setup-pstack
Configure which models pstack uses per role and at what reasoning budget.
Skill by n3m6
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/n3m6-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.
About
Use cases: finance, agent-building
Reviews
Write a reviewNo 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 and code. 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
- Configure which models pstack uses per role and at what reasoning budget. Detects your available models and writes a pstack preferences file that overrides the skill defaults. Use for @setup-pstack, "configure pstack models", "pstack budget", or changing pstack's model choices.
- License
- GPL-3.0
- Instructions
- 15 lines in SKILL.md · view on GitHub
Before installing
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Files (1)
- SKILL.md
SKILL.md (first lines)
# Setup pstack
Configure pstack's worker count and role preferences. Defaults inherit the parent model; no setup is required to start.
1. Read [OpenCode runtime](../../references/opencode-runtime.md), especially model overrides and configuration precedence. Inspect the session's available subagents, models, and variants, and which overrides an agent definition supports. Do not derive model IDs or variants by guessing suffixes.
2. Read existing settings with `python3 <pstack-root>/scripts/config.py show --project <project-root>`, where `<pstack-root>` is the package root (two levels above this skill's directory). Confirm which scope the user requested: personal settings at `~/.config/opencode/pstack/config.json` or project settings at `.opencode/pstack.json`. Preserve unrelated existing settings.
3. Show the current roles and worker counts. If the user already supplied choices, apply them. Otherwise ask only for preferences needed to configure them. Leaving every role inherited is a valid choice. A worker count is a total to queue; concurrency is bounded by `max_workers` and actual runtime limits.
4. Draft JSON with `version: 1`, optional `max_workers`, `arena_candidates`, `reviewers`, and `roles`. Each ordinary role is an object with separate `model` and `reasoning_effort` values. Candidate/reviewer roles can be lists of those objects, one seat per entry; an arena-judge list supplies a pool for one judge. Use `inherit-parent` for either setting to inherit it. Supported role names are defined in [config.py](../../scripts/config.py).
5. For overrides, write a temporary capability record from actual session metadata: `{"parent_model":"<confirmed-model>","models":{"<confirmed-model>":["<supported-effort>"]}}`. These are placeholders describing the schema, not real choices. Validate with `python3 <pstack-root>/scripts/config.py validate <draft.json> --capabilities <capabilities.json>`. Do not claim an override can run when no matching subagent or model supports it.
6. Write the selected file with `config.py write <draft.json> --destination <chosen-path>` and `--capabilities` when overriding a model or effort. Re-read effective settings. Explain that pstack reads this file itself; it is not a native OpenCode setting, and a role override only takes effect through a matching subagent.
7. If the task includes creating a verification skill, route to [create-verification-skill](../create-verification-skill/SKILL.md). Otherwise report any missing verification harness as an optional follow-up.
Reply with the saved scope, effective preferences, and unsupported choices or remaining gaps.From n3m6/opencode-config, GPL-3.0.
More from n3m6/opencode-config
- 0.640score
unslop
n3m6
Edit prose to remove AI writing patterns while preserving meaning, intended tone, and the requested format.
SkillAFreshness: A★ 19Claude Code +9 - 0.635score
no-comments
n3m6
Review comments and workaround explanations in a scoped diff, preserve necessary contracts, and fix accepted findings.
SkillAFreshness: A★ 19Claude Code +9 - 0.620score
architect
n3m6
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: A★ 19Claude Code +9 - 0.620score
create-verification-skill
n3m6
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: A★ 19Claude Code +9 - 0.620score
how
n3m6
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: A★ 19Claude Code +9 - 0.620score
interrogate
n3m6
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: A★ 19Claude Code +9 - 0.620score
poteto-mode
n3m6
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillAFreshness: A★ 19Claude Code +9 - 0.618score
figure-it-out
n3m6
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away.
SkillAFreshness: A★ 19Claude Code +9 - 0.618score
benchmark-checklist
n3m6
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
SkillAFreshness: A★ 19Claude Code +9 - 0.618score
correct
n3m6
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: A★ 19Claude Code +9 - 0.615score
principle-boundary-discipline
n3m6
Apply when wiring validation, error handling, or framework adapters.
SkillAFreshness: A★ 19Claude Code +9 - 0.615score
principle-encode-lessons-in-structure
n3m6
Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction.
SkillAFreshness: A★ 19Claude Code +9
Signals
- Stars
- 19
- Forks
- 2
- Open issues
- 1
- Last commit (this folder)
- Oct 6, 2026 (23 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- GPL-3.0
- Repository
- github.com/n3m6/opencode-config
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from n3m6
- 0.640score
unslop
n3m6
Edit prose to remove AI writing patterns while preserving meaning, intended tone, and the requested format.
SkillAFreshness: A★ 19Claude Code +9 - 0.635score
no-comments
n3m6
Review comments and workaround explanations in a scoped diff, preserve necessary contracts, and fix accepted findings.
SkillAFreshness: A★ 19Claude Code +9 - 0.620score
interrogate
n3m6
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: A★ 19Claude Code +9 - 0.620score
how
n3m6
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: A★ 19Claude Code +9 - 0.620score
create-verification-skill
n3m6
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: A★ 19Claude Code +9 - 0.620score
architect
n3m6
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: A★ 19Claude Code +9
Cite this page
setup-pstack skill. Agent Mart. https://agentmart.dev/skills/n3m6-setup-pstack (last updated 2026-10-24)