* pstack: per-role model configuration via /setup-pstack, drop codex
Makes pstack's model choices configurable per role instead of hardcoded.
- New /setup-pstack skill detects your available models and writes
~/.cursor/rules/pstack-models.mdc, an always-applied rule with one
line per role.
- poteto-mode gains a Model configuration section (default table and
precedence). Skills read the configured model per role and fall back
to the inline default when the rule is absent, so nothing breaks
with no setup.
- Review panels (arena, architect, interrogate, how critics) are now
config-driven and count-agnostic. One subagent runs per configured
model, with no fixed count or A/B/C/D labels.
- Dropped gpt-5.3-codex-high-fast. bug-fix and perf-issue default to
gpt-5.5-high-fast; feature and refactoring stay composer-2.5-fast.
Version bump to 0.8.0.
* pstack: keep model config out of poteto-mode
Drop the Model configuration section and table from poteto-mode. The
canonical defaults live in the setup-pstack rule shape, and each skill
already carries its inline default, so poteto-mode only needs a one-line
pointer in its Task defaults. Fixes the plan.md and setup-pstack
back-references to the removed section.
* fix: match root planner by exact name in kickoff dedupe
findActiveRootPlanner adopted any active cloud agent whose name merely
started with the kickoff slug (`name.startsWith(rootSlug)`). Because the
kickoff command names every root planner exactly `${rootSlug}-root`, a
slug that is a prefix of another goal's slug would wrongly adopt the
unrelated planner: kicking off goal `auth` while `auth-ui-root` is
active matched `"auth-ui-root".startsWith("auth")`, silently attaching a
fresh run to the wrong goal's planner instead of starting a new one.
Match the deterministic canonical name `${rootSlug}-root` exactly. Adds
a regression test asserting a prefix-only slug overlap does not adopt.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* orchestrate: tighten kickoff-dedupe comments
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: lauren <lauren@anysphere.co>
* pstack: build-the-lever defaults to building the tool for any non-trivial work
* pstack: plain wording in build-the-lever Balance
* pstack: add gold-plating to unslop abstract-metaphor list
The skill and agent originally landed in cursor-team-kit via PR #70
and were unintentionally removed when the Thermos plugin (PR #92)
relocated them. Restoring here so they remain available in team-kit
alongside the standalone Thermos plugin.
- Restore cursor-team-kit/skills/thermo-nuclear-code-quality-review/SKILL.md
using the cleaned-up version (no internal-only references) that
Thermos already ships.
- Restore cursor-team-kit/agents/thermo-nuclear-code-quality-review.md
verbatim from the original PR (points at the cursor-team-kit plugin
for skill lookup).
- Add the skill + agent rows back to cursor-team-kit/README.md and
remove the now-misleading "moved to Thermos" pointer.
Users installing both plugins will see the same skill name in two
places; this is a known overlap and is fine for now.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Remove provenance sentence referencing Sualeh, the lukas-pr-review
internal skill, and the "Improve code quality" IDE feature name from
thermo-nuclear-code-quality-review.
- Rephrase thermo-nuclear-review description and intro to drop the
"web Deep review quick action" framing; describe the audit on its
own terms.
- Fix typo: memdium-to-high -> medium-to-high.
- Generalize the "Delete the database" example: drop the company name.
Co-authored-by: Cursor <cursoragent@cursor.com>
Thermos is a new plugin that packages thermo-nuclear branch review:
- thermo-nuclear-review (skill) — deep security/correctness audit
- thermo-nuclear-code-quality-review (skill) — harsh maintainability audit
- thermos (skill) — orchestrator that runs both reviews in parallel
with shared diff context and synthesizes findings
- Two Task subagents (one per review skill) for diff-scoped audits
The code-quality review previously lived in cursor-team-kit. Moved it
into Thermos alongside the new deep-review rubric so the two reviewers
sit together with their orchestrator. cursor-team-kit bumped to 1.2.0
with a pointer to the new plugin.
Marketplace and root README updated with the new entry.
Co-authored-by: Cursor <cursoragent@cursor.com>
* pstack: add usage examples to README
* pstack: condense README examples into a one-line bullet list
* pstack: drop trailing gloss from README examples, keep label + prompt
* pstack: wrap README examples in a single code block
the skills table listed every shipped non-principle skill except
typescript-best-practices. add a row for it in the README's existing
voice. the principles section already enumerates all eighteen principle
skills, including type-system-discipline, so it needs no change.
lauren tan's working style as a Cursor plugin. Bundles the poteto-mode
routing skill plus the workflow skills it routes through (how, why,
architect, arena, unslop, interrogate, automate-me, reflect, tdd) and
the full seventeen-skill set of first principles. Ships the poteto-agent
subagent that runs the same workflow end-to-end.
The why skill discovers available MCPs at run time and maps each to an
evidence category (source control, issue tracker, long-form docs,
real-time chat, infra observability, error tracking, analytics
warehouse). No third-party service integrations required.
cursor-team-kit's control-cli, control-ui, and deslop are referenced as
sibling-plugin dependencies for surfaces and commit cleanup; the kit
works standalone otherwise.
Marketplace entry registered at the root .cursor-plugin/marketplace.json.
Ports an unusually strict code-quality review rubric into cursor-team-kit:
ambitious "code-judo" simplifications, 1k-line file rule, spaghetti
detection, type/boundary cleanliness, and a hard approval bar. Adds a
matching Task subagent that loads the skill and applies it against a
collected diff.
Co-authored-by: Cursor <cursoragent@cursor.com>
lauren