Originally by poteto for Cursor pstack. Adapted for Hermes Agent.
In this page you install the plugin, pick which models pstack uses, and run your first task. Setup is one command plus a short conversation.
Install via the Hermes CLI:
hermes plugin add pstack
Hermes confirms the plugin is installed.
Load the setup skill:
load pstack:setup-pstack
pstack:setup-pstack reads your current Hermes config, detects the models you can route to, asks for a reasoning budget and a delegate model, then writes Hermes' native delegation settings (delegation.model, delegation.provider, delegation.reasoning_effort). Every delegate_task call pstack makes reads them.
Pick inherit-parent to keep delegates on your chat model. A rerun overwrites the same keys. To go back to the default, run hermes config unset delegation.model.
Hermes runs every delegate of one call on the same delegation model. Panels in pstack:interrogate and pstack:architect get their independence from separate subagents and distinct prompts. For a multi-model panel, change delegation.model between runs.
At the end of setup, pstack:setup-pstack checks whether your project has a way to prove app behavior, either a verify-* skill or an existing harness. If it finds neither, it says so once and suggests writing one. Verify and ship covers when it earns its place.
After setup, start a new chat. The model configuration applies to new sessions.
If you're new to pstack, say yes. An agent that can check its own work keeps going until the check passes. An agent that can't hands every result back to you to check by hand. Of everything in this guide, the verification skill pays off the most.
pstack spends extra tokens on subagents and review panels. That's the price of the rigor. To spend fewer:
- Rerun
pstack:setup-pstackand pick a smaller reasoning budget or cheaper models. A strong model in the main chat with cheaper, faster models in the code roles is a good split. - Let a role inherit the parent model so it runs on the chat's own model.
- Shorten a panel list. Each entry runs one delegate.
- Save
pstack:poteto-modefor work that needs rigor. A small, obvious edit doesn't.
Pick something real but small, and describe it the way you'd describe it to a colleague:
load pstack:poteto-mode add a --json flag to this command. text output stays byte-identical. verify both.
Watch the todo list. Its first items are the matched playbook's steps copied in, the Feature playbook for this prompt. If pstack:poteto-mode skips a step, the step stays in the list with skip: <reason>, so you can see what it chose not to do.
From here you can type normal follow-ups. pstack:poteto-mode is sticky. It stays on for the conversation until you opt out by saying so.