get-to-work

get-to-work is a command for coding agents from OdinMB/ops-workflow. It costs 66 tokens per session (2,927 once invoked), scanned A, original, MIT.

An autonomous command for advancing an operations project without waiting for user input. It can work on tasks, opportunities, or both, once or repeatedly.

In plain words
What is it for?
Use it to run research, planning, file updates, and other safe repository work in repeated cycles. It does not send messages, submit forms, make purchases, or change external systems.
Why use it?
It keeps project work moving while you are away and records follow-up questions or decisions for later review.

Command

Part of the ops plugin — 9 skills, 10 commands, 5 agents shipped together

Install

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.

agentmods
npx agentmods add commands/odinmb/ops-workflow/get-to-work
Clone the repo
git clone --depth 1 https://github.com/OdinMB/ops-workflow

Or install ops, the plugin that ships this one along with the rest of its 9 skills, 10 commands, 5 agents.

Wrote 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.

agentmods badge for get-to-work

README.md
[![agentmods](https://agentmods.dev/badge/commands/odinmb/ops-workflow/get-to-work.svg)](https://agentmods.dev/commands/odinmb/ops-workflow/get-to-work)
Your own site
<a href="https://agentmods.dev/commands/odinmb/ops-workflow/get-to-work"><img src="https://agentmods.dev/badge/commands/odinmb/ops-workflow/get-to-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,927 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.02927
Opus 5 $0.00033 $0.01463
Sonnet 5 $0.00013 $0.00585
Haiku 4.5 $0.00007 $0.00293

Measured 3d ago against content hash db3ffc60f00e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

get-to-work 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.

commands/get-to-work.md · 260 lines

How it starts

The opening of the file, as written. The whole thing — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Get to Work

You will autonomously advance this ops project. Follow the work-autonomously skill throughout — the entire process runs without user input.

Safety Constraints

No real-world actions. You must NEVER:

  • Send emails, messages, or notifications
  • Submit forms, applications, or registrations
  • Post to social media or external platforms
  • Make API calls that modify external state
  • Make purchases or financial transactions
  • Contact anyone on behalf of the user

You CAN: research (web search, read public pages), write files, create plans, analyze data, produce drafts and artifacts the user can later use for world-affecting actions, and maintain the repo's knowledge system.

Phase 1: Setup

  1. Determine today's date. Check the current branch — if you're already on a feature branch or a prior get-to-work branch, stay on it. Only create a new branch (YYYY-MM-DD-get-to-work) if you're on main (or the repo's default branch).
  2. Create a follow-up file at plans/YYYY-MM-DD_get-to-work-followup.md:
# Get to Work — Follow-up

## Controversial Decisions
Items where the agent made a judgment call the user should review.

## Skipped Items
Opportunities identified but not acted on, with reasons.

## User Input Needed
Questions that blocked progress on specific items.

## Implementation Issues
Problems encountered during execution.

## Cycle Log
Summary of each identify → prioritize → execute cycle.

How to write an entry. Every entry leads with the decision, question, or omission stated in plain terms — what it means for the project, what it costs to leave as-is, and what the realistic options are. Someone who has not read a single file in this repo must be able to decide from the entry alone. Anything only an agent needs — plan file paths, state file or artifact names, backlog entry wording, commit refs — goes at the end of the entry under a For the executor: line, never in the opening sentences.

  1. Parse $ARGUMENTS:
    • First word — mode: tasks, opps, full, or escalating (default if omitted)
    • Second word — repeat: cycle (default if omitted) or once

Read the full file on GitHub · 260 lines

Changes

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.

  1. 3d ago First seen · 260 lines · 66 tokens per session scan A db3ffc60f00e

Subscribe to this mod's changes

get-to-work is a command published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 16d ago), licensed MIT. It adds 66 tokens to every session and 2,927 once invoked, about $0.0003 per session on Opus 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 2026-08-31.