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/implementation_questionsgit 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/implementation_questions)<a href="https://agentmods.dev/agents/kivo360/omoios/implementation_questions"><img src="https://agentmods.dev/badge/agents/kivo360/omoios/implementation_questions.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 | $0.00000 | $0.06914 |
| Opus 5 | $0.00000 | $0.03457 |
| Sonnet 5 | $0.00000 | $0.01383 |
| Haiku 4.5 | $0.00000 | $0.00691 |
Grade A, and why
implementation_questions 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 3d 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 — 715 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Agent Orchestration System - Implementation Questions
Document Purpose: This document contains focused implementation questions to guide the development of the multi-agent orchestration system using the OpenHands Software Agent SDK framework.
Target Audience: Development team, AI spec agents, system architects
Related Documents:
Created: 2025-11-16
Document Index
- Foundation & OpenHands Integration (8 questions)
- Agent Architecture & Types (8 questions)
- Conversation & Event Management (6 questions)
- Task Queue & Workflow Orchestration (6 questions)
- Workspace & Tool Integration (6 questions)
- Monitoring & Health Management (6 questions)
Total Questions: 40
1. Foundation & OpenHands Integration
Q1.1: OpenHands Package Selection [CRITICAL]
Context: OpenHands provides 4 packages: openhands-sdk (core), openhands-tools, openhands-workspace, openhands-agent-server.
Question: Which OpenHands packages should we use as the foundation for each agent type (Worker, Monitor, Watchdog, Guardian), and should we use the openhands-agent-server package for our orchestration layer or build a custom service?
Considerations:
- Worker agents need SDK + Tools + Workspace
- Monitor/Watchdog agents might only need SDK for metrics
- Agent server provides REST/WebSocket APIs we might leverage
- Custom orchestration might need direct SDK integration
Related Requirements: REQ-ALM-001, REQ-ALM-002
Q1.2: Agent Base Class Extension [CRITICAL]
Context: OpenHands provides openhands.sdk.agent.Agent as the core agent orchestration class.
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.
- 3d ago First seen · 715 lines · 0 tokens per session scan A 4ab35f55bb4a
implementation_questions 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 6,914 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
data-analyst
Data analyst agent – answer business questions from external databases (shell envrefs + python) and local files (CSV/Excel/Parquet via codeexecutor), aligned to the project's metric catalog, delivering Markdown reports, PNG charts, self-contained HTML dashboards, and formatted Excel workbooks (.xlsx).
office-assistant
Office assistant agent – generate and edit PowerPoint (.pptx via python-pptx), Excel (.xlsx via openpyxl), Word (.docx via python-docx), PDF (.pdf via reportlab), and web-based slide decks (self-contained reveal.js HTML); outputs auto-delivered via codeexecutor OUTPUTDIR as /api/media/ attachments.
DocSummarize
Summarize large or multiple documents (PDF/DOCX/PPTX/XLSX/HTML/CSV/TXT/MD). Wraps /skill:doc-summarizer. Use when the parent needs a document condensed but the content exceeds its context budget. Map-reduce — extracts, chunks, fans out, synthesizes one unified summary. Returns the summary path + key points.
ecosystem-doc-bridge-corpus-scanner
Status: human guide. Owner: Emerson Braun. Reviewed: 2026-08-14.
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.