Cursor plugin specification and official plugins
TypeScript
pstack: update Opus 4.7 references to 4.8 (#98)
laurenec44aed93cda
diff --git a/pstack/skills/architect/SKILL.md b/pstack/skills/architect/SKILL.mdindex 37854ac2..0310fa4b 100644--- a/pstack/skills/architect/SKILL.md+++ b/pstack/skills/architect/SKILL.md@@ -30,7 +30,7 @@ Skip Phase A only when the work is genuinely greenfield with no surrounding systRun the **arena** skill with the design-sketch task and the Phase A grounding artifacts as input. Pass `references/runner-prompt.md` as each runner's prompt. Each candidate produces a design package shaped per `references/rationale-template.md`: the caller's usage written first, then the type sketch, function signatures, module map, and prose rationale derived from it.-Use these slugs for the Phase B runners: `claude-opus-4-7-thinking-xhigh`, `gpt-5.3-codex-high-fast`, `gpt-5.5-high-fast`, and `composer-2.5-fast`.+Use these slugs for the Phase B runners: `claude-opus-4-8-thinking-xhigh`, `gpt-5.3-codex-high-fast`, `gpt-5.5-high-fast`, and `composer-2.5-fast`.This is the **exhaust-the-design-space** principle skill made concrete. Whole-shape alternatives, not point fixes inside one shape.diff --git a/pstack/skills/arena/SKILL.md b/pstack/skills/arena/SKILL.mdindex 9ee0b927..8b3da49b 100644--- a/pstack/skills/arena/SKILL.md+++ b/pstack/skills/arena/SKILL.md@@ -25,7 +25,7 @@ The N candidates will receive the same prompt, so the prompt is the contract. Ge1. State the artifact each candidate is producing.2. Derive the rubric. State what success looks like for *this* task, then turn it into 3-6 concrete gradeable criteria. Concrete: `Adds a --dry-run flag that skips writes`. Vague: `code is correct`. The rubric is the picker's tool in Phase D; candidates only see the task.-3. Pick the runners. Default 4: `claude-opus-4-7-thinking-xhigh`, `gpt-5.3-codex-high-fast`, `gpt-5.5-high-fast`, and `composer-2.5-fast`. Spawn more when the arena covers multiple design directions. Same model N times when the work is generation-bound rather than judgment-sensitive.+3. Pick the runners. Default 4: `claude-opus-4-8-thinking-xhigh`, `gpt-5.3-codex-high-fast`, `gpt-5.5-high-fast`, and `composer-2.5-fast`. Spawn more when the arena covers multiple design directions. Same model N times when the work is generation-bound rather than judgment-sensitive.4. Assign output paths. Each candidate writes to its own location (a git worktree where possible, otherwise `/tmp/arena-<slug>/candidate-<n>/`). N candidates writing to the same path is shared mutable state and fails the the **separate-before-serializing-shared-state** principle skill test.## Phase B: Fan outdiff --git a/pstack/skills/how/SKILL.md b/pstack/skills/how/SKILL.mdindex efb56fa4..75d36a75 100644--- a/pstack/skills/how/SKILL.md+++ b/pstack/skills/how/SKILL.md@@ -64,7 +64,7 @@ Then proceed to Step 3.Spawn a single Task subagent that explores and explains in one pass:- `subagent_type`: `generalPurpose`-- `model`: `claude-opus-4-7-thinking-xhigh`+- `model`: `claude-opus-4-8-thinking-xhigh`- `readonly`: `true`This agent does its own exploration (Glob, Grep, Read) and writes the explanation directly. Read `references/explainer-prompt.md` for the communication style and output format. The agent follows the same structure, it just doesn't have explorer findings as input.@@ -76,7 +76,7 @@ Proceed to Step 4.Once all explorers have returned, spawn a single Task subagent to synthesize their findings into one coherent explanation:- `subagent_type`: `generalPurpose`-- `model`: `claude-opus-4-7-thinking-xhigh`+- `model`: `claude-opus-4-8-thinking-xhigh`- `readonly`: `true`The explainer gets all explorers' findings and writes the human-facing explanation (see output format below). Read `references/explainer-prompt.md` for the full prompt template. The explainer reconciles overlapping findings, resolves contradictions, and weaves the separate slices into a unified picture.@@ -113,7 +113,7 @@ After the explanation is complete, spawn architectural critics. Launch all in a| Subagent | Model ||----------|-------|-| Critic A | `claude-opus-4-7-thinking-xhigh` |+| Critic A | `claude-opus-4-8-thinking-xhigh` || Critic B | `gpt-5.3-codex-high-fast` || Critic C | `gpt-5.5-high-fast` |diff --git a/pstack/skills/interrogate/SKILL.md b/pstack/skills/interrogate/SKILL.mdindex 2ae56ef2..dcf8d8d6 100644--- a/pstack/skills/interrogate/SKILL.md+++ b/pstack/skills/interrogate/SKILL.md@@ -37,7 +37,7 @@ Launch all four in a single message using the Task tool, each with a different m| Subagent | Model ||----------|-------|-| Reviewer A | `claude-opus-4-7-thinking-xhigh` |+| Reviewer A | `claude-opus-4-8-thinking-xhigh` || Reviewer B | `gpt-5.3-codex-high-fast` || Reviewer C | `gpt-5.5-high-fast` || Reviewer D | `composer-2.5-fast` |diff --git a/pstack/skills/poteto-mode/SKILL.md b/pstack/skills/poteto-mode/SKILL.mdindex 7f0f8555..4e1a0f1a 100644--- a/pstack/skills/poteto-mode/SKILL.md+++ b/pstack/skills/poteto-mode/SKILL.md@@ -76,7 +76,7 @@ Read the leaf skill in full for any principle you apply.**Use `subagent_type: "poteto-agent"` for any subagent you spawn directly inside a playbook step** (code-writing delegates, ad-hoc helpers). `/poteto-mode` and `subagent_type: "poteto-agent"` route through the same wrapper. Routed workflow skills (`how`, `why`, `interrogate`, `reflect`) configure their own `subagent_type` for diverse-model review and exploration; respect what the skill prescribes rather than overriding it to `poteto-agent`.-**Defaults for every `Task` call.** `run_in_background: true`, agent mode (readonly strips MCP), file pointers not inlined context, and explicit model (`composer-2.5-fast` for code, `claude-opus-4-7-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, and explicit model (`composer-2.5-fast` for code, `claude-opus-4-8-thinking-xhigh` for prose and judgment).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.diff --git a/pstack/skills/poteto-mode/references/plan.md b/pstack/skills/poteto-mode/references/plan.mdindex 7855ca13..5b8b4543 100644--- a/pstack/skills/poteto-mode/references/plan.md+++ b/pstack/skills/poteto-mode/references/plan.md@@ -25,7 +25,7 @@ Resolve what is in scope vs explicitly out, technical or platform constraints, pDelegate codebase exploration (the **guard-the-context-window** principle skill).- Prefer `subagent_type: "poteto-agent"`. `generalPurpose` is the fallback. Never use the built-in `plan` subagent_type; it ignores this skill.-- Pass `model:` explicitly. `composer-2.5-fast` for code reads, `claude-opus-4-7-thinking-xhigh` for judgment.+- Pass `model:` explicitly. `composer-2.5-fast` for code reads, `claude-opus-4-8-thinking-xhigh` for judgment.Each explorer returns file pointers, conventions, dependencies, test infrastructure, and entry points. No inlined dumps.diff --git a/pstack/skills/reflect/SKILL.md b/pstack/skills/reflect/SKILL.mdindex 6b2ad9d8..94cdadf5 100644--- a/pstack/skills/reflect/SKILL.md+++ b/pstack/skills/reflect/SKILL.md@@ -38,15 +38,15 @@ One message, three `Task` calls, `subagent_type: generalPurpose`, explicit `mode| Lens | `model` | Prompt template ||---|---|---|-| Judgment | `claude-opus-4-7-thinking-xhigh` | `references/judgment-reviewer.md` |+| Judgment | `claude-opus-4-8-thinking-xhigh` | `references/judgment-reviewer.md` || Tooling | `composer-2.5-fast` | `references/tooling-reviewer.md` |-| Divergent | `claude-opus-4-7-thinking-xhigh` | `references/divergent-reviewer.md` |+| Divergent | `claude-opus-4-8-thinking-xhigh` | `references/divergent-reviewer.md` |Pass each template verbatim, substituting the transcript path or digest where marked. Reviewers return findings in the `Task` response body.### 3. Synthesize-One `Task` call, `subagent_type: generalPurpose`, `model: claude-opus-4-7-thinking-xhigh`, agent mode (`readonly: false`). The synthesizer's quality check includes spot-verifying citations, which can require MCP access; readonly strips MCPs and defeats that. Use `references/synthesizer.md` verbatim, with each reviewer's full output inlined where marked. The synthesizer returns a structured Accepted / Rejected / Backlog list.+One `Task` call, `subagent_type: generalPurpose`, `model: claude-opus-4-8-thinking-xhigh`, agent mode (`readonly: false`). The synthesizer's quality check includes spot-verifying citations, which can require MCP access; readonly strips MCPs and defeats that. Use `references/synthesizer.md` verbatim, with each reviewer's full output inlined where marked. The synthesizer returns a structured Accepted / Rejected / Backlog list.### 4. Structural enforcement checkdiff --git a/pstack/skills/why/SKILL.md b/pstack/skills/why/SKILL.mdindex 76526eab..04fd17d7 100644--- a/pstack/skills/why/SKILL.md+++ b/pstack/skills/why/SKILL.md@@ -163,7 +163,7 @@ If your scope assessment suggests a single-commit trivial target where the PR deSpawn one synthesizer subagent:- `subagent_type`: `generalPurpose`-- `model`: `claude-opus-4-7-thinking-xhigh`+- `model`: `claude-opus-4-8-thinking-xhigh`- `readonly`: `false` (agent mode). The synthesizer's quality check includes spot-verifying citations, which can require MCP access. Readonly/Ask mode strips MCPs and defeats that.The synthesizer gets: