ODS is a system for turning a PC, Mac, or Linux computer into a private local AI server, meaning a machine that runs models and related AI services itself. It supports local model inference, chat, voice, agents, workflows, document retrieval, search, and image generation. The catalogue includes commands and an instruction for operating or configuring this system.
Borrowing it
Nothing to install: this file belongs to Osmantic/ODS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Osmantic/ODS/main/.claude/commands/team-plan.mdgit clone --depth 1 https://github.com/Osmantic/ODSWrote 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/commands/osmantic/ods/team-plan)<a href="https://agentmods.dev/commands/osmantic/ods/team-plan"><img src="https://agentmods.dev/badge/commands/osmantic/ods/team-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/osmantic/ods/team-plan"><img src="https://agentmods.dev/badge/commands/osmantic/ods/team-plan.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.07084 |
| Opus 5.5 | $0.00005 | $0.02834 |
| Sonnet 5.5 | $0.00002 | $0.01417 |
| Haiku 4.5 | $0.00001 | $0.00708 |
Grade A, and why
team-plan 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 2mo 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 — 798 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Team Planner
Analyze a user prompt, decompose it into workstreams, and interactively assign agent roles to form a coordinated team plan.
Arguments
$ARGUMENTS- A description of the task, feature, or project to plan for.
Philosophy: Ask Early, Ask Often
This skill should liberally use AskUserQuestion at every decision point. Do NOT assume user intent — validate it. The cost of asking is low; the cost of building the wrong plan is high. When in doubt, ask. Specifically:
- Before narrowing scope — confirm what's in and out
- Before committing to an approach — present alternatives
- After discovering something unexpected — share findings and get direction
- Between phases — checkpoint progress and confirm next steps
- When models disagree — let the user break the tie
- When tradeoffs exist — present them explicitly
The user should feel like a co-pilot throughout the entire planning process, not a rubber stamp at the end.
Workflow
Phase 1: Analyze the Prompt
Read and understand $ARGUMENTS. Identify:
- Scope - What is being asked? (feature, refactor, bug fix, migration, research, etc.)
- Domains touched - Which parts of the codebase are involved? (installer libs, installer phases, scripts, CLI, dashboard-api, dashboard UI, extensions, Docker config, tests, docs)
- Complexity signals - Multi-file? Cross-cutting concerns? External dependencies? Breaking changes?
- Risks - What could go wrong? What needs careful attention?
Before proceeding, explore the relevant codebase areas to ground your analysis in reality:
# Identify relevant files
Glob for patterns matching the task domains
Grep for key symbols, functions, or patterns mentioned in the prompt
Read critical files to understand current state
1a. Validate Understanding with User
After initial analysis, always confirm your understanding before proceeding. Do NOT silently assume scope:
AskUserQuestion:
question: "Here's my understanding of the task. Is this correct, or should I adjust scope?"
header: "Scope"
multiSelect: false
options:
- label: "Looks correct"
description: "<1-2 sentence summary of your understanding of scope and domains>"
- label: "Broader scope"
description: "I want this to also cover <adjacent areas you identified but weren't sure about>"
- label: "Narrower scope"
description: "Focus only on the core ask — skip <peripheral concerns you identified>"
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.
- 2mo ago First seen · 798 lines · 12 tokens per session scan A 8e558079c0f1
team-plan is a command published in the GitHub repository Osmantic/ODS (7,712 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 7,084 once invoked, about $0.0000 per session on Opus 5.5. 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 commands, from other repositories
review
Review code changes against project conventions.
resume-workflow
Restore the original Moira execution and continue its current step.
save-to-md
Save session documentation with Neo4j memory integration.
revise-claude-md
Update CLAUDE.md with learnings from this session.
check
View the latest screenshot from /Pictures/Screenshots.
deploy
Deploy all MCP plugin servers from .claude-plugin/marketplace.json.