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/pr.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/pr)<a href="https://agentmods.dev/commands/osmantic/ods/pr"><img src="https://agentmods.dev/badge/commands/osmantic/ods/pr/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/pr"><img src="https://agentmods.dev/badge/commands/osmantic/ods/pr.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 | $0.00024 | $0.01667 |
| Opus 5.5 | $0.00010 | $0.00667 |
| Sonnet 5.5 | $0.00005 | $0.00333 |
| Haiku 4.5 | $0.00002 | $0.00167 |
Grade A, and why
pr 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 — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Workflow Skill
Create a new branch from main, stage all changes, commit, push, create a PR, and iteratively fix all failing checks until they pass.
Arguments
$ARGUMENTS- Branch name (required) and optional commit message- Format:
<branch-name> [commit message in quotes] - Example:
feat/add-auth "Add user authentication"
- Format:
Philosophy: Ask Early, Ask Often
This skill should liberally use AskUserQuestion at every decision point. PRs are visible to the team — assumptions about commit messages, PR descriptions, and fix strategies should be validated. Specifically:
- Before committing — confirm commit message and staged files
- Before creating the PR — confirm title and description
- When checks fail — ask how to handle before auto-fixing
- After completion — ask about next steps
Workflow
1. Parse Arguments
Extract branch name and commit message from $ARGUMENTS:
- First word is the branch name
- Remaining text (if any) is the commit message
- If no commit message provided, generate one based on staged changes
2. Verify Clean State & Create Branch
# Fetch latest from origin
git fetch origin
# Create and checkout new branch from main
git checkout -b <branch-name> origin/main
3. Stage and Commit Changes
# Check what files have changes
git status
# Stage all changes
git add -A
# If no commit message provided, analyze changes for a message
git diff --cached --stat
3a. Confirm What Gets Committed
Before staging, present the changes and ask the user to confirm:
AskUserQuestion:
question: "These files will be staged and committed. Does this look right?"
header: "Stage"
multiSelect: false
options:
- label: "Stage all changes"
description: "<N files changed, +X/-Y lines — summary of key changes>"
- label: "Let me pick files"
description: "I want to selectively stage specific files"
- label: "Review changes first"
description: "Show me the diff before I decide"
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 · 245 lines · 24 tokens per session scan A 2eee78950f5e
pr is a command published in the GitHub repository Osmantic/ODS (7,712 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 1,667 once invoked, about $0.0001 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
quick-push
Git add all, commit with Claude, and push to current/new feature branch.
caveman-commit
Generate a terse caveman-style commit message for staged changes.
speckit.git.commit
Proxy for speckit.git.commit.md.
start-development
Start the available Software Development Flow in Moira.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
careful
Blocks destructive shell commands once invoked: a PreToolUse Bash guard denies rm -rf outside temp dirs, force pushes and remote branch deletes, git reset --hard, DROP TABLE / DROP DATABASE / TRUNCATE, kubectl delete and terraform or tofu destroy, including inside ssh remote commands, and makes Claude ask the…