Before following this workflow, read the Codex runtime contract. It defines plugin paths, model configuration, delegation, and persistence.
Poteto help
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 retain any user instruction to apply it throughout this task in durable notes.
This file maps questions to the skills and guide pages 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 plugin, which the user may not be able to open, so give the user the file's public copy: https://github.com/ScriptedAlchemy/pstack-codex/blob/main/plugins/pstack/ 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
$poteto-mode - Pick a skill for a situation
- Fix a run that went wrong
- Make pstack my own
Check the state that changes the answer, and mention it only when it does:
- No
~/.codex/pstack-models.mdmeans$setup-pstackhasn't run for this user, so every role uses its default model. - No
verify-*skill or other app harness in the project means agents have no scripted way to drive the app. Mention$create-verification-skillwhen the question is about proving a change works. - No formal verification skill in the project means no property is checked past what tests reach. Mention
$create-formal-verification-skillwhen the question is about a race, an invariant, or another case tests rarely hit. When one exists and the code it covers changed after the commit it records as last in sync, mention$maintain-formal-verification-skillif the question touches that code.
When the model rule is missing 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-pstackto type, and answer their question too. - Later: answer their question, and add one line saying every role keeps its default model until they run
$setup-pstack.
Get set up
- Install with
codex plugin marketplace add ScriptedAlchemy/pstack-codex, thencodex plugin add pstack@pstack-codex. Start a new Codex task. - Run
$setup-pstack. It asks for a reasoning budget, maps a model to each role, and writes~/.codex/pstack-models.md. Delegated roles read that file. It then offers to generate an app verification skill and a formal verification skill when the project lacks them. - Start a real task with
$poteto-mode, a goal, and a check that can pass or fail.
Installing changes nothing until the user invokes a skill. Only $setup-pstack loads from the user's words. The README and guide page 1 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 auto or inherit-parent runs on the chat's model, which saves tokens when the chat runs on Auto or a cheaper model. A shorter panel list runs fewer subagents, one for each entry. Save $poteto-mode for work that needs rigor.
This is the Codex port of pstack. Its runtime contract defines collaboration, worktrees, model overrides, heartbeat automations, and persistence. Installation does not register Cursor Custom Modes or provide Cursor built-ins.
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. Guide page 2 has examples.
Ask Codex to use $poteto-mode throughout the current task, and preserve that standing instruction in resume notes. For persistence in a repository across tasks, read the optional scoped AGENTS.md method and use it only when requested.
For subagents, follow CODEX.md and pass the absolute persona instruction path. Use a named agent only when the active host exposes that role. Spawning does not isolate a checkout or create a cloud VM.
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.
| The user wants to | Skill |
|---|---|
| Do any non-trivial task with rigor | $poteto-mode |
| Know how code works now, or where new code should live | $how |
| Know why code is shaped this way, or where a number came from | $why |
| Understand a change or subsystem, explained plainly | $teach |
| Catch up on their own recent work on a topic | $recall |
| Catch up on this chat and pending decisions | $ketchup |
Catch up like $ketchup, in a short silent video of slides, with the waiting calls as text under it | $ketchup-video |
| Know what a small diff could break outside itself | $blast-radius |
| Settle types and module shape before code that crosses a function boundary | $architect |
| Get several attempts at one brief, merged into the best one | $arena |
| Run parallel checks over slices, or race workers, through Codex subagents | $swarm |
| Have several models review a diff and try to break it | $interrogate |
| Fix a bug test-first when a cheap local test exists | $tdd |
Apply TypeScript rules to .ts or .tsx work | $typescript-best-practices |
| Strip comments before review, using a reviewer that didn't write them | $no-comments |
| Clean AI tells out of prose | $unslop |
| Write docs, an RFC, a README, a PR description, or a commit message to a standard | $technical-writing |
| Hear the last reply again in plain words | $bro |
| Give agents a scripted way to drive the app and prove behavior | $create-verification-skill |
| Bring a verification skill and its feature map back in line with the app | $maintain-verification-skill |
| Vet a performance number before reporting or acting on it | $benchmark-checklist |
| Run a large or cross-cutting change, or one to review after stepping away | $figure-it-out |
| Keep a decision log during a run, and review it afterward | $show-me-your-work |
| Pick a model for each role and a reasoning budget | $setup-pstack |
| Turn their own working habits into a personal mode skill | $automate-me |
| Turn what a finished task taught into skill edits | $reflect |
| Stop agents from repeating the same mistakes in this repo | $correct |
| Build a page over an existing Codex endpoint or the bundled loopback bridge | $make-bot-ui |
| Find their way around pstack | $poteto-help |
| Check that the agent understood their goal and the problem before it starts | $in-your-own-words |
| Get a prompt rewritten deeper, not bigger, before sending it: what a top professional would add, their raw material and methods, and an outside check. It returns the prompt and doesn't do the task | $sharpen |
| Formally verify a race, invariant, or other property that tests rarely reach | $create-formal-verification-skill |
| Bring a formal verification back in line after the code it covers changed, and learn whether a failure is drift or a bug | $maintain-formal-verification-skill |
| Show a PM or designer what the user sees as a chart checked by a model, with each bug drawn as a numbered path, turn an agreed chart into a TLA+ skeleton, or audit the code against its TLA+ spec | $statechart |
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:
$howexplains what the code does.$whyexplains the reasons.$teachruns one or both and explains the result plainly.$arenagives every worker the same brief and merges the best parts.$swarmsplits work into slices or a race and returns one report.$architectimplements right after it settles the design. Add "with checkpoint" to review the design before it writes code.$interrogatereviews the diff.$blast-radiuslooks for breakage outside the diff and proves the one fact that makes the change safe.$recallrebuilds context across recent chats.$ketchupcovers only this chat since the user's last message. Resuming one specific chat or branch is the Session pickup playbook.$figure-it-outdesigns one rigorous run. The Orchestrate playbook runs a program that spans days and many PRs. The Autonomous run playbook drives one task to a finish condition.
Host capabilities:
- A focused diff cleanup pass replaces Cursor deslop. Use the available browser, computer-use, terminal, or project verification skill for live proof.
- Use Codex skill-creator for authoring and the supported automation tool for future wakeups.
- Orchestrate is a poteto-mode playbook, not a separate pstack skill.
Playbooks and principles
Playbooks are step lists inside $poteto-mode, not skills, so they have no slash command. Inside $poteto-mode, describing the task picks one, and these phrases name one directly:
- "babysit this pr" or "check on pr 123" runs Babysit. It drives the PR to merge-ready and stops there. It doesn't merge unless the user asks to merge, land, or ship.
- "land the stack" runs Shipping.
- "take over this branch" runs Session pickup.
- "pause safely" runs Pause safely.
- "full autopilot on this queue" runs Autopilot-full. "stack them, don't ship" runs Autopilot-stack.
- "run the eval playbook" runs Eval.
Name $poteto-mode when you want pstack's Babysit playbook. The Playbooks section of poteto-mode lists every playbook and when it applies. Guide page 6 covers opening, babysitting, and landing a PR.
pstack has no separate planning skill. Use the host's available planning flow when appropriate. For work that spans phases or stacked PRs, asking $poteto-mode for a plan runs the Multi-phase plan playbook, which writes the plan and doesn't implement it. For a design question, the Prototype playbook or $architect settles it in code first.
Principles are one-rule skills that $poteto-mode reads and cites in its replies. The user rarely invokes one. They steer with the names instead, as in "apply prove it works. show me the real output." Typing $principle-<name> still loads one on demand. Guide page 8 lists them.
Fix a run that went wrong
| Symptom | Fix |
|---|---|
| The mode stopped applying after a few turns | Restate the task-long standing instruction and retain it in resume notes, or invoke $poteto-mode for the next task. |
| A question got treated as the next step of the last task | Say "new task", or say the turn doesn't need the mode. |
| A new model choice had no effect | Check ~/.codex/pstack-models.md and the active host model schema before the next delegation. |
| Runs cost more than expected | See the cost paragraph under Get set up. |
| A skill didn't load on its own | Only $setup-pstack loads from the user's words. The others load when the user types them or when $poteto-mode runs them, and it doesn't run every skill. |
| Parallel agents overwrote each other | Give each agent its own worktree, or run them run sequentially. Codex subagents share the host workspace. |
| An overnight run moved but finished nothing | A heartbeat or bounded monitor needs a check that can pass or fail, not a duration. See guide page 7. |
| The reply claims success from a green build | Ask for the real command, flow, stored value, or profile. That's the prove-it-works principle. |
For a run that drifts, references/prompting.md has one-line steers. Guide page 10 has more pitfalls and the recipes worth copying.
Make pstack my own
$automate-medrafts a personal mode skill from the user's own history, to use alongside$poteto-mode.$automate-maintainercaptures named GitHub users or groups from their engineering activity.$automate-teamdiscovers a repository's active core contributors and captures team conventions.$reflectafter a session turns its lessons into skill edits the user approves.$poteto-mode write a skill for <workflow>runs the authoring playbook. The eval playbook tests a skill change blind.- Fix a misbehaving skill in its own PR, not inside the feature work where it went wrong.
Guide page 9 covers each of these.
Reply
Lead with the answer. Give at most one example prompt in a code block, adapted from references/recipes.md when one fits, then the link to that file. Keep it short unless the user asked for the whole map.
