yabasha/pstack-openai
pstack-openai packages a set of engineering workflows — planning, implementation, review, and verification — as installable skills for ChatGPT and Codex. It is an unofficial, skills-only port of Lauren Tan's pstack, maintained by yabasha, and it ships 51 skills: 24 engineering principles and 23 task playbooks pinned to the pstack v0.15.15 baseline. It suits developers who want structured, repeatable agent behaviour inside a chat host rather than ad-hoc prompting — routing a task through poteto-mode, comparing implementations with arena, reviewing a change with interrogate and blast-radius, or explaining code with how and why.
The design is deliberately thin. Written in Python, the plugin supplies instructions plus bundled helper source, and nothing else: it does not provision models, register an MCP server, or enable integrations. Worker execution, model selection, history access, and persistence are left to the host and its current permissions, which keeps the port portable across Codex and ChatGPT. Reading skills needs no dependency installation; only the optional development helpers pull in Bun and pinned packages. Compatibility evidence is tracked against a frozen revision, covering 104 workflow cases per host with results split into passed, reduced-capability, and blocked.
That honesty about limits is the most interesting part. The README states plainly that reduced results do not establish full behaviour, that blocked cases stay unsupported in their recorded environment, and that directory publication is still pending. Attribution is handled carefully too, with upstream pins, hashes, and provenance in separate NOTICE and UPSTREAM files under the original MIT licence. It is worth a look as a study in packaging agent skills with explicit, auditable scope boundaries.
- Stars
- 0
- Forks
- 0
- Language
- Python
- Updated
- 19h ago
§ Readme
Edit on GitHub ↗Engineering workflows for planning, implementation, review, and verification in ChatGPT and Codex.
An unofficial, skills-only port of pstack, created by Lauren Tan. yabasha maintains and publishes this port. It includes 51 skills, including 24 engineering principles, and 23 task playbooks from the pinned pstack v0.15.15 baseline.
Website and examples · Get started · Choose a skill · Compatibility · Documentation
Free to use, with no plugin purchases. Availability is intended for all countries supported by the distribution platform. The existing upstream icon is retained.
What it does
- Routes engineering tasks through a playbook with
poteto-mode. - Compares alternative implementations with
arena, or divides independent work withswarmwhen the host supports workers. - Explains code and design decisions with
how,why, andteach. - Reviews changes with
interrogateand checks affected code withblast-radius. - Adds verification workflows and removes formulaic wording with
unslop.
The plugin provides instructions and bundled helper source. It does not provision models, register an MCP server, or enable integrations. Worker execution, model selection, history access, and persistence depend on the host and the permissions available in the current chat.
Get started
-
Install the package through your host's supported plugin controls. Follow the Codex setup guide or ChatGPT setup guide. Directory publication is still pending; do not assume a public listing exists.
-
Start a fresh chat with the plugin enabled and confirm its skills are available.
-
Invoke a skill with a concrete goal and a check for completion. For example:
Use poteto-help to choose a workflow for reviewing a pull request.Use poteto-mode to fix the failing checkout flow. Reproduce the bug, keep the change scoped, and verify the affected user journey.Use how to explain the authentication flow, citing the relevant files.
Slash-command availability depends on the host. If a command is absent, ask for the skill by name. If the host has not loaded the plugin, a name alone does not make its instructions available.
Reading skills requires no helper dependency installation. Some development helpers need Bun and their pinned dependencies. See helper setup before using those helpers.
Choose a skill
| Goal | Start with |
|---|---|
| Find the right workflow | poteto-help |
| Implement or fix something | poteto-mode |
| Sketch types and module boundaries | architect |
| Compare competing solutions | arena |
| Divide independent work | swarm |
| Review a change and its consequences | interrogate, blast-radius |
| Understand code or its rationale | how, why, teach |
| Build a project verification workflow | create-verification-skill |
| Improve prose | unslop |
Browse all 51 skills, all 24 principles, or the workflow selection guide.
Compatibility
Version 0.1.3 has retained discovery and workflow evidence for both hosts at frozen revision 51f209daf83cd97d64f89881d66533bb59dc57db. The reviewed results cover 104 workflow cases per host:
| Host | Passed | Reduced capability | Blocked |
|---|---|---|---|
| Codex | 33 | 50 | 21 |
| ChatGPT | 21 | 56 | 27 |
Package discovery is recorded separately. Reduced results do not establish full behavior or independent workers. Blocked cases remain unsupported in their recorded environment. See the reviewed results, Codex case index, and ChatGPT case index.
These results qualify the named frozen revision. The README and listing changes in this publication candidate need a new frozen revision and fresh discovery checks before release. See compatibility details and the publication checklist.
Documentation
| Topic | Guide |
|---|---|
| Installation | Codex, ChatGPT |
| Workflow walkthroughs | Poteto mode, Arena, Swarm |
| Original guide and port notes | Guide index |
| Troubleshooting | Troubleshooting, host test matrix |
| Optional helpers | Dependency setup, Benny readiness |
| Maintenance | Upstream updates, customization boundary, rollback |
| Publication | Readiness checklist and packaging command, changelog |
Permissions
Invoking a skill does not authorize installation, changes to settings, external messages, publishing, integrations, or recurring schedules. Workflows must respect the user's scope and the host's permissions. Model and worker claims require observed execution.
Credits and license
Lauren Tan created pstack and its skills and principles. yabasha maintains this unofficial port and its host adaptations, documentation, and packaging. The original MIT copyright and permission notice remain in LICENSE.
Read NOTICE.md for attribution and UPSTREAM.md for source pins, hashes, and adaptation provenance. This port is not affiliated with or endorsed by the upstream project or its author.
§ Cite this project
For papers, blog posts, & AI referencesBashar Ayyash. (2026). yabasha/pstack-openai [Computer software]. https://yabasha.dev/open-source/pstack-openai