Skip to content

pstack: route hardest tasks to claude-fable-5-thinking-max #143

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
poteto merged 1 commit into from
Jul 8, 2026
Merged

pstack: route hardest tasks to claude-fable-5-thinking-max #143

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion pstack/.cursor-plugin/plugin.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
{
"name": "pstack",
"displayName": "pstack",
"version": "0.10.1",
"version": "0.10.2",
"description": "if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence.",
"author": {
"name": "Lauren Tan"
Expand Down
2 changes: 1 addition & 1 deletion pstack/skills/poteto-mode/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ Read the leaf skill in full for any principle you apply. Each entry names when i

**Use `subagent_type: "poteto-agent"` for any subagent you spawn inside a playbook step** (code-writing delegates, ad-hoc helpers). `/poteto-mode` and `poteto-agent` route through the same wrapper. Routed workflow skills (`how`, `why`, `interrogate`, `reflect`) set their own `subagent_type` for diverse-model review; respect what the skill prescribes, don't override to `poteto-agent`.

**Defaults for every `Task` call.** `run_in_background: true`, agent mode (readonly strips MCP), file pointers not inlined context, explicit model per role (configurable via `/setup-pstack`; defaults `grok-4.5-fast-xhigh` for code, `claude-opus-4-8-thinking-xhigh` for prose and judgment).
**Defaults for every `Task` call.** `run_in_background: true`, agent mode (readonly strips MCP), file pointers not inlined context, explicit model per role (configurable via `/setup-pstack`; defaults `grok-4.5-fast-xhigh` for code, `claude-opus-4-8-thinking-xhigh` for prose and judgment). The hardest changes (cross-cutting design, gnarly concurrency, subtle algorithms, vague intent) go to `claude-fable-5-thinking-max`.

@cursor cursor Bot Jul 8, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hardest-tasks override never applies

Medium Severity · Logic Bug

poteto-mode hardcodes claude-fable-5-thinking-max for "hardest tasks", ignoring the configurable model defined via setup-pstack. Unlike other roles, this prevents user overrides in pstack-models.mdc from taking effect, forcing users to the hardcoded model even if they lack access or prefer another.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 3f43ff6. Configure here.


You own every subagent's work. Review the diff and write your own summary, don't pass through what it said. Interrupt-chained resumes silently drop directives, so fire a fresh subagent with consolidated scope rather than trusting a "done" summary. A second opinion is the same prompt against a different model. Agreement is high-signal.

Expand Down
1 change: 1 addition & 0 deletions pstack/skills/setup-pstack/SKILL.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,6 +40,7 @@ bug-fix: gpt-5.5-high-fast
perf-issue: gpt-5.5-high-fast
hillclimb: gpt-5.5-high-fast
judgment and prose: claude-opus-4-8-thinking-xhigh
hardest tasks: claude-fable-5-thinking-max
how explorer: grok-4.5-fast-xhigh
how explainer: claude-opus-4-8-thinking-xhigh
how critics: claude-opus-4-8-thinking-xhigh, gpt-5.5-high-fast, grok-4.5-fast-xhigh
Expand Down
Loading