Skip to content
Agentmart
Submit a tool

setup-pstack

Check pstack installation and configure role effort and panel size for Codex and Claude Code.

Skill by MachineLearning-Nerd

IndexedMIT
Write a review

Chalk Labs

Need help deploying setup-pstack?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/machinelearning-nerd-setup-pstack

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Check pstack installation and configure role effort and panel size for Codex and Claude Code. Models always inherit the current chat. Use for setup-pstack or pstack configuration requests.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/setup-pstack

What's inside

Skill name
setup-pstack
Description
Check pstack installation and configure role effort and panel size for Codex and Claude Code. Models always inherit the current chat. Use for setup-pstack or pstack configuration requests.
License
MIT
Instructions
42 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Setup pstack

Read ../pstack-harness/SKILL.md. Resolve the installed skills root and the explicit
project destination. Run its bundled `pstack.py doctor --project <root>` to check
payloads, native agent files, config, and CLI versions. File readiness and live
agent loading are distinct: inspect the session's agent catalog before claiming
activation. Start a fresh session when agent definitions were newly installed.

Every role inherits the current chat's model. The user selects the model in the
chat; setup does not assign separate models to workers or reviewers. Two-arm
panels still run two independent agents, labeled independent same-model review.
Do not change host settings, credentials, global configuration, or permissions.

When the user wants effort or panel-size settings, create `.pstack-dual/models.json` in the
project with `pstack.py config-init --project <root>` if absent. Use user scope
only when requested. Show the resolved role choices before applying preference
changes; existing authorization can supply those choices. The schema and example
are in ../pstack-harness/references/models.md.

Use `inherit-parent` for all model fields. Existing valid configuration files
remain compatible: explicit legacy model choices are ignored and reported through
`ignored_model` in role resolution. Do not rewrite user configuration merely to
remove those choices. Effort and panel size remain configurable independently.

Validate with `pstack.py validate-config --file <path>` and resolve representative
code, judgment, and panel roles with `pstack.py resolve`; every arm must have
`model: null`. Unsupported per-agent
effort inherits and is reported. Configuration updates apply to the next resolved
delegation, not automatically to agents already running.

If the project has no behavioral verification path, offer once to create a
[verification skill](../create-verification-skill/SKILL.md). If it has no formal
verification skill, separately offer once to create a
[formal verification skill](../create-formal-verification-skill/SKILL.md).
Generate either only when accepted; declining does not block setup. For an
existing formal skill whose covered code changed after its sync commit, point
to [formal verification maintenance](../maintain-formal-verification-skill/SKILL.md).
These offers do not authorize installing verification tools or changing product code.
Report the actual checks, unresolved capabilities,
and how to invoke `$poteto-mode` in Codex or `/poteto-mode` in Claude.

From MachineLearning-Nerd/pstack-dual, MIT.

More from MachineLearning-Nerd/pstack-dual

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Oct 21, 2026 (10 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from MachineLearning-Nerd

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get setup-pstack running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying setup-pstack?

CallGet help
Cite this page

setup-pstack skill. Agent Mart. https://agentmart.dev/skills/machinelearning-nerd-setup-pstack (last updated 2026-10-24)