creedants/pstack-t3/poteto-help

Poteto help

Read the pstack-t3 runtime before spawning workers, choosing models, scheduling, or isolating work. It maps those steps onto T3's orchestrator tools.

Answer the user's question about pstack, hand them a prompt they can send, and link the file the answer came from. For a help question, don't start the work. The user asked how, and a pstack run spends real tokens, so let them send the prompt.

A message that asks for work, such as "use pstack to fix this bug", is not a help question. Read `poteto-mode`, do the work under it, and mention once that the next task should start with $poteto-mode.

This file maps questions to the skills and guide sections that hold the answers. Those files own the details. Read the file you route to before you quote it, and trust it when it disagrees with this map. The links here point into the installed skills, which the user may not be able to open, so give the user the file's public copy: https://github.com/creedants/pstack-t3/blob/main/ followed by its path.

Find out what they need

Infer the need from the message and the conversation. A named situation, such as "which skill reviews a PR?", goes straight to its section. If the need is still unclear, ask one multiple-choice question with these options, then answer only the section they pick:

• Get set up
• Start a task with $poteto-mode
• Pick a skill for a situation
• Fix a run that went wrong
• Make pstack my own

Check the state that changes the answer, and mention it only when it does:

• No .pstack/t3-roles.json, and no ~/.config/pstack-t3/roles.json or $XDG_CONFIG_HOME/pstack-t3/roles.json, means $setup-pstack hasn't run for this user, so every role except review backups resolves to inherit and runs on the chat's model, and review backups stays unset. Built-in defaults states the rule.
• No verify-* skill or other app harness in the project means agents have no scripted way to drive the app. Mention $create-verification-skill when the question is about proving a change works.
• No formal verification skill in the project means agents have no project skill for formal verification. Mention $create-formal-verification-skill when the question is about a race, an invariant, or another case tests rarely hit. When one exists and the code it covers changed after the commit it records as last in sync, mention $maintain-formal-verification-skill if the question touches that code.

When no roles file exists and it matters, ask whether the user wants to pick a model for each role and a reasoning budget now. It matters when the user is new, the question is about setup or cost, or the answer depends on which models run. Ask at most once per chat. If the need is also unclear, ask both questions together. Offer two choices:

• Now: give them $setup-pstack to type, and answer their question too.
• Later: answer their question, and add one line saying every role except review backups runs on the chat's model until they run $setup-pstack, and review backups stays unset.

Get set up

1. git clone https://github.com/creedants/pstack-t3.git ~/pstack-t3, then run python3 scripts/install.py in that directory. Then run python3 scripts/install.py doctor. Each provider should show the same count on both sides of N/N pstack-t3.
2. Run `$setup-pstack`. It asks for a reasoning budget, maps a model to each role, and writes ~/.config/pstack-t3/roles.json, or $XDG_CONFIG_HOME/pstack-t3/roles.json when that variable is set. Every skill reads that file when it resolves roles. Then it offers once each to generate a verification skill and a formal verification skill for the project, unless the project already has one.
3. Start a real task with $poteto-mode, a goal, and a check that can pass or fail.

Typing $name loads a skill. Most skills can also load when the request matches their description. $poteto-help has a narrow description, so type it. The README and install section have the details. Offer to word their first prompt with them, per `references/prompting.md`.

If cost is the worry, say where the tokens go and how to spend fewer. pstack spends extra tokens on subagents and review panels. Rerun $setup-pstack and pick a smaller budget or cheaper models. A role set to inherit runs on the chat's model, which saves tokens when the chat runs on a cheaper model. A shorter panel list runs fewer subagents, one for each entry. Save $poteto-mode for work that needs rigor.

pstack-t3 runs in T3 Code. Outside T3 covers other hosts.

Start a task with $poteto-mode

$poteto-mode matches the task to a playbook, copies the playbook's steps into the todo list, and runs the other skills as the steps need them. A step it skips stays in the list as skip: <reason>. A good prompt states the goal and how to tell it's done. It doesn't list skills, because a hand-written sequence tends to drop or reorder steps the playbook would keep. Read `references/prompting.md` before you help word one. The guide's first task has an example.

Whether $poteto-mode stays on:

• Naming $poteto-mode in a message attaches the skill to that message. It fades as the chat moves on.
• T3 has no switch that pins the skill on later tasks. Start the next task with $poteto-mode again.

Mid-chat, "new task" makes the mode match a fresh playbook. $poteto-mode already uses the poteto-agent persona for the subagents its playbook steps spawn. To get the same style from a subagent of your own, call delegate_task and paste the body of `../pstack-runtime/agents/poteto-agent.md` at the top of the brief. The runtime has the call shape.

Pick a skill

The default answer is $poteto-mode, which runs most of the others when its steps need them. Name a skill directly when the user wants more or less of something than the playbook gives. Read the skill before you recommend it, and give one example prompt.

If a skill directory next to this one is missing from the table, read its frontmatter and route by its description. The principle-* directories are covered under principles below.

Close calls: