Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/pr1m8/haive/enhanced_multi_agent_v4_guide_2025git clone --depth 1 https://github.com/pr1m8/haiveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/pr1m8/haive/enhanced_multi_agent_v4_guide_2025)<a href="https://agentmods.dev/agents/pr1m8/haive/enhanced_multi_agent_v4_guide_2025"><img src="https://agentmods.dev/badge/agents/pr1m8/haive/enhanced_multi_agent_v4_guide_2025.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03147 |
| Opus 5 | $0.00000 | $0.01573 |
| Sonnet 5 | $0.00000 | $0.00629 |
| Haiku 4.5 | $0.00000 | $0.00315 |
Grade A, and why
enhanced_multi_agent_v4_guide_2025 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
EnhancedMultiAgentV4 Guide - Haive Framework
Date: August 7, 2025
Version: 1.0
Purpose: Comprehensive guide to EnhancedMultiAgentV4 orchestration
🚀 Overview
EnhancedMultiAgentV4 is the state-of-the-art multi-agent orchestrator in Haive that enables:
- Sequential, parallel, and conditional agent execution
- Clean list-based initialization
- Dynamic agent composition
- Structured data flow between agents
- Full integration with enhanced agent architecture
📋 Quick Start
Basic Sequential Workflow
from haive.agents.multi.enhanced_multi_agent_v4 import EnhancedMultiAgentV4
from haive.agents.react.agent_v4 import ReactAgentV4
from haive.agents.simple.agent_v3 import SimpleAgentV3
from pydantic import BaseModel
# Define structured output
class AnalysisResult(BaseModel):
summary: str
key_points: list[str]
confidence: float
# Create agents
analyzer = ReactAgentV4(
name="analyzer",
tools=[research_tool, calculator]
)
formatter = SimpleAgentV3(
name="formatter",
structured_output_model=AnalysisResult
)
# Create workflow - just pass a list!
workflow = EnhancedMultiAgentV4(
name="analysis_workflow",
agents=[analyzer, formatter], # Simple list initialization
execution_mode="sequential"
)
# Execute
result = await workflow.arun({
"task": "Analyze market trends for AI in 2025"
})
# result.summary, result.key_points, result.confidence available!
🏗️ Architecture
Class Hierarchy
Agent (base with enhanced features)
└── EnhancedMultiAgentV4
├── Implements build_graph()
├── Uses AgentNodeV3 for state projection
└── Integrates all enhanced agent features
Key Components
- MultiAgentState - Container for all agent states
- AgentNodeV3 - Handles state projection to individual agents
- Execution Modes - Different orchestration patterns
- Build Modes - Control when graph is constructed
🎯 Execution Modes
1. Sequential Mode
Agents execute one after another in order.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 531 lines · 0 tokens per session scan A 62b9f3ef9638
enhanced_multi_agent_v4_guide_2025 is an agent published in the GitHub repository pr1m8/haive (23 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,147 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
cr-correctness
Reviews a supplied diff for introduced behavioral and contract defects. Use only when dispatched by the code-review skill.
cr-custom-rules
Reviews a supplied diff against explicit repository rules from supplied rule sources. Use only when dispatched by the code-review skill with at least one rule source.
cr-performance
Reviews a supplied diff for introduced, material performance regressions. Use only when dispatched by the code-review skill.
cr-security
Reviews a supplied diff for introduced, practically exploitable security vulnerabilities. Use only when dispatched by the code-review skill.
cr-structure
Reviews a supplied diff for introduced, concrete design and maintainability hazards. Use only when dispatched by the code-review skill.
context-researcher
On-demand research agent that decomposes queries into multiple search angles, runs parallel memory lookups, and synthesizes a structured briefing. Use when deep memory context is needed for a topic, entity, or decision.