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/parallel_work_streamsgit 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/parallel_work_streams)<a href="https://agentmods.dev/agents/kivo360/omoios/parallel_work_streams"><img src="https://agentmods.dev/badge/agents/kivo360/omoios/parallel_work_streams.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 | $0.03497 |
| Opus 5 | $0.00000 | $0.01749 |
| Sonnet 5 | $0.00000 | $0.00699 |
| Haiku 4.5 | $0.00000 | $0.00350 |
Grade A, and why
parallel_work_streams 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 4d 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 — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Work Streams & Agent Assignment Plan
Document Purpose: Identify parallelizable work streams that can be assigned to different agents simultaneously, with clear boundaries and interfaces.
Created: 2025-11-16
Status: Active Planning
Related Documents:
- Implementation Roadmap
- Foundation & Smallest Runnable
Parallelization Strategy
Principles
- Independent Work Streams: Tasks that don't share code paths or have minimal overlap
- Clear Interfaces: Well-defined contracts between components
- Database Schema Coordination: Shared schema changes need coordination
- Test Isolation: Each stream has its own test suite
Phase 1: Core Workflow Enhancement - Parallel Streams
Stream A: Task Dependencies & Blocking
Agent Assignment: Agent A
Files to Modify:
omoi_os/models/task.py(adddependenciesJSONB field)omoi_os/services/task_queue.py(dependency resolution logic)omoi_os/api/routes/tasks.py(dependency API endpoints)tests/test_task_dependencies.py(new test file)
Database Changes:
- Migration: Add
dependenciesJSONB column totaskstable - Index: Add GIN index on
dependenciesfor query performance
Interface Contracts:
# Task model
dependencies: Mapped[Optional[dict]] = mapped_column(JSONB, nullable=True)
# Format: {"depends_on": ["task_id_1", "task_id_2"], "blocks": ["task_id_3"]}
# TaskQueueService methods
def get_next_task(self, phase_id: str) -> Task | None:
# Must filter out tasks with incomplete dependencies
def check_dependencies_complete(self, task_id: str) -> bool:
# New method: Check if all dependencies are completed
def get_blocked_tasks(self, task_id: str) -> list[Task]:
# New method: Get tasks blocked by this task
Dependencies: None (can start immediately)
Deliverables:
- ✅ Task model with dependencies field
- ✅ Dependency resolution in
get_next_task() - ✅ Circular dependency detection
- ✅ Tests for dependency resolution
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.
- 4d ago First seen · 443 lines · 0 tokens per session scan A af90a22db208
parallel_work_streams is an agent published in the GitHub repository kivo360/OmoiOS (75 stars, last pushed 2mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,497 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.
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.