click.group()
+@click.version_option(version="1.0.0")
+def cli():
+    """OSS Contributor Accelerator - turn issue backlog into shippable plans."""
+
+
+@cli.command()
+@click.option("--mock", is_flag=True, help="Run in mock mode")
+@click.option("--quiet", "-q", is_flag=True, help="Only output result JSON")
+@click.option("--verbose", "-v", is_flag=True, help="Show execution details")
+@click.option("--debug", is_flag=True, help="Show debug logging")
+def run(mock, quiet, verbose, debug):
+    """Execute the workflow."""
+    if not quiet:
+        setup_logging(verbose=verbose, debug=debug)
+
+    context = {}
+    result = asyncio.run(default_agent.run(context, mock_mode=mock))
+
+    output_data = {
+        "success": result.success,
+        "steps_executed": result.steps_executed,
+        "output": result.output,
+    }
+    if result.error:
+        output_data["error"] = result.error
+
+    click.echo(json.dumps(output_data, indent=2, default=str))
+    sys.exit(0 if result.success else 1)
+
+
+@cli.command()
+@click.option("--json", "output_json", is_flag=True)
+def info(output_json):
+    """Show agent information."""
+    info_data = default_agent.info()
+    if output_json:
+        click.echo(json.dumps(info_data, indent=2))
+    else:
+        click.echo(f"Agent: {info_data['name']}")
+        click.echo(f"Version: {info_data['version']}")
+        click.echo(f"Description: {info_data['description']}")
+        click.echo(f"\nNodes: {', '.join(info_data['nodes'])}")
+        click.echo(f"Client-facing: {', '.join(info_data['client_facing_nodes'])}")
+        click.echo(f"Entry: {info_data['entry_node']}")
+        click.echo(f"Terminal: {', '.join(info_data['terminal_nodes'])}")
+
+
+@cli.command()
+def validate():
+    """Validate agent structure."""
+    validation = default_agent.validate()
+    if validation["valid"]:
+        click.echo("Agent is valid")
+        if validation["warnings"]:
+            for warning in validation["warnings"]:
+                click.echo(f"  WARNING: {warning}")
+    else:
+        click.echo("Agent has errors:")
+        for error in validation["errors"]:
+            click.echo(f"  ERROR: {error}")
+    sys.exit(0 if validation["valid"] else 1)
+
+
+if __name__ == "__main__":
+    cli()
diff --git a/examples/templates/oss_contributor_accelerator/agent.json b/examples/templates/oss_contributor_accelerator/agent.json
new file mode 100644
index 0000000000..997e11d2b9
--- /dev/null
+++ b/examples/templates/oss_contributor_accelerator/agent.json
@@ -0,0 +1,117 @@
+{
+  "agent": {
+    "id": "oss_contributor_accelerator",
+    "name": "OSS Contributor Accelerator",
+    "version": "1.0.0",
+    "description": "Rank high-leverage OSS issues and generate execution-ready contribution briefs with PR drafts."
+  },
+  "graph": {
+    "id": "oss-contributor-accelerator-graph",
+    "goal_id": "oss-contributor-accelerator",
+    "version": "1.0.0",
+    "entry_node": "intake",
+    "entry_points": {
+      "start": "intake"
+    },
+    "pause_nodes": [],
+    "terminal_nodes": [
+      "contribution-pack"
+    ],
+    "nodes": [
+      {
+        "id": "intake",
+        "name": "Intake",
+        "node_type": "event_loop",
+        "client_facing": true,
+        "input_keys": [],
+        "output_keys": [
+          "repo_context"
+        ]
+      },
+      {
+        "id": "issue-scout",
+        "name": "Issue Scout",
+        "node_type": "event_loop",
+        "client_facing": false,
+        "input_keys": [
+          "repo_context"
+        ],
+        "output_keys": [
+          "shortlisted_issues"
+        ],
+        "tools": [
+          "github_get_repo",
+          "github_list_issues",
+          "github_get_issue"
+        ]
+      },
+      {
+        "id": "selection",
+        "name": "Selection",
+        "node_type": "event_loop",
+        "client_facing": true,
+        "input_keys": [
+          "shortlisted_issues",
+          "repo_context"
+        ],
+        "output_keys": [
+          "selected_issues"
+        ]
+      },
+      {
+        "id": "contribution-pack",
+        "name": "Contribution Pack",
+        "node_type": "event_loop",
+        "client_facing": true,
+        "input_keys": [
+          "selected_issues",
+          "repo_context"
+        ],
+        "output_keys": [
+          "contribution_brief"
+        ],
+        "tools": [
+          "save_data",
+          "append_data",
+          "serve_file_to_user"
+        ]
+      }
+    ],
+    "edges": [
+      {
+        "id": "intake-to-issue-scout",
+        "source": "intake",
+        "target": "issue-scout",
+        "condition": "on_success",
+        "priority": 1
+      },
+      {
+        "id": "issue-scout-to-selection",
+        "source": "issue-scout",
+        "target": "selection",
+        "condition": "on_success",
+        "priority": 1
+      },
+      {
+        "id": "selection-to-contribution-pack",
+        "source": "selection",
+        "target": "contribution-pack",
+        "condition": "on_success",
+        "priority": 1
+      }
+    ]
+  },
+  "required_tools": [
+    "github_get_repo",
+    "github_list_issues",
+    "github_get_issue",
+    "save_data",
+    "append_data",
+    "serve_file_to_user"
+  ],
+  "metadata": {
+    "created_by": "template",
+    "node_count": 4,
+    "edge_count": 3
+  }
+}
diff --git a/examples/templates/oss_contributor_accelerator/agent.py b/examples/templates/oss_contributor_accelerator/agent.py
new file mode 100644
index 0000000000..73cc9f9541
--- /dev/null
+++ b/examples/templates/oss_contributor_accelerator/agent.py
@@ -0,0 +1,302 @@
+"""Agent graph construction for OSS Contributor Accelerator."""
+
+from pathlib import Path
+
+from framework.graph import Constraint, EdgeCondition, EdgeSpec, Goal, SuccessCriterion
+from framework.graph.checkpoint_config import CheckpointConfig
+from framework.graph.edge import GraphSpec
+from framework.graph.executor import ExecutionResult
+from framework.llm import LiteLLMProvider
+from framework.runner.tool_registry import ToolRegistry
+from framework.runtime.agent_runtime import AgentRuntime, create_agent_runtime
+from framework.runtime.execution_stream import EntryPointSpec
+
+from .config import default_config, metadata
+from .nodes import (
+    contribution_pack_node,
+    intake_node,
+    issue_scout_node,
+    selection_node,
+)
+
+
+goal = Goal(
+    id="oss-contributor-accelerator",
+    name="OSS Contributor Accelerator",
+    description=(
+        "Identify high-leverage issues in an OSS repository, rank them based on "
+        "contributor fit and expected impact, and generate an execution-ready "
+        "contribution brief with PR-ready artifacts."
+    ),
+    success_criteria=[
+        SuccessCriterion(
+            id="issue-quality",
+            description="Shortlist contains issues with meaningful user/project impact",
+            metric="impact_score",
+            target=">=0.8",
+            weight=0.25,
+        ),
+        SuccessCriterion(
+            id="fit-accuracy",
+            description="Selected issues match contributor skills and time budget",
+            metric="fit_score",
+            target=">=0.85",
+            weight=0.25,
+        ),
+        SuccessCriterion(
+            id="execution-clarity",
+            description="Contribution brief has concrete implementation and testing steps",
+            metric="plan_actionability",
+            target=">=0.9",
+            weight=0.3,
+        ),
+        SuccessCriterion(
+            id="shipping-readiness",
+            description="PR draft content is clear enough to submit with minor edits",
+            metric="pr_draft_quality",
+            target=">=0.85",
+            weight=0.2,
+        ),
+    ],
+    constraints=[
+        Constraint(
+            id="no-fabrication",
+            description="Do not invent issue/repo facts not present in retrieved data",
+            constraint_type="accuracy",
+            category="integrity",
+        ),
+        Constraint(
+            id="human-choice",
+            description="Only generate deep plans for issues explicitly selected by user",
+            constraint_type="behavioral",
+            category="user_control",
+        ),
+        Constraint(
+            id="high-signal-output",
+            description="Outputs must stay concise, technical, and actionable",
+            constraint_type="quality",
+            category="communication",
+        ),
+    ],
+)
+
+nodes = [
+    intake_node,
+    issue_scout_node,
+    selection_node,
+    contribution_pack_node,
+]
+
+edges = [
+    EdgeSpec(
+        id="intake-to-issue-scout",
+        source="intake",
+        target="issue-scout",
+        condition=EdgeCondition.ON_SUCCESS,
+        priority=1,
+    ),
+    EdgeSpec(
+        id="issue-scout-to-selection",
+        source="issue-scout",
+        target="selection",
+        condition=EdgeCondition.ON_SUCCESS,
+        priority=1,
+    ),
+    EdgeSpec(
+        id="selection-to-contribution-pack",
+        source="selection",
+        target="contribution-pack",
+        condition=EdgeCondition.ON_SUCCESS,
+        priority=1,
+    ),
+]
+
+entry_node = "intake"
+entry_points = {"start": "intake"}
+pause_nodes: list[str] = []
+terminal_nodes = ["contribution-pack"]
+
+
+class OSSContributorAcceleratorAgent:
+    """4-node pipeline for OSS issue selection and contribution planning."""
+
+    def __init__(self, config=None):
+        self.config = config or default_config
+        self.goal = goal
+        self.nodes = nodes
+        self.edges = edges
+        self.entry_node = entry_node
+        self.entry_points = entry_points
+        self.pause_nodes = pause_nodes
+        self.terminal_nodes = terminal_nodes
+        self._graph: GraphSpec | None = None
+        self._agent_runtime: AgentRuntime | None = None
+        self._tool_registry: ToolRegistry | None = None
+        self._storage_path: Path | None = None
+
+    def _build_graph(self) -> GraphSpec:
+        return GraphSpec(
+            id="oss-contributor-accelerator-graph",
+            goal_id=self.goal.id,
+            version="1.0.0",
+            entry_node=self.entry_node,
+            entry_points=self.entry_points,
+            terminal_nodes=self.terminal_nodes,
+            pause_nodes=self.pause_nodes,
+            nodes=self.nodes,
+            edges=self.edges,
+            default_model=self.config.model,
+            max_tokens=self.config.max_tokens,
+            loop_config={
+                "max_iterations": 120,
+                "max_tool_calls_per_turn": 30,
+                "max_history_tokens": 32000,
+            },
+            conversation_mode="continuous",
+            identity_prompt=(
+                "You are an OSS contribution closer. You prioritize high-impact work, "
+                "maintain factual accuracy, and turn vague issue queues into shippable plans."
+            ),
+        )
+
+    def _setup(self, mock_mode=False) -> None:
+        self._storage_path = Path.home() / ".hive" / "agents" / "oss_contributor_accelerator"
+        self._storage_path.mkdir(parents=True, exist_ok=True)
+
+        self._tool_registry = ToolRegistry()
+
+        mcp_config_path = Path(__file__).parent / "mcp_servers.json"
+        if mcp_config_path.exists():
+            self._tool_registry.load_mcp_config(mcp_config_path)
+
+        llm = None
+        if not mock_mode:
+            llm = LiteLLMProvider(
+                model=self.config.model,
+                api_key=self.config.api_key,
+                api_base=self.config.api_base,
+            )
+
+        tool_executor = self._tool_registry.get_executor()
+        tools = list(self._tool_registry.get_tools().values())
+
+        self._graph = self._build_graph()
+
+        checkpoint_config = CheckpointConfig(
+            enabled=True,
+            checkpoint_on_node_start=False,
+            checkpoint_on_node_complete=True,
+            checkpoint_max_age_days=7,
+            async_checkpoint=True,
+        )
+
+        entry_point_specs = [
+            EntryPointSpec(
+                id="default",
+                name="Default",
+                entry_node=self.entry_node,
+                trigger_type="manual",
+                isolation_level="shared",
+            )
+        ]
+
+        self._agent_runtime = create_agent_runtime(
+            graph=self._graph,
+            goal=self.goal,
+            storage_path=self._storage_path,
+            entry_points=entry_point_specs,
+            llm=llm,
+            tools=tools,
+            tool_executor=tool_executor,
+            checkpoint_config=checkpoint_config,
+        )
+
+    async def start(self, mock_mode=False) -> None:
+        if self._agent_runtime is None:
+            self._setup(mock_mode=mock_mode)
+        if not self._agent_runtime.is_running:
+            await self._agent_runtime.start()
+
+    async def stop(self) -> None:
+        if self._agent_runtime and self._agent_runtime.is_running:
+            await self._agent_runtime.stop()
+        self._agent_runtime = None
+
+    async def trigger_and_wait(
+        self,
+        entry_point: str = "default",
+        input_data: dict | None = None,
+        timeout: float | None = None,
+        session_state: dict | None = None,
+    ) -> ExecutionResult | None:
+        if self._agent_runtime is None:
+            raise RuntimeError("Agent not started. Call start() first.")
+
+        return await self._agent_runtime.trigger_and_wait(
+            entry_point_id=entry_point,
+            input_data=input_data or {},
+            session_state=session_state,
+        )
+
+    async def run(
+        self, context: dict, mock_mode=False, session_state=None
+    ) -> ExecutionResult:
+        await self.start(mock_mode=mock_mode)
+        try:
+            result = await self.trigger_and_wait(
+                "default", context, session_state=session_state
+            )
+            return result or ExecutionResult(success=False, error="Execution timeout")
+        finally:
+            await self.stop()
+
+    def info(self):
+        return {
+            "name": metadata.name,
+            "version": metadata.version,
+            "description": metadata.description,
+            "goal": {
+                "name": self.goal.name,
+                "description": self.goal.description,
+            },
+            "nodes": [n.id for n in self.nodes],
+            "edges": [e.id for e in self.edges],
+            "entry_node": self.entry_node,
+            "entry_points": self.entry_points,
+            "pause_nodes": self.pause_nodes,
+            "terminal_nodes": self.terminal_nodes,
+            "client_facing_nodes": [n.id for n in self.nodes if n.client_facing],
+        }
+
+    def validate(self):
+        errors: list[str] = []
+        warnings: list[str] = []
+
+        node_ids = {node.id for node in self.nodes}
+        for edge in self.edges:
+            if edge.source not in node_ids:
+                errors.append(f"Edge {edge.id}: source '{edge.source}' not found")
+            if edge.target not in node_ids:
+                errors.append(f"Edge {edge.id}: target '{edge.target}' not found")
+
+        if self.entry_node not in node_ids:
+            errors.append(f"Entry node '{self.entry_node}' not found")
+
+        for terminal in self.terminal_nodes:
+            if terminal not in node_ids:
+                errors.append(f"Terminal node '{terminal}' not found")
+
+        for ep_id, node_id in self.entry_points.items():
+            if node_id not in node_ids:
+                errors.append(
+                    f"Entry point '{ep_id}' references unknown node '{node_id}'"
+                )
+
+        return {
+            "valid": len(errors) == 0,
+            "errors": errors,
+            "warnings": warnings,
+        }
+
+
+default_agent = OSSContributorAcceleratorAgent()
diff --git a/examples/templates/oss_contributor_accelerator/config.py b/examples/templates/oss_contributor_accelerator/config.py
new file mode 100644
index 0000000000..35065febc8
--- /dev/null
+++ b/examples/templates/oss_contributor_accelerator/config.py
@@ -0,0 +1,25 @@
+"""Runtime configuration for OSS Contributor Accelerator."""
+
+from dataclasses import dataclass
+
+from framework.config import RuntimeConfig
+
+
+default_config = RuntimeConfig()
+
+
+@dataclass
+class AgentMetadata:
+    name: str = "OSS Contributor Accelerator"
+    version: str = "1.0.0"
+    description: str = (
+        "Find high-leverage issues in an OSS repo, rank them by impact/fit, and "
+        "generate an execution-ready contribution brief with PR drafts."
+    )
+    intro_message: str = (
+        "I help you land meaningful OSS contributions fast. Share a repo and I’ll "
+        "shortlist high-impact issues, then build a contribution brief you can execute."
+    )
+
+
+metadata = AgentMetadata()
diff --git a/examples/templates/oss_contributor_accelerator/mcp_servers.json b/examples/templates/oss_contributor_accelerator/mcp_servers.json
new file mode 100644
index 0000000000..18ba362f80
--- /dev/null
+++ b/examples/templates/oss_contributor_accelerator/mcp_servers.json
@@ -0,0 +1,9 @@
+{
+  "hive-tools": {
+    "transport": "stdio",
+    "command": "uv",
+    "args": ["run", "python", "mcp_server.py", "--stdio"],
+    "cwd": "../../../tools",
+    "description": "Hive tools MCP server"
+  }
+}
diff --git a/examples/templates/oss_contributor_accelerator/nodes/__init__.py b/examples/templates/oss_contributor_accelerator/nodes/__init__.py
new file mode 100644
index 0000000000..5e417be082
--- /dev/null
+++ b/examples/templates/oss_contributor_accelerator/nodes/__init__.py
@@ -0,0 +1,168 @@
+"""Node definitions for OSS Contributor Accelerator."""
+
+from framework.graph import NodeSpec
+
+
+intake_node = NodeSpec(
+    id="intake",
+    name="Intake",
+    description="Collect repository + contributor context",
+    node_type="event_loop",
+    client_facing=True,
+    max_node_visits=1,
+    input_keys=[],
+    output_keys=["repo_context"],
+    success_criteria=(
+        "Repository target and contributor preferences are collected and normalized."
+    ),
+    system_prompt="""\
+You are an elite OSS strategy partner helping contributors pick winning issues.
+
+**Objective:** collect enough context to identify the best 8 issues for this contributor.
+
+1) Ask the user for:
+- target repository in `owner/repo` format
+- their strongest skills/stack
+- available time per week
+- preferred issue types (bug/docs/feature/refactor/tests)
+- whether they prefer quick wins or deeper architectural work
+
+2) Keep questions concise and practical. If the user already provided data, do NOT ask again.
+
+3) Once you have enough context, call:
+set_output("repo_context", "<JSON with owner, repo, skills, weekly_hours, issue_preferences, depth_preference>")
+
+Do not over-interview. Get the essentials and move on.
+""",
+    tools=[],
+)
+
+
+issue_scout_node = NodeSpec(
+    id="issue-scout",
+    name="Issue Scout",
+    description="Find and rank the best OSS issues for the contributor",
+    node_type="event_loop",
+    client_facing=False,
+    max_node_visits=1,
+    input_keys=["repo_context"],
+    output_keys=["shortlisted_issues"],
+    success_criteria=(
+        "At least 8 candidate issues are ranked with clear fit rationale and execution risk."
+    ),
+    system_prompt="""\
+You are an OSS issue triage specialist.
+
+INPUT: `repo_context` JSON.
+
+Use GitHub tools to discover and rank opportunities:
+1) github_get_repo(owner, repo) for repo context
+2) github_list_issues(owner, repo, state="open", limit=100)
+3) For promising issues, call github_get_issue(owner, repo, issue_number)
+
+Selection policy:
+- Prioritize issues labeled `good first issue`, `help wanted`, `bug`, `enhancement`, `documentation`, `tests`.
+- Exclude stale/blocked issues when signals suggest no movement.
+- Prefer issues with clear acceptance criteria and reproducible context.
+
+Create a ranked shortlist of **8 issues**. For each issue include:
+- issue_number
+- title
+- url
+- labels
+- impact_score (1-10)
+- effort_score (1-10)
+- confidence_score (1-10)
+- why_fit (specific to contributor skills + weekly hours)
+- first_90_min_steps
+- risk_flags
+
+Then call:
+set_output("shortlisted_issues", "<JSON array of 8 ranked issue objects>")
+
+Be concrete. No vague rankings.
+""",
+    tools=["github_get_repo", "github_list_issues", "github_get_issue"],
+)
+
+
+selection_node = NodeSpec(
+    id="selection",
+    name="Selection",
+    description="Present ranked issues and let user choose targets",
+    node_type="event_loop",
+    client_facing=True,
+    max_node_visits=1,
+    input_keys=["shortlisted_issues", "repo_context"],
+    output_keys=["selected_issues"],
+    success_criteria="User explicitly selects 1-3 issues to pursue.",
+    system_prompt="""\
+You are a pragmatic OSS mentor.
+
+1) Present all shortlisted issues in a numbered list with:
+- title + issue number
+- impact/effort/confidence
+- 1-line why-fit summary
+
+2) Ask user to choose 1-3 issue numbers.
+
+3) After selection, call:
+set_output("selected_issues", "<JSON array containing only selected issue objects>")
+
+Do not re-rank unless user asks. Keep it crisp.
+""",
+    tools=[],
+)
+
+
+contribution_pack_node = NodeSpec(
+    id="contribution-pack",
+    name="Contribution Pack",
+    description="Generate execution-ready contribution brief for selected issues",
+    node_type="event_loop",
+    client_facing=True,
+    max_node_visits=1,
+    input_keys=["selected_issues", "repo_context"],
+    output_keys=["contribution_brief"],
+    success_criteria=(
+        "A structured markdown brief is generated and shared with implementation plans and PR drafts."
+    ),
+    system_prompt="""\
+You are a senior OSS execution coach.
+
+Create a single markdown file named `contribution_brief.md`.
+
+**IMPORTANT:** Build it incrementally to avoid token overflow:
+1) save_data with the report header and summary table
+2) append_data once per selected issue section
+3) append_data for final checklist and closing
+4) serve_file_to_user(filename="contribution_brief.md")
+
+For EACH selected issue include:
+- Issue snapshot (title, url, labels)
+- Why this is high leverage
+- Implementation plan (5-8 steps)
+- Test/verification plan
+- PR title draft
+- PR body draft (Summary, Changes, Testing, Risks)
+- Maintainer update comment draft
+- 90-minute kickoff checklist
+
+Constraints:
+- Never invent repo facts not grounded in issue data.
+- Keep claims realistic and actionable.
+- Optimize for shipping first meaningful PR quickly.
+
+Finish with:
+set_output("contribution_brief", "Created contribution_brief.md for {N} selected issues")
+""",
+    tools=["save_data", "append_data", "serve_file_to_user"],
+)
+
+
+__all__ = [
+    "intake_node",
+    "issue_scout_node",
+    "selection_node",
+    "contribution_pack_node",
+]