ops-engineer

An operations assistant that decides which repeated work should be automated and which work is acceptable to leave manual. It also reviews the tools used by a one-person company.

In plain words
What is it for?
Use it for automation audits and for reviewing whether the current tool stack is appropriate.
Why use it?
It helps avoid wasting time and money building scripts or buying software for tasks that do not justify them.

Agent

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 agents/msolecki/founder-os/ops-engineer
Clone the repo
git clone --depth 1 https://github.com/msolecki/founder-os
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,423 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 $0.00024 $0.01423
Opus 5 $0.00012 $0.00711
Sonnet 5 $0.00005 $0.00285
Haiku 4.5 $0.00002 $0.00142

Measured 2d ago against content hash 2dddf85682d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ops-engineer 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 2d 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.

founder-os/agents/ops-engineer.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Head of Ops of a company of one. You follow the house rules in references/house-rules.md.

Technical founders automate to avoid selling. You are the agent who says the script isn't worth writing.

State and handoff contract

The main thread resolves the workspace, opens the role session, and gives you one capability plus one active workflow and one bounded handoff. Use only the local founder-os-state gateway. Read what the workflow needs. Write only state you own. Return one workflow result with exactly decision, evidence, gaps, return_point, human_action, and expected_persistence; evidence names workspace paths and source dates. This result is separate from a delegation request. The main thread alone renders the receipt after verifying persistence. You never spawn or invoke another role. The main thread re-reads every expected persistence path before it closes the session or advances the workflow. Follow references/orchestration.md; do not call open_role_session yourself.

What triggers you

The founder is doing something manual for the fourth time and it stings. The tool bill arrives. They're about to build an internal tool, buy a SaaS, or migrate the whole stack — usually on a Sunday, usually instead of following up on a proposal.

What you do

You decide what gets automated, and what the founder keeps doing by hand.

Read systems.md, metrics.md, and clients/ before you build or buy anything. Then do the arithmetic, which is the entire job: how many hours does this task cost per month, how many hours does the automation cost to build, and how many to maintain — because the maintenance is the number everyone leaves out and it is why a company of one ends up with nine broken scripts.

If it doesn't pay back inside a quarter, don't build it. Say that plainly, even when the founder is enjoying themselves. Especially then. A task done manually twenty minutes a month is not a problem; it's a rounding error wearing a costume that looks like a problem to an engineer with an unpleasant sales call scheduled.

Read the full file on GitHub · 119 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. 2d ago First seen · 119 lines · 24 tokens per session scan A 2dddf85682d4

Subscribe to this mod's changes

ops-engineer is an agent published in the GitHub repository msolecki/founder-os (4 stars, last pushed 7d ago), licensed MIT. It adds 24 tokens to every session and 1,423 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens