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/kivo360/omoios/openhands_insights_prioritizationgit clone --depth 1 https://github.com/kivo360/OmoiOSWrote 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/kivo360/omoios/openhands_insights_prioritization)<a href="https://agentmods.dev/agents/kivo360/omoios/openhands_insights_prioritization"><img src="https://agentmods.dev/badge/agents/kivo360/omoios/openhands_insights_prioritization.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 | $0.07852 |
| Opus 5 | $0.00000 | $0.03926 |
| Sonnet 5 | $0.00000 | $0.01570 |
| Haiku 4.5 | $0.00000 | $0.00785 |
Grade A, and why
openhands_insights_prioritization 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 — 600 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenHands SDK Insights & Question Prioritization
Document Purpose: This document synthesizes key insights from OpenHands SDK documentation research and proposes a revised prioritization strategy for implementation questions, optimized for spec-driven development (tests-first approach).
Created: 2025-11-16
Related Documents:
- OpenHands SDK Documentation Findings
- Implementation Questions
- Multi-Agent Orchestration Design
Key Insights from Documentation Research
1. OpenHands is Conversation-Scoped, Not System-Scoped
Finding: OpenHands events (MessageEvent, ActionEvent, ObservationEvent) are tied to individual Conversation instances. The EventService manages events per conversation, not system-wide.
Technical Details:
- All events inherit from the base
Eventclass (immutable withfrozen=Trueinmodel_config) - Event types include:
SystemPromptEvent,MessageEvent,ActionEvent,ObservationEvent,AgentErrorEvent,Condensation,PauseEvent,ConversationStateUpdateEvent - Events have common fields:
id(unique),timestamp,source(agent/user/environment) LLMConvertibleEventsubset can be converted to LLMMessageobjects for context constructionEventServiceusesPubSub[Event]class withsubscribe(subscriber),unsubscribe(subscriber_id), and async__call__(event)methods- Each subscriber receives events independently; failures in one subscriber don't affect others
ConversationState._state.set_on_state_change(callback)enables state change hooks
Implication: Our orchestration layer must build a separate system-wide event bus (Redis Pub/Sub, RabbitMQ, Kafka) for cross-agent communication, monitoring alerts, and workflow coordination. OpenHands provides the raw event data via callbacks/APIs, but we own the routing and persistence.
Affects Questions: Q1.4, Q3.1, Q3.2, Q3.6
SDK Reference:
- Source:
openhands-sdk/openhands/sdk/event/ - Event Service:
openhands-agent-server/openhands/agent_server/event_service.py - DeepWiki – Event System
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 · 600 lines · 0 tokens per session scan A 46ed13dff560
openhands_insights_prioritization is an agent published in the GitHub repository kivo360/OmoiOS (76 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 7,852 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
assistant
You are a general-purpose assistant — the example agent that ships with Archie so a fresh install does something useful out of the box. You handle small, self-contained requests: summarizing a block of text, drafting a short reply, or explaining something plainly.
gatekeeper
You exist to exercise the MCP tool approval gate in end-to-end checks. When asked to call your tools, call them exactly as instructed and report exactly what they returned — no improvisation, no retries beyond what the instructions say.
pm
This is the example PM overlay. The text here is appended to the PM agent's system prompt, so use it to give the PM the standing context it needs for your organization — what the company/team does, who the regular requesters are, house style for replies, and any defaults that should hold across every conversation.
ralph-loop-runner
Use this agent when you need to execute a Ralph orchestration loop end-to-end and verify its completion. This includes testing prompts against the Ralph system, validating that orchestration completes successfully, and capturing both results and any runtime issues. Examples:\n\n \nContext: User wants to test if a…
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
annotator
Phase 2.5 전용 @AX 태그 스캔 및 적용 에이전트. executor가 수정한 파일 목록을 받아 @AX 태그를 자동으로 분석하고 적용한다.