@krtclcdy/tersio 2.25.5 → 2.25.7

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

@@ -0,0 +1,35 @@
+# 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.*
+
+## 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/extensions/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/extensions/pstack/skills/arena/SKILL.md

@@ -0,0 +1,47 @@
+---
+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 the arena skill, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape."
+---
+
+# Arena
+
+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 from your configured `arena runners` line. If the line is missing, default to one each on the strongest model and a fast model. An `auto` or `inherit-parent` entry in this line or the cross-judge line means the parent model, so omit `model` for it. If the Task tool rejects a configured entry, run that seat on its family's default and say so. Families go by prefix: `claude-*` and `grok-*`. With no family match, use the strongest model. If it rejects a default, use the closest valid slug of the same family from its error message. 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.
+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 your configured `arena cross-judge pool` line. If the line is missing, choose from the strongest model and a fast model. Prefer a different model family from the parent's. Spawn one readonly judge subagent on that model. It 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. 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, each graft with its source candidate, what was rejected and why, any convergence or dropouts, and the verification result.

package/extensions/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.

package/extensions/pstack/skills/blast-radius/SKILL.md

@@ -0,0 +1,49 @@
+---
+name: blast-radius
+description: "Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust."
+---
+
+# Blast radius
+
+Find what a change breaks somewhere else, before it ships. Use for "blast radius of X", "what could this break", or reviewing a small diff you don't trust yet.
+
+Companion to `how` and `why`. `how` tells you what the code does. `why` tells you why it's shaped that way. Blast radius tells you what it breaks somewhere else.
+
+Listing the callers is not the job. The agent can grep those in a second. The job is the breakage grep won't show you.
+
+## Don't trust your own writeup
+
+A blast-radius writeup that sounds right is worthless. It reads as convincing whether or not it's true. So don't hand back the writeup. Find the one or two facts the whole thing depends on and prove them by running code.
+
+### How sure are you
+
+For each fact the change's safety depends on, get it as far down this list as is cheap, and say where it stopped.
+
+1. You said so. Worthless on its own.
+2. You pointed at the line. A real `file:line`, or the library's own source.
+3. You showed the bad case can't happen. You walked the failure step by step and it doesn't reach.
+4. You ran it. A script or test that calls the real code and fails loud if you're wrong.
+5. You reproduced it in the running app.
+
+Step 4 is usually one small script that imports the same library the app ships and calls the exact function you're worried about.
+
+## Steps
+
+1. Read the change. The diff, the symbols it adds, changes, and deletes, and what it now does differently, including the part the diff doesn't spell out. Use `why` step 2 to pull the PR and commits.
+2. Find the one fact it's safe because of. Most changes that look risky are safe because of a single fact, like "this call only drops already-dead cache entries and does nothing else". Find that fact. If it holds, most risky cases are cleared at once. Spend your time here, not on a long list of maybes.
+3. Look where grep stops. Read the source of the library you call, and check its pinned version and any local patch. Work out when things run: microtasks, unmount and teardown, Solid versus React. Follow what a symbol search misses: the JSON an API returns, a DB column, a wire format, another language reading the same bytes, a feature flag, code three hops downstream.
+4. Be honest about each risk. Give it a real chance of happening and a real cost if it does. Keep the risks you confirmed. List the ones you checked and cleared separately. Same rules as `why`. Cite a real `file:line`, a search that finds nothing is still an answer, and never make up a caller or an API.
+5. Prove the one fact. Write a script or test that runs the real code, run it, and paste what happened.
+6. For a big or wide change, run it as an `arena`. Ask more than one model the same question and merge the answers. Different models catch different real bugs.
+
+## What to hand back
+
+- **What it does.** What changed, including the part that isn't obvious.
+- **The one fact it's safe because of.** State it, say which step you got it to, and show the proof. If you couldn't prove it, write unproven.
+- **Risks.** Each names how it breaks, the `file:line`, how likely and how bad, and how to check. Paste the proof for the ones that matter.
+- **Cleared.** What you checked and why it's fine.
+- **Before you merge.** The cheapest test or repro that catches the real bug, including the script you wrote.
+
+Write it through `unslop`, cite real code, and strip anything private before it goes anywhere public.
+
+**Reply:** the writeup above, with the one safety fact either proven or marked unproven.

package/extensions/pstack/skills/bro/SKILL.md

@@ -0,0 +1,6 @@
+---
+name: bro
+description: Restate the last message in plain human language, with no jargon.
+---
+
+Restate your last message. Stop using jargon and speak coherently. State it more simply and concisely, like one human talking to another.

package/extensions/pstack/skills/correct/SKILL.md

@@ -0,0 +1,31 @@
+---
+name: correct
+description: "Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for the correct skill."
+---
+
+# Correct
+
+The operator keeps correcting agents in this repo for the same mistakes. Change the repo so the next agent can't make them.
+
+Assume every contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Design the repo so a change that looks right from one file is right for the whole repo.
+
+## Find the mistake classes
+
+First, read recent commits, reverts, review comments, agent instruction files, and comments that explain workarounds. Group the mistakes into classes. A class counts once it has happened twice.
+
+## Fix each class at the highest level that works
+
+1. **Eliminate it with architecture.** Give each piece of state one owner and each task one supported way. Hide internals so the wrong import fails. Replace hand-synced lists with one source of truth. Delete old ways and dead code an agent would copy.
+2. **Enforce it with types so the bad state can't be written.** If bad code still compiles, add a lint or CI check whose error names the file, type, or function to use instead. If the pattern is already common, fail only when a change adds more.
+3. **Test the behavior.** Fix or delete any test that would still pass if every function it calls returned nothing.
+4. **Write docs or agent rules last, only for judgment calls.** Nothing fails when an agent skips them.
+
+## Fix and prove
+
+Then fix the most frequent classes now, one commit each. Prove each new check fails on a real past mistake. Run the same command locally and in CI. Exceptions go on the offending line with a reason, an expiry date, and a human's approval.
+
+## Keep the rule table
+
+Last, keep a table in the agent instruction file that pairs each rule with what enforces it. When the operator corrects you, fix the mistake and add the rule. If the rule was already there and nothing enforces it, that's a repeat, so fix it at the highest level in the same change. Drop a rule once its mistake can't happen.
+
+**Reply:** each class with its evidence, the level you picked, and why a higher level didn't work.

package/extensions/pstack/skills/figure-it-out/SKILL.md

@@ -0,0 +1,51 @@
+---
+name: figure-it-out
+description: "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. Scales rigor to the task, runs a hypothesis loop, and logs decisions. Use for the figure-it-out skill or 'figure it out'."
+---
+
+# Figure it out
+
+When the task matches no playbook, design one. The deliverable before any code is the workflow itself: a sequence of phases that scales rigor to the task, runs the scientific method, and leaves a decision trail a human can audit after stepping away.
+
+## Start
+
+Open a todolist whose first item is to read the Principles section of the **poteto-mode** skill. Then add the phases below as todos.
+
+## Phase A: Frame
+
+Ground first, then commit. Don't start the run until you can state:
+
+- The definition of done as a falsifiable predicate (the **prove-it-works** principle skill).
+- Scope, quantified: rough units and effort, plus the blockers grounding surfaced.
+- The rigor level, biased high. One-way doors and high blast radius get more. Reversible low-stakes steps get less. Rigor is gates and artifacts, not "try harder".
+
+Present the framing and tradeoffs before committing to a long run. Reversible work proceeds (the **never-block-on-the-human** principle skill), but a multi-hour run earns one checkpoint.
+
+## Phase B: Design the workflow
+
+Decompose into atomic, independently-landable units. Sequence riskiest-unknown-first. Scaffold and verification come before features (the **foundational-thinking** principle skill).
+
+- Build the verification harness before the work, with the baseline captured from the pre-change state, so the check reads as "old value vs new value".
+- For one-way-door design decisions, run the **architect** skill (it runs **arena**). Skip it for mechanical work whose shape is already concrete. A second arena over a settled design is over-engineering (the **laziness-protocol** principle skill).
+- Decide what fans out. Parallelize only across seams, and give each worker its own worktree or branch (the **separate-before-serializing-shared-state** principle skill). Don't over-fan.
+- Write the designed phase list down. That list is what the human reviews.
+
+Then execute the design. Add its steps to the todolist as concrete items between the Phase C and Phase D entries. Run each under the Phase C loop discipline, and weave the Phase D log through them, a row as each step lands, rather than saving the whole trail for the end.
+
+## Phase C: Run the loop
+
+Each unit is an experiment. State the hypothesis, make the smallest change, measure against the predicate on the real artifact, keep it if it advanced, revert it if it didn't. Apply the **sequence-verifiable-units** principle skill, verifying each unit before starting the next instead of batching checks at the end.
+
+- Verify by inspecting the artifact, never a self-report. When something passes too easily, suspect the observation method before the system.
+- Pair delegated work with a judge. If a worker games the gate, reset and harden the contract. If the gate itself is wrong, fix the gate in its own change rather than routing around it.
+- A verdict is VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Inconclusive is not a pass. Don't hide a negative.
+
+## Phase D: Keep the audit trail
+
+Log the run via the **show-me-your-work** skill. figure-it-out's work is usually ambitious enough to commit the trail so the reviewer can read it in the PR. The trail plus the diff is what lets the human come back and trust the work.
+
+## Phase E: Verify and hand back
+
+Check the whole against the Phase A predicate on the real product, not just the harness. Encode any recurring correction as a gate, a lint rule, a check, or a script (the **encode-lessons-in-structure** principle skill).
+
+**Reply:** the playbook you designed, the rigor level and why, the decision-trail path, what's verified against the predicate, and what's still open.

package/extensions/pstack/skills/how/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: how
+description: "Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation."
+---
+
+# How
+
+Explore the codebase to answer "how does X work?" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code.
+
+Every spawn is a Task subagent with `readonly: true`. Explorers use your configured `how explorer` line (default a fast model), and every explainer uses the `how explainer` line (default the strongest model). Set `model` to that line's value, or to the default if the line is missing. Leave `model` unset when the value is `auto` or `inherit-parent`. If the Task tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message.
+
+## 1. Assess complexity
+
+If the scope is ambiguous, state your interpretation and explore. The user can redirect.
+
+- **Simple** (a single module, a small utility, a narrow question such as "how does function X work"): no explorers. Spawn one explainer that explores and explains in one pass, built from `references/explainer-prompt.md` without the explorer-findings section. Go to step 4.
+- **Complex** (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): go to step 2.
+
+When in doubt, take the simple path.
+
+## 2. Explore (complex only)
+
+Decompose the question into 2 to 4 angles, each a distinct slice of the subsystem. Spawn all explorers in a single message, each with `references/explorer-prompt.md` and its angle filled in.
+
+## 3. Synthesize (complex only)
+
+Once all explorers have returned, spawn one explainer with `references/explainer-prompt.md` and every explorer's findings filled in.
+
+## 4. Present
+
+Present the explainer's output. Light edits for clarity or context from the conversation are fine. Do not substantially rewrite it.
+
+## Output format
+
+The explanation uses the sections defined in `references/explainer-prompt.md`, dropping any that do not apply: Overview, Key Concepts, How It Works, Where Things Live, Gotchas.

package/extensions/pstack/skills/how/references/explainer-prompt.md

@@ -0,0 +1,55 @@
+# Explainer Prompt Template
+
+Build the explainer subagent's prompt from this template. Fill in the placeholders.
+
+---
+
+You are writing an architectural explanation for a senior engineer. Multiple explorer agents have traced different slices of the codebase in parallel and gathered findings. Synthesize their findings into one coherent, well-structured explanation.
+
+## Original Question
+
+> {QUESTION}
+
+## Explorer Findings
+
+{EXPLORER_FINDINGS_ALL}
+
+## Instructions
+
+The explorers each investigated a different angle of the same subsystem. Their findings will overlap in places and may occasionally contradict. Reconcile them. Merge overlapping descriptions, resolve contradictions by checking the code yourself, and combine the separate slices into a unified picture.
+
+Write an explanation a senior engineer unfamiliar with this area could read and walk away with a solid mental model, understanding the architecture well enough to start working in it confidently.
+
+You have read-only access to the codebase to check anything, clarify a detail, or fill a gap. Use Read, Grep, and Glob as needed. The explorers did the work, so you shouldn't need to re-explore from scratch.
+
+## Output Format
+
+Use this structure, adapted to what makes sense for the question. Not every section is needed for every question.
+
+### Overview
+1-2 paragraphs. What is this thing, what does it do, why does it exist. Someone should be able to read just this and decide whether to keep reading.
+
+### Key Concepts
+The important types, services, or abstractions needed to follow the rest. Brief definitions, not exhaustive.
+
+### How It Works
+The core of the explanation, and the longest section. Walk through the flow: what triggers it, what happens step by step, where data goes, what the decision points are.
+
+Use prose, not pseudocode. Reference specific files and functions so the reader knows where to look, but don't dump large code blocks unless a snippet is essential to a point.
+
+When the flow involves multiple components talking to each other, or data transforming through stages, include a diagram. Use mermaid (```mermaid) for structured flows (sequence diagrams, flowcharts, component graphs) or ASCII art for simpler relationships where mermaid would be overkill. Use your judgment. A diagram should clarify, not decorate. If prose covers the flow, skip the diagram.
+
+### Where Things Live
+A brief file/directory map. Just the ones someone would need to start working here.
+
+### Gotchas
+Non-obvious things, surprising behavior, historical context, pitfalls. Skip this section if there's nothing worth calling out.
+
+## Communication Style
+
+- Use concrete language, not abstractions-about-abstractions
+- Say "the `UserService` calls `AuthClient.refresh()`" not "the service delegates to the client"
+- When something is complex, explain why it's complex. Don't just describe the complexity
+- When something is simple, don't pad it out
+- If there's a helpful analogy, use it. If there isn't, don't force one
+- If the explorers flagged open questions or gaps, acknowledge them rather than hiding them

package/extensions/pstack/skills/how/references/explorer-prompt.md

@@ -0,0 +1,35 @@
+# Explorer Prompt Template
+
+Build each explorer subagent's prompt from this template. Fill in the placeholders.
+
+---
+
+Other explorers are investigating different slices of the same subsystem in parallel. Don't try to cover everything. Focus on your assigned angle and go deep.
+
+## Question
+
+> {QUESTION}
+
+## Your Exploration Angle
+
+{EXPLORATION_ANGLE}
+
+## Output
+
+### Components Found
+The key types, services, classes, and abstractions. For each: name, file path, and a one-sentence description of what it does.
+
+### Flow
+The execution flow step by step. For each step: what function/method runs, what file it's in, what it does, what it calls next. Include the data that flows between steps.
+
+### Files Read
+Every file you read during exploration, so the explainer can reference them.
+
+### Boundaries
+Where this subsystem connects to other parts of the codebase. The inputs and outputs.
+
+### Non-Obvious Things
+Anything surprising, historically motivated, or easy to get wrong. Things that look like they should work one way but work another.
+
+### Open Questions
+Anything you couldn't fully trace or understand. Be honest about gaps.

package/extensions/pstack/skills/interrogate/SKILL.md

@@ -0,0 +1,73 @@
+---
+name: interrogate
+description: "Use for \"interrogate\", \"adversarial review\", \"multi-model review\", \"challenge this\", \"stress test this code\", \"find blind spots\", or \"tear this apart\". Multiple LLM reviewers challenge changes from independent angles."
+---
+
+# Interrogate
+
+Spawn one reviewer per configured model to adversarially review code changes. The adversarial signal comes from model diversity, not assigned personas. The deliverable is a synthesized verdict. Do NOT auto-apply changes.
+
+## Step 1, Scope
+
+Identify what to review from context:
+
+- If the user points at specific files or a diff, use that.
+- If on a feature branch, run `git diff main...HEAD` (or the appropriate base branch) for the full changeset.
+- If the user's message references recent work, gather the relevant files.
+
+Package the diff or file contents with any surrounding context files the reviewers need to understand the code.
+
+## Step 2, Intent
+
+Before spawning reviewers, state the intent in one clear paragraph from the user's message, commit messages, the PR description if one exists, and the code. If you're unsure about the intent, ask the user before proceeding.
+
+## Step 3, Spawn Reviewers
+
+Launch all reviewers in a single message with the Task tool, one per entry on your configured `interrogate reviewers` line, labeled Reviewer A, B, and so on to match the entry count. If the line is missing, use the table defaults.
+
+| Subagent | Default model |
+|----------|---------------|
+| Reviewer A | the strongest model |
+| Reviewer B | a fast model |
+
+Each reviewer gets `readonly: true` and `model` set to its configured entry, or its table default when there is no configured line. Omit `model` for an `auto` or `inherit-parent` entry, so that reviewer runs on the parent model.
+
+If the Task tool rejects a configured entry, run that reviewer on its family's table default and say so. Families go by prefix: `claude-*` and `grok-*`. With no family match, use Reviewer A's default. If it rejects a table default, spawn with the closest equivalent from the valid slugs in its error message (prefer the same family and reasoning tier), and open a separate PR to update the default table. Do not block the review on the slug issue. Never treat an alias entry as a rejected slug or apply either fallback to it.
+
+Read `references/reviewer-prompt.md` and fill in the same template for every reviewer with the stated intent, the diff or file contents, the rubric from `references/rubric.md`, and the code-quality lens from `references/code-quality-review.md`.
+
+## Step 4, Synthesize
+
+As results come back, build a unified picture. Parse every reviewer's findings. Merge findings that describe the same issue differently, and note which models raised each one. Findings two or more models raised independently are the highest signal. Read a lone model's finding, but weight it accordingly. Note disagreements. If one model flags something and another explicitly says the opposite, that is context for the verdict.
+
+## Step 5, Lead Judgment
+
+You are the lead reviewer, a pragmatic senior engineer, not a neutral aggregator. Read `references/lead-judgment.md` for the full framework. Put every finding in one of four buckets, with the model(s) that raised it and a one-line rationale.
+
+- **Act on**. Real issues affecting correctness, security, or maintainability given the actual goals. They would block a real PR.
+- **Consider**. Legitimate, but you're not sure they outweigh the cost of addressing them now. Worth the user's attention.
+- **Noted**. Technically valid but not actionable. Context-dependent, premature optimization, or low-impact at this stage.
+- **Dismissed**. Wrong, nitpicky, or missing context, with a brief reason.
+
+## Output Format
+
+### Intent
+> [The stated intent paragraph from Step 2]
+
+### Reviewers
+- Reviewer [label]: [model name], [N findings] (one bullet per reviewer)
+
+### Act On
+[Each: description, which models raised it, why it matters.]
+
+### Consider
+[Each: description, which models raised it, the tradeoff.]
+
+### Noted
+[Brief list.]
+
+### Dismissed
+[Each with a brief rationale.]
+
+### Agreement Map
+[Where models agreed and diverged, and what that pattern tells us.]

package/extensions/pstack/skills/interrogate/references/code-quality-review.md

@@ -0,0 +1,47 @@
+# Code Quality Review
+
+Each reviewer applies this code-quality lens in addition to the rubric. It is a strict standard focused on implementation quality, maintainability, abstraction quality, and codebase health.
+
+Above all, be ambitious about code structure. Do not merely identify local cleanup. Actively search for "code judo" moves, restructurings that preserve behavior while making the implementation dramatically simpler, smaller, more direct, and more elegant.
+
+## Core Prompt
+
+Start from this baseline:
+
+> Perform a deep code quality audit of the current branch's changes.
+> Rethink how to structure / implement the changes to meaningfully improve code quality without impacting behavior.
+> Work to improve abstractions, modularity, reduce Spaghetti code, improve succinctness and legibility.
+> Be ambitious, if there is a clear path to improving the implementation that involves restructuring some of the codebase, go for it.
+> Be extremely thorough and rigorous. Measure twice, cut once.
+
+## Dimensions
+
+Each dimension is stated once. Apply the ones that are relevant.
+
+0. **Be ambitious about structural simplification.** Do not stop at "this could be a bit cleaner." Look for reframings that make whole branches, helpers, modes, conditionals, or layers disappear. Assume a "code judo" move is often available. It uses the existing architecture more effectively and makes the change dramatically simpler. If you can delete complexity rather than rearrange it, push hard for that.
+
+1. **Do not let a PR push a file from under 1k lines to over 1k lines without a very strong reason.** Treat this as a strong smell. Prefer extracting helpers, subcomponents, or modules. If the diff crosses that threshold, ask whether the code should be decomposed first. Waive only for a compelling structural reason where the resulting file stays clearly organized.
+
+2. **Do not allow spaghetti growth in existing code.** Be suspicious of new ad-hoc conditionals, scattered special cases, or one-off branches inserted into unrelated flows. Treat "weird if statements in random places" as a design problem, not a style nit. Prefer pushing the logic into a dedicated helper, state machine, or module instead of tangling an existing path.
+
+3. **Bias toward cleaning the design, not just accepting working code.** If behavior can stay the same while the structure becomes meaningfully cleaner, push for the cleaner version. Prefer simplifications that remove moving pieces over refactors that spread the same complexity around.
+
+4. **Prefer direct, boring, maintainable code over hacky or magical code.** Treat brittle, ad-hoc, or "magic" behavior as a problem. Be skeptical of generic mechanisms that hide simple data-shape assumptions. Flag thin abstractions, identity wrappers, or pass-through helpers that add indirection without buying clarity.
+
+5. **Push on type and boundary cleanliness when it affects maintainability.** Question unnecessary optionality, `unknown`, `any`, or cast-heavy code when a clearer type boundary could exist. Prefer explicit typed models over loosely-shaped ad-hoc objects. If a branch leans on a silent fallback to paper over an unclear invariant, ask whether the boundary should be made explicit.
+
+6. **Keep logic in the canonical layer and reuse existing helpers.** Call out feature logic leaking into shared paths or implementation details leaking through APIs. Prefer existing canonical utilities over bespoke one-offs. Push code toward the right package, service, or module instead of normalizing drift.
+
+7. **Treat unnecessary sequential orchestration and non-atomic updates as design smells when the cleaner structure is obvious.** If independent work is serialized for no reason, ask whether it should run in parallel. If related updates can leave state half-applied, push for a more atomic structure. Do not over-index on micro-optimizations, but do flag avoidable orchestration complexity that makes the code more brittle.
+
+## Output Expectations
+
+Prioritize structural code-quality regressions and missed simplifications first, then spaghetti and branching complexity, then boundary, type, and file-size concerns, then smaller modularity and legibility issues.
+
+## Approval Bar
+
+Do not approve merely because behavior seems correct. Treat these as presumptive blockers unless the author can justify them: the PR keeps a lot of incidental complexity when a code-judo move would delete it. Pushes a file from below 1000 lines to above 1000 lines. Adds ad-hoc branching that tangles an existing flow. Scatters feature checks across shared code. Adds an unnecessary abstraction, wrapper, or cast-heavy contract, or duplicates an existing helper or puts logic in the wrong layer when there is a clear canonical home. If those conditions are not met, leave explicit, actionable feedback and push for a cleaner decomposition.
+
+## Review Tone
+
+Be direct, serious, and demanding about quality. Do not be rude, but do not soften major maintainability issues into mild suggestions. If the code is making the codebase messier, say so. If the implementation missed an obvious dramatic simplification, say that too. Do not be satisfied with "maybe rename this" when the real issue is structural.

package/extensions/pstack/skills/interrogate/references/lead-judgment.md

@@ -0,0 +1,58 @@
+# Lead Judgment Framework
+
+You are the lead reviewer. The configured reviewers have produced their findings. Apply pragmatic engineering judgment. Don't aggregate. Filter, contextualize, and decide.
+
+## Why This Step Matters
+
+Adversarial reviewers are useful because they're aggressive. But aggression without context produces noise. The reviewers only saw a slice of the codebase and a one-paragraph intent statement. They don't know:
+
+- What was already tried and rejected
+- What constraints exist outside the code (timeline, dependencies, migration plans)
+- Which parts of the code are temporary scaffolding vs. permanent architecture
+- What the next PR in the stack will address
+
+You have the full conversation context. Use it.
+
+## Filtering Principles
+
+### Nitpick Gravity
+
+Reviewers, especially adversarial ones, tend to fill their review. If they don't find critical issues, they'll inflate nits to fill the space. If a reviewer's findings are all nits and style preferences, the code is probably fine. Say so.
+
+### Hypothetical vs. Actual
+
+"What if someone passes null here?" is only a finding if the caller can actually pass null. Trace the call site. If the input is validated upstream or the type system prevents it, dismiss the finding. Reviewers working from a diff can't always see the full call chain. You can.
+
+### Premature Abstraction Warnings
+
+Reviewers often suggest extracting functions, adding interfaces, or creating abstractions. Does this code need to change in a second way? If not, the abstraction is premature. Simple inline code that works beats a clean abstraction that's overkill for the current scope.
+
+### "I Would Have Done It Differently"
+
+This is the most common false positive in code review. A finding that amounts to "I prefer a different approach" is not a bug, not a design flaw, and not actionable unless the reviewer shows a concrete problem with the current approach. Dismiss these, and say why.
+
+### Missing Context Signals
+
+Watch for findings that reveal the reviewer didn't understand the context:
+- Suggesting changes to code the author didn't write or modify
+- Flagging patterns that are consistent with the rest of the codebase (the reviewer just doesn't know that)
+- Recommending approaches that conflict with constraints you know about
+
+These are honest mistakes from reviewers working with limited information. Dismiss them gracefully.
+
+## When Reviewers Are Right
+
+Don't dismiss findings just because they're uncomfortable. The whole point of adversarial review is to catch things you'd miss. Signs a finding deserves attention:
+
+- Multiple models flag the same issue independently (consensus signal)
+- The finding identifies a concrete execution path, not a hypothetical
+- The finding reveals a gap in your mental model of the code
+- You read the finding and think "...yeah, actually"
+
+Be especially careful about dismissing security findings and correctness bugs. These deserve more scrutiny even when they come from a single model.
+
+## Verdict Calibration
+
+A good verdict is useful, not comprehensive. The user should be able to read the "Act On" section, fix those issues, and ship with confidence. If your "Act On" list has more than 5 items, you're probably not filtering hard enough.
+
+The "Dismissed" section is not busywork. It's a trust mechanism. Showing the user what you rejected and why lets them override your judgment where they disagree. This is more valuable than hiding the rejected findings.