pstack-claude-mirror 0.0.0-stage → 0.9.133

package/plugins/pstack/pi/worktree.ts

@@ -0,0 +1,74 @@
+import { spawnSync } from "node:child_process";
+import { existsSync, lstatSync, realpathSync } from "node:fs";
+import { join } from "node:path";
+import { type Static, Type } from "typebox";
+
+export const worktreeSchema = Type.Object({ repo: Type.String(), path: Type.String(), branch: Type.String(), base: Type.String() });
+export type Worktree = Static<typeof worktreeSchema>;
+
+// The error message ends up in an agent's final text, so it stays short. The
+// buffer is sized for a long reflog, which the default 1 MB is not.
+function git(cwd: string, args: string[], input?: string): string {
+  const r = spawnSync("git", args, { cwd, encoding: "utf8", input, maxBuffer: 256 * 1024 * 1024 });
+  if (r.status !== 0) throw new Error(`git ${args.join(" ").slice(0, 200)} failed: ${(r.stderr || r.error?.message || "").trim().slice(0, 1000)}`);
+  return r.stdout.trim();
+}
+
+export function planWorktree(cwd: string, agentId: string): Worktree {
+  const repo = git(cwd, ["rev-parse", "--show-toplevel"]);
+  return {
+    repo,
+    path: join(repo, ".claude", "worktrees", `agent-${agentId}`),
+    branch: `worktree-agent-${agentId}`,
+    base: git(repo, ["rev-parse", "HEAD"]),
+  };
+}
+
+// An existing path can be a leftover directory, a replacement repository, or
+// a link to another checkout. None is permission to run an isolated writer there.
+function assertWorktree(wt: Worktree): void {
+  const invalid = () => new Error(`not the expected linked worktree: ${wt.path.slice(0, 200)}`);
+  if (!lstatSync(wt.path).isDirectory()) throw invalid();
+  const root = realpathSync(wt.path);
+  if (root === realpathSync(wt.repo) || root !== realpathSync(git(wt.path, ["rev-parse", "--show-toplevel"]))) throw invalid();
+  const commonDir = (cwd: string) => realpathSync(git(cwd, ["rev-parse", "--path-format=absolute", "--git-common-dir"]));
+  if (commonDir(wt.path) !== commonDir(wt.repo)) throw invalid();
+  const registered = git(wt.repo, ["worktree", "list", "--porcelain", "-z"]).split("\0").some((field) => {
+    if (!field.startsWith("worktree ")) return false;
+    try {
+      return realpathSync(field.slice("worktree ".length)) === root;
+    } catch {
+      return false;
+    }
+  });
+  if (!registered) throw invalid();
+}
+
+// Creates the worktree on first use and re-creates it for a resume after a
+// clean finish removed it. A retained path is checked before any child starts.
+export function ensureWorktree(wt: Worktree): void {
+  if (!existsSync(wt.path)) {
+    const branchExists = git(wt.repo, ["branch", "--list", wt.branch]) !== "";
+    git(wt.repo, branchExists ? ["worktree", "add", wt.path, wt.branch] : ["worktree", "add", wt.path, "-b", wt.branch, wt.base]);
+  }
+  assertWorktree(wt);
+}
+
+// True when the agent left anything behind and the worktree stays. Ignored
+// files count: a build the agent produced is its output too, and a fresh
+// checkout has none. Commits are counted from the branch and from every
+// commit HEAD's reflog visited, since an agent can commit on a detached HEAD
+// and move away, which leaves the commit reachable only from the reflog.
+export function settleWorktree(wt: Worktree): boolean {
+  if (!existsSync(wt.path)) return false;
+  assertWorktree(wt);
+  // A display preference must not hide output from automatic cleanup.
+  const dirty = git(wt.path, ["status", "--porcelain", "--untracked-files=normal", "--ignored"]) !== "";
+  // The reflog goes in on stdin: a long one would overflow an argument list.
+  const visited = git(wt.path, ["log", "-g", "--format=%H", "HEAD"]);
+  const ahead = git(wt.path, ["rev-list", "--count", "--stdin"], `${visited}\nrefs/heads/${wt.branch}\n^${wt.base}\n`) !== "0";
+  if (dirty || ahead) return true;
+  git(wt.repo, ["worktree", "remove", wt.path]);
+  git(wt.repo, ["branch", "-D", wt.branch]);
+  return false;
+}

package/plugins/pstack/skills/architect/SKILL.md

@@ -0,0 +1,100 @@
+---
+name: architect
+description: "Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape."
+---
+
+# Architect
+
+On Codex, read the [platform mapping](../poteto-mode/references/codex-tools.md), including its per-skill notes, before following this skill.
+
+On GitHub Copilot, read the [platform mapping](../poteto-mode/references/copilot-tools.md), including its per-skill notes, before following this skill.
+
+On Muse, read the [platform mapping](../poteto-mode/references/muse-tools.md), including its per-skill notes, before following this skill.
+
+On Antigravity, read the [platform mapping](../poteto-mode/references/agy-tools.md), including its per-skill notes, before following this skill.
+
+Sketch types, function signatures, class shapes, and module boundaries with `not implemented` bodies and pseudocode. Synthesize across multiple model perspectives, then fill in code against the chosen sketch.
+
+## Start
+
+Open a todolist with one entry per phase before starting.
+
+1. Ground
+2. Sketch
+3. Agree
+4. Implement
+5. Scrap
+
+## Phase A: Ground the problem
+
+Build a real mental model of every system the new code touches. Run the **how** skill over the relevant subsystems. Naming a file isn't grounding. Produce the architectural explanation `how` prescribes. If the design redefines ownership or layering, also run the **why** skill on the existing shape so the rationale becomes a constraint, not a guess.
+
+Skip Phase A only when the work is genuinely greenfield with no surrounding system to integrate.
+
+## Phase B: Sketch
+
+Run the **arena** skill with the design-sketch task and the Phase A grounding artifacts. Pass `references/runner-prompt.md` as each runner's prompt.
+
+Take the runners from the `architect runners` line in `pstack-models.md`, in place of the `arena runners` line. If the sheet or that line is missing, use the defaults in [Models](#models). Alias and rejected entries follow the runner rules in the **arena** skill's Phase A.
+
+Design it twice. Require at least two structurally distinct candidates before synthesis, even when the first looks sufficient. This is the **exhaust-the-design-space** principle skill made concrete. Whole-shape alternatives, not point fixes inside one shape.
+
+Screen every candidate against [`references/design-red-flags.md`](references/design-red-flags.md) before synthesis. Assume the next contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Prefer the design where a change that looks right from one file is right for the whole repo.
+
+Compare viable candidates on interface depth. Prefer the design that hides more complexity behind a smaller, simpler public surface. A rich interface can keep call chains short by concentrating capability instead of scattering it across layers.
+
+Arena returns one synthesized design package. Its synthesis decision fills the rationale's "Synthesis decision" section.
+
+## Phase C: Agree (opt-in)
+
+Default: proceed directly to implementation with the synthesized design. No human checkpoint.
+
+Opt in to a checkpoint when the invoker explicitly asks: "/architect with checkpoint," "stop and show me before implementing," or similar. Then surface the synthesized design and pause for sign-off.
+
+The synthesis can ship as its own commit either way, as the "scaffold first" mode of the **foundational-thinking** principle skill. Planned and scoped breakage during fill-in is fine, per the **outcome-oriented-execution** principle skill. For adversarial pressure on the design before implementing, run the **interrogate** skill on the synthesized sketch.
+
+If the human pushes back on the shape (in a checkpoint or after the fact), treat that as Phase A evidence. Re-ground and re-run Phase B before writing more code.
+
+## Phase D: Implement against the sketch
+
+Replace `not implemented` bodies with code, pseudocode with logic. The synthesized sketch is the contract. Deviations from it are signal to surface, not friction to absorb silently. If a function needs a parameter the sketch didn't anticipate, ask whether the sketch was wrong, the requirement was missed, or the implementation is overreaching.
+
+Before closing each implementation unit or handing its contract to the next worker, compare accepted deviations with the saved behavior contracts, interfaces, and responsibility assignments. Once the appropriate owner or review process accepts a change, update the affected parts of the existing sketch and rationale. Record the acceptance source there. A change from raising an error to returning a refusal must update the outcome contract before the next unit begins.
+
+For a local deviation that leaves the shared contract intact, record the decision and why the design still holds; a local variable rename need not rewrite the architecture. Keep unaccepted changes and unresolved disagreements visible. Do not call the unit reconciled while the next worker would receive contradictory instructions, or edit the specification merely to justify what was implemented. Use the existing design artifact rather than a parallel record per unit. Repeated structural deviations still trigger Phase E.
+
+## Phase E: Scrap when the architecture is wrong
+
+If implementation keeps producing friction the sketch can't absorb, throw the sketch out. Don't bolt fixes onto a wrong design, per the **redesign-from-first-principles** and **fix-root-causes** principle skills.
+
+The signal is a *pattern*, not single instances. Tells:
+
+- The same shape of workaround appearing repeatedly across unrelated code.
+- Multiple unrelated edge cases that all need special-case branches.
+- Types that need escape hatches (`any`, casts, optional fields always set in practice) to compile.
+- The "we need a lock" reflex when the sketch said the state wasn't shared.
+- Callers having to know the abstraction's internal rules to use it.
+- Two or more independent Phase D deviations of the same shape across the implementation.
+
+Use judgment. A few edge cases don't condemn an architecture. Some problems are legitimately complex. Complexity in the data is not complexity in the design.
+
+When you scrap:
+
+1. Re-run the **how** skill over what's been built.
+2. Redesign as if the new constraints had been day-one assumptions, per redesign-from-first-principles.
+3. Subtract before adding, per the **subtract-before-you-add** principle skill. The new sketch should be smaller than the old one before it grows.
+4. Return to Phase B and re-run arena.
+
+## Outputs
+
+The caller's usage is written first and the type sketch derived from it. One file with new types and signatures for small changes. Module map plus type definitions for larger work. The rationale ships alongside, shaped per `references/rationale-template.md`, including the usage sketch and the synthesis decision.
+
+## Models
+
+Role defaults, stamped from `plugins/pstack/models.json` (edit there, rerun `tools/generate.mjs`). A matching role line in the `pstack-models.md` override sheet overrides each at runtime; `/setup-pstack` writes it and lists its path per runtime.
+
+- architect runners: `opus`, `fable`, `sonnet`, `haiku`
+
+## Reasoning effort
+
+A role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. On Claude Code, `session` sets no effort. On other runtimes, follow the platform mapping for `session`. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. Pass the level as the dispatch's effort field and keep the `subagent_type` you would otherwise use. That is `effort` on the Claude Code `Agent` call and `reasoning_effort` on Codex's `spawn_agent`. On Muse it is `effort` on a Workflow child; a `subagent_spawn` dispatch keeps the session's effort.

package/plugins/pstack/skills/architect/references/design-red-flags.md

@@ -0,0 +1,57 @@
+# Design red flags
+
+Screen every candidate before synthesis. A red flag is a reason to revise or reject the shape.
+
+## Shallow module
+
+A shallow module exposes a large interface while hiding little complexity. Judge depth by the capability and policy hidden behind the public surface relative to the size of that surface. Prefer a simple interface backed by substantial behavior.
+
+Do not confuse a deep module with a deep call chain. A deep call chain scatters understanding across layers. A deep module concentrates capability behind one interface.
+
+Look for these signs:
+
+- Callers coordinate several methods to complete one operation.
+- Public options expose internal stages or implementation choices.
+- Learning the interface does not save the caller from learning the implementation.
+
+## Information leakage
+
+Information leakage makes multiple modules depend on the same internal decision. A representation, policy, or protocol detail appears in more than one place, so changing it requires coordinated edits.
+
+Public re-exports of transport or wire types are leakage. Parse external data into domain types behind the interface. Keep storage schemas, framework objects, and protocol details private.
+
+## Temporal decomposition
+
+Temporal decomposition organizes modules by execution order instead of the knowledge they own. Separate load, validate, transform, and save stages often repeat one representation and its invariants across several boundaries.
+
+Group code around domain knowledge and ownership. Methods that run at different times can still belong to one module when they protect the same decisions.
+
+## Pass-through method
+
+A pass-through method forwards the same arguments to another method with the same shape. It adds a layer without hiding complexity.
+
+Remove it or move responsibility to the module that can complete the operation. Keep a forwarding boundary only when it adds policy, adaptation, or a distinct abstraction.
+
+## Split ownership
+
+More than one module writes the same state or keeps its own copy of it. An agent that edits one writer can't see the others, so their rules diverge.
+
+Give each piece of state one owner. Other modules read it or ask the owner to change it.
+
+## Two ways to do one task
+
+The design supports more than one way to do the same task. An agent copies whichever way it finds first, so every way keeps gaining callers.
+
+Keep one way. Move callers off the others and delete them in the same change.
+
+## Importable internals
+
+A caller can import a module's internals. An agent takes the shortest path that compiles, so it imports them directly and they become part of the interface.
+
+Make internals unreachable from outside the module, so an import from outside fails the build.
+
+## Hand-synced list
+
+Two or more places list the same items, and adding an item means editing every list. An agent that sees one list updates only that one.
+
+Keep one list and derive the others from it. If a list can't be derived, make the build fail when the lists disagree.

package/plugins/pstack/skills/architect/references/rationale-template.md

@@ -0,0 +1,39 @@
+# Rationale template
+
+The prose that ships alongside the type sketch. One page. Sentence-case headings, no boilerplate. Replace the italic notes with actual content.
+
+## Problem
+
+*One paragraph. What we're trying to do, and what about the existing system or constraints makes the shape non-obvious. If [Phase A](../SKILL.md#phase-a-ground-the-problem) surfaced constraints the design must honor (existing types to interop with, callers we can't break, invariants that crossed our boundary), name them here so the reader sees the same constraints you saw.*
+
+## Usage (caller's view)
+
+*Write this first, before the type sketch. Show the README or quickstart the consumer reads, plus two or three realistic call sites in their own code. What they import, what they call, what comes back. The type sketch in [Shape](#shape) is derived from this. The two must agree. When they diverge, reconcile the sketch to the usage, not the reverse. The caller's experience is the spec. The types serve it.*
+
+## Shape
+
+*The recommended architecture. Data structures first. Then how data flows through the signatures. Name the load-bearing decisions. State which invariants are encoded in types, where validation lives, and what the system deliberately does not do. Judge interface depth explicitly. State what complexity the public surface hides, what remains exposed to callers, and why the interface is no larger than needed. Cite the principle behind each decision (e.g., `per boundary-discipline`). Don't restate it.*
+
+## Synthesis decision
+
+*Filled in by [arena](../../arena/SKILL.md). Records which candidate became the base and why, what was adapted from each of the others, and what was rejected and why.*
+
+## Tradeoffs accepted
+
+*One bullet per tradeoff the chosen shape makes. Form: "we accept X in exchange for Y." Name anything a future reader might mistake for an oversight, including things that look like premature optimization or premature simplification.*
+
+## Alternatives considered
+
+*Required. Name at least one concrete alternative shape, with one line on why it lost. Judge each alternative on interface depth, not implementation simplicity alone. Name the complexity it exposes to callers and the complexity it hides. Two or three alternatives belong here when the design space had real contenders. One is fine when the constraints forced the answer, with the conclusion phrased as "this was the only viable shape because..." Avoid listing flavors of the same shape. This section covers design alternatives the chosen shape considered and rejected, not other runner candidates.*
+
+## Implementation reconciliation
+
+*During implementation, record accepted deviations and their acceptance sources here, and update the affected usage, outcome contracts, signatures, and ownership in this design. Record why local deviations leave the shared contract valid. Keep unaccepted changes unresolved. Reconcile before closing a unit or handing its contract to the next worker.*
+
+## Open questions and risks
+
+*Things you noticed during the sketch that the human needs to weigh in on, and risks worth flagging before implementation starts. Phrase as questions, not assertions, so the human's answer is the resolution rather than a comment.*
+
+## Next implementation step
+
+*The first thing to build against the sketch. One sentence. What you'd start writing immediately after synthesis (or after Phase D sign-off, if a checkpoint was opted into).*

package/plugins/pstack/skills/architect/references/runner-prompt.md

@@ -0,0 +1,20 @@
+# Architect runner prompt
+
+The orchestrator passes this file through to every parallel candidate runner during Phase B and fills in the variable inputs around it: the task, the Phase A grounding artifacts, the isolated working directory, and the path to write outputs. The working directory is a git worktree when available, otherwise a per-runner subdirectory under the sketch dir. What matters is independence between candidates.
+
+You are producing one candidate design in architect's parallel exploration. Read the **architect** skill in full first. That's the workflow you're inside. Output a candidate design package: type sketch, function signatures, module map, and prose rationale shaped per [`rationale-template.md`](rationale-template.md).
+
+Apply the following discipline. The orchestrator compares candidates on these axes to pick a base.
+
+- Caller's usage first. Write the README-style usage and two or three real call sites before the types, then derive the type sketch from them. The usage is the spec. The two must agree, so reconcile the sketch to the usage, not the reverse.
+- Data structures first. Get the core types right and the code becomes obvious. Trace each dominant access pattern through the proposed structure. If the answer is "we'll add a map / index / cache later," the structure is wrong.
+- Interface depth. Compare the capability hidden behind the public surface relative to the size of that surface. Prefer a simple interface that pulls complexity into the callee, even when the implementation becomes less simple. Do not put transport or wire types on the public API. Parse into domain types behind the interface.
+- Shared state: if two actors might both write, ask "what happens?" If the answer isn't "nothing," default to per-actor state with a merge at the read boundary, per the **separate-before-serializing-shared-state** principle skill.
+- Make boundaries visible. `not implemented` errors for bodies, `// TODO` pseudocode for tricky logic, doc comments stating intent and invariants. A reader should trace data from input to output by reading types and signatures alone.
+- Encode invariants in types: hard-to-misuse types > runtime checks > prose comments, per the **encode-lessons-in-structure** principle skill.
+- Validate at boundaries, trust types inside, per the **boundary-discipline** principle skill. Business logic as pure functions. The shell stays thin.
+- Single source of truth per invariant. Derive instead of sync.
+- Idempotent state transitions where applicable, per the **make-operations-idempotent** principle skill. Ask what happens if the operation runs twice or crashes halfway.
+- Short call chains. If tracing the flow needs more than three files, flatten the hierarchy, per the **laziness-protocol** and **minimize-reader-load** principle skills.
+
+You are one of the parallel runners, each on a different model. Produce the best design your model can make. Don't hedge against the others. Differences between candidates are the signal used to pick a base and graft. Converging on a safe-looking middle defeats the exploration.

package/plugins/pstack/skills/arena/SKILL.md

@@ -0,0 +1,66 @@
+---
+name: arena
+description: "Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape."
+---
+
+# Arena
+
+On Codex, read the [platform mapping](../poteto-mode/references/codex-tools.md), including its per-skill notes, before following this skill.
+
+On GitHub Copilot, read the [platform mapping](../poteto-mode/references/copilot-tools.md), including its per-skill notes, before following this skill.
+
+On Muse, read the [platform mapping](../poteto-mode/references/muse-tools.md), including its per-skill notes, before following this skill.
+
+On Antigravity, read the [platform mapping](../poteto-mode/references/agy-tools.md), including its per-skill notes, before following this skill.
+
+Open a todolist with one entry per phase (Frame, Fan out, Cross-judge, Pick, Graft, Verify) before launching anything.
+
+## Phase A: Frame
+
+Every candidate gets the same prompt, so the prompt is the contract.
+
+1. State the artifact each candidate is producing.
+2. Derive the rubric, 3-6 concrete gradeable criteria for what success looks like on *this* task. It is the picker's tool in Phase D. Candidates only see the task.
+3. Pick the runners. Use the `arena runners` line in `pstack-models.md`. If the sheet or that line is missing, run one each on the defaults in [Models](#models). An `auto` or `inherit-parent` entry in this line means the parent model, so omit `model` for it. If the `Agent` tool rejects a configured entry, run that seat on its family's default and say so. Families go by model name, such as Opus, Fable, or Sonnet. If the family has no default, or the `Agent` tool rejects that default, use the closest valid slug of the same family from its error message, or drop the seat and say so when there is none. If dropped seats leave fewer than two runners, add runners until there are two, or one when the line has one entry. Run each added runner on a remaining runner's model, or omit `model` so it runs on the parent model when none remain, and say so. Spawn more runners when the arena covers multiple design directions. Use the same model N times when the work is generation-bound rather than judgment-sensitive. Pick each subagent's reasoning level for the job, per the Subagents section of the **poteto-mode** skill.
+4. Give each candidate its own output location (a git worktree where possible, otherwise `/tmp/arena-<slug>/candidate-<n>/`), per the **separate-before-serializing-shared-state** principle skill.
+
+## Phase B: Fan out
+
+Spawn all N subagents in one message with `run_in_background: true`, each with the task, the path to the shared grounding, its own output path, and instructions to produce the artifact and a short rationale naming the alternatives it considered and what it rejected.
+
+If a candidate produces no output, proceed with N-1 and note the dropout.
+
+## Phase C: Cross-judge
+
+After all Phase B candidates complete, choose one model from the `arena cross-judge pool` line in `pstack-models.md`. If the sheet or that line is missing, choose from the runner defaults in [Models](#models). Spawn one readonly judge subagent. The judge is never from the parent's family, as Phase A step 3 defines families. Try only the entries from another family, in pool order. An `auto` or `inherit-parent` entry is the parent model, so it never judges. If the `Agent` tool rejects an entry, use a valid slug of the same model at the closest level or speed from the error message, or move to the next entry when there is none. If no entry from another family runs, try the default pool's entries from another family the same way. If none of those runs, skip the judge, pick the base alone in Phase D, and say so. If you do not know the parent's model, try the pool's real slugs in pool order and say that the family check did not run. The judge sees the rubric and the candidates by path label, scores each criterion, and recommends a base with rationale. It runs in parallel with your reading in Phase D. Don't spawn it while candidates are still writing.
+
+## Phase D: Pick a base
+
+Read every candidate end to end before picking. Score each against the rubric criterion by criterion, not on holistic feel, and compare with the cross-judge when Phase C ran one. Agreement on the base confirms the pick. Disagreement means one of you is biased or the rubric was ambiguous. Read both rationales before deciding.
+
+Pick the base a future maintainer can extend most easily without breaking invariants. When two feel tied, prefer the cleaner boundary or smaller API, per the Laziness Protocol.
+
+## Phase E: Graft
+
+Walk each losing candidate once more for what is worth porting into the base, usually one or two things per candidate, not most of it. Fold each graft in by hand, per the **redesign-from-first-principles** principle skill, so the result stays coherent under one mental model. Don't paste mechanically.
+
+If the candidates converge on one shape, that is strong agreement. Note it and ship the consensus shape. No graft is needed. If they wildly diverge, Phase A was under-specified. Reframe and re-run rather than averaging the divergence.
+
+## Phase F: Verify
+
+Verify the synthesized artifact like any other output, per the **prove-it-works** principle skill. If verification finds a problem the arena missed, either Phase A was wrong (re-frame and re-run) or a candidate caught it and you missed the graft (go back to Phase E). Don't paper over it.
+
+## Outputs
+
+One synthesized artifact, with a short synthesis note alongside naming the base and why, the cross-judge's verdict or that Phase C skipped the judge, each graft with its source candidate, what was rejected and why, any convergence or dropouts, and the verification result.
+
+## Models
+
+Role defaults, stamped from `plugins/pstack/models.json` (edit there, rerun `tools/generate.mjs`). A matching role line in the `pstack-models.md` override sheet overrides each at runtime; `/setup-pstack` writes it and lists its path per runtime.
+
+- arena runners: `opus`, `fable`, `sonnet`, `haiku`
+- arena cross-judge pool: `opus`, `fable`, `sonnet`, `haiku`
+
+## Reasoning effort
+
+A role value in the override sheet may name a reasoning effort after its model, as in `opus @xhigh`. Levels on Claude Code: `low`, `medium`, `high`, `xhigh`, `max`. Which ones apply depends on the model. A value without `@` takes the sheet's `default effort` line, a level or `session`, and `session` when the sheet has no such line. On Claude Code, `session` sets no effort. On other runtimes, follow the platform mapping for `session`. Strip the suffix before reading the model: `inherit-parent` or `auto` still omits `model` at every level, and a model name is passed as `model`. Pass the level as the dispatch's effort field and keep the `subagent_type` you would otherwise use. That is `effort` on the Claude Code `Agent` call and `reasoning_effort` on Codex's `spawn_agent`. On Muse it is `effort` on a Workflow child; a `subagent_spawn` dispatch keeps the session's effort.

package/plugins/pstack/skills/automate-me/SKILL.md

@@ -0,0 +1,111 @@
+---
+name: automate-me
+description: "Use for \"automate me\", \"create/update/refresh my -mode skill\", \"turn/capture my preferences or working style into a skill\", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via plugin-dev:skill-development + unslop, optionally pulling fresh evidence from recent transcripts."
+---
+
+# Automate me
+
+On Codex, read the [platform mapping](../poteto-mode/references/codex-tools.md), including its per-skill notes, before following this skill.
+
+On GitHub Copilot, read the [platform mapping](../poteto-mode/references/copilot-tools.md), including its per-skill notes, before following this skill.
+
+On Muse, read the [platform mapping](../poteto-mode/references/muse-tools.md), including its per-skill notes, before following this skill.
+
+On Antigravity, read the [platform mapping](../poteto-mode/references/agy-tools.md), including its per-skill notes, before following this skill.
+
+A guided flow for turning the user's working conventions into a skill agents will follow. The output is one `-mode` skill tailored to them (e.g. `jay-mode`, `priya-mode`).
+
+This skill orchestrates three others: an inline mining pass (see step 1), the **plugin-dev:skill-development** skill (authoring), and the **unslop** skill (prose discipline). It sequences them. It doesn't replace them.
+
+## Flow
+
+### 0. Check for an existing skill
+
+Look recursively for `.claude/skills/**/*-mode/SKILL.md` and `${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/*-mode/SKILL.md` matching the user's handle. Mode skills can live in a personal category directory (`.claude/skills/<handle>/`), not only at the top level. If one exists, confirm intent with `AskUserQuestion` (unless they already said "update my skill" or similar):
+
+- Update the existing skill (default for repeat runs)
+- Start fresh (rare, ask why before doing it)
+
+Update mode changes the rest of the flow:
+- Step 1 mines only history since the skill was last edited (`git log -1 --format=%cI <path>`).
+- Step 2 asks what's changed or missing, not what to capture from zero.
+- Step 4 edits the existing file in place. Preserve sections the user hasn't contradicted. Revise ones with new evidence. Add new sections only for genuinely new rules.
+
+### 1. Mine their history
+
+Locate the active workspace's transcripts before fanning out. Claude Code stores them at `${CLAUDE_CONFIG_DIR:-$HOME/.claude}/projects/<encoded-cwd>/*.jsonl`. Run `node <plugin>/skills/reflect/scripts/claude-project-dir.mjs` to print this session's directory rather than building `<encoded-cwd>` by hand. Use only that path. Don't glob across `${CLAUDE_CONFIG_DIR:-$HOME/.claude}/projects/`. That crosses workspace boundaries and reads private chats from unrelated projects.
+
+Survey recent agent conversations within that scope for recurring patterns. Run multiple parallel subagents across slices of history (e.g. last 2-4 weeks, split into 3 slices so each has enough material). Pick each subagent's reasoning level for the job, per the Subagents section of the **poteto-mode** skill. Each slice mining subagent reads transcripts from the workspace-scoped path the parent provides, looks for the signals below, and returns a short structured list of patterns it saw with evidence pointers. Default signals worth hunting:
+
+- Response preferences (length, tone, format, "dumb it down" corrections)
+- Delegation habits (subagents, models, specialized workflows, parallelism)
+- Verification posture (what "done" means, unit tests vs live repro, reviewers)
+- Code and prose discipline (style, principles cited, lint/format tools)
+- Process conventions (worktrees, commits, PRs, review/merge tooling)
+- Meta preferences (fixing skills mid-task, proposing new ones)
+
+Cross-check across slices before elevating a signal. Patterns seen in 2+ slices are high-confidence. Lone signals are weak and usually get dropped.
+
+### 2. Ask the user directly
+
+Mining misses intent that hasn't come up yet. Use the `AskUserQuestion` tool (structured multi-choice) rather than asking the user to type from scratch.
+
+Shape: one or two questions with 4-6 options each, `allow_multiple: true` for category questions. Start broad ("Which areas matter most?"), then follow up on selected areas with specific options. After the structured rounds, one free-form chat question catches anything the options missed.
+
+Don't dump 20 questions.
+
+### 3. Cluster findings
+
+Group the combined signals into sections. Common ones (use only what applies):
+
+- **Response style**: length, tone, format.
+- **Autonomy**: how much to do without asking, MCP tool use.
+- **Understand first**: which skills to reach for when scoping or investigating a change.
+- **Subagents**: default, parallelism, model-to-task, specialized workflows.
+- **Prose / code discipline**: principles, lint tools, style guides.
+- **Review and verify**: repro posture, verification skills, live-testing tools.
+- **Process**: git worktrees, commits, PRs, review/merge tooling.
+- **Skills**: skill-authoring habits, fix-the-skill-first, proposing new skills.
+
+The **poteto-mode** skill shows the shape. Read it for granularity. Don't copy its content. The user's rules are not the same as poteto-mode's.
+
+### 4. Draft the skill
+
+Use the **plugin-dev:skill-development** skill to author the skill. Placement:
+
+- Path: preserve an existing mode skill's category. For a new mode, use `.claude/skills/<handle>/<handle>-mode/SKILL.md` when the repo has an established personal category for that handle. Otherwise default to `.claude/skills/<handle>-mode/SKILL.md` in the project (or `${CLAUDE_CONFIG_DIR:-$HOME/.claude}/skills/<handle>-mode/` if the user prefers a personal skill).
+- Handle: the user's first name or chosen identifier.
+- Frontmatter `description`: trigger on their name + `/<handle>-mode` + "work in their style", not on generic keywords like "write code" or "review PR".
+- Frontmatter formatting: follow `plugin-dev:skill-development`'s YAML rules. Keep `description` as one YAML scalar. Quote it or use `description: >-` with indented continuation lines when punctuation or wrapping requires it.
+- Frontmatter `disable-model-invocation: true` by default. Opt out only if the user explicitly wants their mode to apply on every turn.
+
+### 5. Iterate on prose
+
+Apply the **unslop** skill and `plugin-dev:skill-development`'s writing guidelines to every line.
+
+Show the draft to the user and take feedback. Expect multiple iterations. Cut ruthlessly. A mode skill is not a manual.
+
+### 6. Land it
+
+Work in a worktree off main. Commit and open a PR. Don't push to main directly.
+
+## Guardrails
+
+- **Don't overfit to one conversation.** A preference stated once and contradicted another time is noise. Require multiple instances before codifying it.
+- **Don't be clever.** Restating other skills' contents, inventing metaphors, or writing "poetic" prose for an agent reader is cost without benefit. Keep it operational.
+- **Reference, don't inline.** Other skills the user relies on should appear as path references, not pasted excerpts. Same for any principle docs they maintain elsewhere.
+- **Keep sections minimal.** Only add a section if the user has a specific, non-default rule there. "Communicate clearly" is not a section. "Short paragraphs. Tables when comparing options. Bullets only when items are genuinely parallel." is.
+- **Name conventions generic.** Use "the user" or "the human" in imperatives, not the author's first name.
+- **Don't force symmetry.** If a user has no process rules worth writing down, skip the Process section entirely.
+
+## Evaluation
+
+A `-mode` skill is subjective output. A `plugin-dev:skill-development`-style test/iterate benchmark loop isn't useful here. Vibe-check with the user: does it read like them? Did it miss anything? Then ship.
+
+Run a description-optimization loop only if the skill's trigger accuracy turns out to be a problem in practice.
+
+## When not to use
+
+- User wants a task-specific skill (not working conventions): `plugin-dev:skill-development` alone, no mining required.
+- User wants to capture one narrow workflow (e.g. "how I write commit messages"). That's a regular skill, not a mode skill.
+

package/plugins/pstack/skills/babysit/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: babysit
+description: Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
+---
+
+# Babysit a PR
+
+On Codex, read the [platform mapping](../poteto-mode/references/codex-tools.md), including its per-skill notes, before following this skill.
+
+On GitHub Copilot, read the [platform mapping](../poteto-mode/references/copilot-tools.md), including its per-skill notes, before following this skill.
+
+On Muse, read the [platform mapping](../poteto-mode/references/muse-tools.md), including its per-skill notes, before following this skill.
+
+On Antigravity, read the [platform mapping](../poteto-mode/references/agy-tools.md), including its per-skill notes, before following this skill.
+
+Claude Code analog of Cursor's built-in `/babysit`. The implementation is a loop over `gh` CLI plus the Claude Code `loop` skill for pacing.
+
+Inside poteto-mode, the **Babysit** playbook ([`../poteto-mode/playbooks/babysit.md`](../poteto-mode/playbooks/babysit.md)) supersedes this skill: it owns mode declaration, the merge frontier, stack safety, and the `watch-pr` watcher. This skill stays the standalone `/babysit` entry point for a single PR outside a poteto-mode run.
+
+## When to use
+
+- There's an open PR and the user explicitly wants it kept green, and you are not already inside a poteto-mode run (the playbook owns that case).
+- The user invokes `/babysit` directly.
+- A subagent that opens a PR does NOT babysit — return to the parent and let the parent decide.
+
+## Steps
+
+1. **Fetch PR state.**
+
+   ```bash
+   gh pr view <number> --json number,title,state,mergeable,reviewDecision,statusCheckRollup,mergeStateStatus,comments,reviews
+   ```
+
+2. **Triage in priority order.**
+   - Merge conflicts (`mergeStateStatus == DIRTY`): run the **fix-merge-conflicts** skill. Force-push only if the branch is yours and not shared.
+   - Failing checks (`statusCheckRollup` entries with `conclusion: FAILURE`): run the **fix-ci** skill. Root-cause the failure; fix the underlying code or test; commit; push.
+   - Review comments: run the **get-pr-comments** skill for the summary, then act only on feedback you actually agree with. When a comment has a single mechanical answer — a rename, a guard clause, a formatting nit — make the edit and quote the comment in the commit message. When it hinges on a judgement call, or you can't tell what's being asked, don't guess: leave it and reply with what you would have done.
+   - Review-bot comments (Bugbot and similar automation): classify fix/dismiss/ask before acting, per [`bugbot-triage.md`](../poteto-mode/references/bugbot-triage.md). Ask by default on security, data, and high-severity findings.
+
+3. **Loop.** Use the Claude Code `loop` skill to pace re-checks. Pick the interval from what you're watching:
+   - Active CI run: poll `gh pr checks --watch` (it blocks until checks finish, so no separate loop interval needed).
+   - Awaiting reviewer: 20–30 min heartbeat.
+   - Idle but want to catch new comments: hourly.
+
+4. **When to stop.**
+   - Build is green, every comment resolved, branch merges cleanly → call it ready.
+   - You've run three rounds of fix → push → recheck and it still isn't fully green → stop, summarise what's still broken, and hand control back.
+   - The next fix would force a design choice → pause and put it to the user with `AskUserQuestion`.
+
+5. **Report.** Summarize fixes applied, comments addressed, comments deferred (with reason), current PR status. Cite each commit by SHA.
+
+## Hard rules
+
+- Don't rewrite history on a branch others may have pulled. If a rebase or force-push looks necessary, clear it with the user first.
+- Don't tweak a test's expected values just to get a pass. Only change an assertion when the behaviour genuinely changed and the assertion was pinned to the old behaviour.
+- Never skip hooks (`--no-verify`).
+- Never bypass a failing check by marking it as not required.
+- `gh pr ready` only when all checks are green and no unresolved review comments remain.
+
+## Cross-refs
+
+- Opening a PR does not start a babysit; inside poteto-mode the Babysit playbook owns the request and starts only when asked.
+- Use `interrogate` before opening if the diff is contested; once open, babysit takes over.
+- Use `unslop` on any prose you write here (PR comments, commit messages, status reports).
+
+## Provenance
+
+This is a Claude Code analog of Cursor's `/babysit`, not a port — Cursor's implementation is closed source. The skill is independently authored, with its own prose and structure; the workflow is informed by Cursor's public `/babysit` behavior. The only overlap with other PR tools is the `gh` CLI commands it runs, which are functional invocations rather than copied text.

package/plugins/pstack/skills/benchmark-checklist/SKILL.md

@@ -0,0 +1,38 @@
+---
+name: benchmark-checklist
+description: "Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured."
+---
+
+# Benchmark checklist
+
+Use this when you produce a performance number: a PR's before and after, a regression claim, a hillclimb harness, or a library or config choice. Answer each question with evidence from a run, not a guess about the code.
+
+For a quick ballpark the user asked for, one run is enough. Still check questions 4 and 7, and say that it is one run. Skip the rest unless that run looks wrong. A choice between options is never a ballpark.
+
+## Before you run anything
+
+- Write down the claim you expect to make, in the words you would ship ("export is 30% faster at p50 on the 60k-row dataset"). The questions test that sentence.
+- Read the measurement script. Note what it times, counts, and ignores.
+- Check the load average with `uptime` and the core count with `nproc`. If the machine is busy, find out what is running. If you cannot stop it, interleave the sides so both see the same noise, and say so in the report.
+
+## The questions
+
+1. **Why not double?** Name the limiter. Profile in a run you do not report, because profilers and tracers slow the work down. Use CPU per process (`top`, `pidstat`), a runtime profiler (`node --cpu-prof`, `py-spy`, `perf`), I/O wait, and syscall counts (`strace -c` on Linux), then map the hot spot to source. Watch the load generator too: if it saturates first, you measured the load generator. If a change did not move the number, the limiter explains why, so find it before you call the change useless.
+2. **Was it tuned?** Run every side the way production runs it: release builds, production flags and env, batching and transaction settings, connection pools, caches as warm or cold as production sees them, and the same versions and data. If one side runs on defaults, you compared configurations, not implementations. A limiter that is a setting (a commit per row, a debug build, a missing index) means that side is untuned. Tune it and measure again before you pick a winner. If you cannot tune it, do not pick a winner from that run. When the user is choosing what to adopt, narrowing the claim to the code as it ships today does not fix this, because they adopt the option, not today's settings.
+3. **Did it break limits?** Do the arithmetic. Compare bytes per second with disk and network bandwidth, operations per second times cost per operation with your cores, and the time saved with the time the changed piece took. Removing a piece that takes 10% of the run can make the run at most about 11% faster. A result past a limit measured something other than the work, such as a cache, a no-op, or a bug.
+4. **Did it error?** Count failures and non-success responses, and check that outputs are correct, not just present. Rejections are often fast, and timeouts and retries are slow. If the script does not count errors, add the count.
+5. **Does it reproduce?** Run each side at least 5 times, alternating (A, B, A, B, and so on) so warmup, lazy initialization, caches, and drift favor neither. Report the median and range. A gap smaller than the run-to-run variation is no measurable difference. When the call is close, use a rank-sum test or the harness's own statistics.
+6. **Does it matter?** Next to any micro result, measure the end-to-end path a user waits on, with realistic data sizes and concurrency, and report the micro result as a share of the whole. A helper that takes 1% of a request can make the request at most 1% faster, however fast the helper gets.
+7. **Did it even happen?** Confirm the work ran inside the timed region: the request reached the server, the rows were written, the bytes were read, and the code used the result. Lazy code (generators nobody iterates, promises nobody awaits, results the JIT can discard) and timeouts produce numbers for work that never happened.
+
+## Report
+
+- Lead with the verdict: faster, slower, no measurable difference, or inconclusive.
+- Give the number with its unit, the run count, the range, and the limiter. For example, "p50 41 ms → 33 ms, median of 7 runs per side, range 32 to 35 ms after, bound by JSON parsing on one core."
+- Call the verdict inconclusive when you claim a difference but cannot name the limiter, when a side ran untuned, or when you could not check questions 4 and 7. Name the gap.
+- Keep a PR body to one primary number, per the **Opening a PR** playbook. Put the runs, range, and limiter evidence in a linked artifact or notes file.
+
+## Other perf material
+
+- Vet the **Perf issue** playbook's baseline before the playbook plans from it, and every number after that.
+- Vet the **Hillclimb** playbook's harness before it is frozen. The frozen harness then prints error and work counts, so each keep-or-revert checks questions 4 and 7 for free.