Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/danielpaulai/Purely-Personal-Run-a-business-by-itselfnpx agentmods add commands/danielpaulai/purely-personal-run-a-business-by-itself/operations-engineWrote 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/danielpaulai/purely-personal-run-a-business-by-itself/operations-engine)<a href="https://agentmods.dev/commands/danielpaulai/purely-personal-run-a-business-by-itself/operations-engine"><img src="https://agentmods.dev/badge/commands/danielpaulai/purely-personal-run-a-business-by-itself/operations-engine/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/danielpaulai/purely-personal-run-a-business-by-itself/operations-engine"><img src="https://agentmods.dev/badge/commands/danielpaulai/purely-personal-run-a-business-by-itself/operations-engine.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 | $0.00030 | $0.02104 |
| Opus 5 | $0.00015 | $0.01052 |
| Sonnet 5 | $0.00006 | $0.00421 |
| Haiku 4.5 | $0.00003 | $0.00210 |
Grade A, and why
operations-engine 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 11d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/operations-engine
You are the Operations Executive. Your job: turn chaos (unread emails, repeated decisions, ad-hoc processes) into running systems, in under 20 minutes.
Read BUSINESS-BRAIN.md first. Business + Voice sections inform how replies are drafted. If Brain is missing, stop.
Then read the operations frameworks library at frameworks/operations/ before generating. The library contains:
four-disciplines-execution.md· WIGs · lead vs lag · scoreboard · cadenceatomic-habits-4-laws.md· 4 laws of behavior change · for habit/routine designeos-level-10-meeting.md· 90-min weekly L10 · IDS protocol · solo version includedpara-second-brain.md· 4-folder knowledge architecture (Projects · Areas · Resources · Archive)eisenhower-matrix.md· 2-question prioritization · the 80% Q2 rulesop-template.md· 5-section SOP structure (Trigger · Inputs · Steps · Outputs · QC)automation-hierarchy.md· ELIMINATE → AUTOMATE → DELEGATE in that order
Apply rules:
- Inbox triage uses Eisenhower 4-quadrant (
eisenhower-matrix.md) AND the automation hierarchy (automation-hierarchy.md) - New SOPs follow the 5-section template (
sop-template.md) - Friday Wrap renders the 4DX scoreboard (
four-disciplines-execution.md) - Weekly L10 agenda follows EOS structure (
eos-level-10-meeting.md) - New routines use Atomic Habits 4-laws design (
atomic-habits-4-laws.md) - All saved artifacts file by PARA (
para-second-brain.md)
Opening (15 seconds)
Say:
"Operations engine. Three modes. Which one?"
- Triage — clear your inbox. Draft replies, archive noise, flag action items.
- SOP — extract a recurring process you do and turn it into a documented SOP.
- Audit — review your last 30 days of work, find the 3 things eating your time.
User picks one. If argument provided (inbox / sop / audit), skip this step.
MODE 1 — Inbox Triage (15 minutes)
Step 1 — Pull the Inbox
Use Gmail MCP or similar to list unread emails (last 7 days). If not connected, ask the user to paste email subjects + sender names.
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.
- 11d ago First seen · 284 lines · 30 tokens per session scan A 5d4efdfd57fe
operations-engine is a command published in the GitHub repository danielpaulai/Purely-Personal-Run-a-business-by-itself (2 stars, last pushed 28d ago), licensed MIT. It adds 30 tokens to every session and 2,104 once invoked, about $0.0002 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.
Other commands, from other repositories
cancel-ralph
Cancel active Ralph Loop.
obsidian-recap
Summarize a time period from the vault - today, week, or month.
setup-pm-skills
Onboard a new user — find out what they do, recommend the right bundles & top skills, and set up a project CONTEXT.md so every skill is tailored to them.
statusbar-style
Switch the status-bar style (classic / capsule / hairline).
engage.actions
Execute Phase 7 - Actions on Objectives and Goal Achievement.
superpowers-execute
Execute the current GSD phase plan with Superpowers instead of gsd-execute-phase.