nstack

Plugin nstack from marketplace nilpath-marketplace in nilpath/nilpath-marketplace. Commands read from the repo's manifest — 20 days ago.

Skills (51)

• architect

  Design before code: ground the problem in the existing system, write the caller''s usage first, produce at least two structurally distinct candidate designs in parallel, screen them for red flags, and synthesize one design package (types, signatures, module map, rationale). Use for ''architect this'

• benchmark-checklist

  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.

• candidate-graft

  Run N independent candidates at the same task in parallel, have a blind cross-judge score them against a private rubric, pick the most extensible base, and graft the strongest parts of the others into it, then verify. Use for 'candidate-graft this', design or code bakeoffs, or when one attempt at a

• control-cli

  Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.

• control-ui

  Build or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs.

• create-verification-skill

  Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.

• deslop

  Remove AI-generated code slop and clean up code style

• figure-it-out

  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 /figure-it-out or ''figure it out''.

• how

  Explain how a subsystem works from the source: architecture, runtime flow, where things live, and gotchas. Use for ''how does X work'', code walkthroughs before changing something, and placement or ownership questions (''where should this live'', ''which package owns this'', ''is this the right laye

• maintain-verification-skill

  Periodic pass that keeps a project''s verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".

• no-comments

  Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.

• nstack-flow

  nstack's agent style for deliberate subagents, principled decisions, unslopped prose, simple code, and verified work. Runs the feature, bug-fix, or investigation playbook to a reviewed draft pull request or a cited answer. Invoke explicitly.

• nstack-help

  Guides users through nstack setup, nstack-flow, and picking the skill, playbook, or principle for a task. Invoke nstack-help explicitly with a question.

• principle-attack-the-premise

  Apply when two or more fixes that share one premise have failed the same gate. Take a census of which actors hold the imbalance before the next fix, then question the premise instead of writing another fix that assumes it.

• principle-boundary-discipline

  Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

• principle-build-the-lever

  Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.

• principle-depend-on-caller-contracts

  Apply when you design a dependency or interface, or call through a collaborator to reach another object.

• principle-encode-lessons-in-structure

  Apply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.

• principle-exhaust-the-design-space

  Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.

• principle-experience-first

  Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.

• principle-explain-the-number

  Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

• principle-extend-at-evidenced-seams

  Apply when you add a required variant or decide whether code needs an extension point. Base the choice on known requirements or a concrete testing need.

• principle-fix-root-causes

  Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.

• principle-foundational-thinking

  Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.

• principle-guard-the-context-window

  Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

• principle-laziness-protocol

  Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.

• principle-make-operations-idempotent

  Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

• principle-migrate-callers-then-delete-legacy-apis

  Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.

• principle-minimize-reader-load

  Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.

• principle-model-the-domain

  Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files.

• principle-never-block-on-the-human

  Apply when tempted to ask 'should I do X?' on reversible work.

• principle-outcome-oriented-execution

  Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.

• principle-own-coherent-responsibilities

  Apply when you create or split a module, decide where state belongs, or consider extracting shared code.

• principle-preserve-substitution-contracts

  Apply when you add or replace an implementation of an existing contract. Preserve the inputs, results, invariants, errors, and effects that callers rely on.

• principle-prove-it-works

  Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.

• principle-redesign-from-first-principles

  Apply when integrating a new requirement into an existing design.

• principle-separate-before-serializing-shared-state

  Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.

• principle-sequence-verifiable-units

  Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.

• principle-subtract-before-you-add

  Apply when sequencing an addition, refactor, or rewrite. Remove dead code, redundant validators, and stub references first, then build on the simpler base.

• principle-test-behavior-not-implementation

  Apply when you write, change, or keep a test. Call the code as its users do and assert the exact result they see. Rewrite or delete a test that would pass if every imported function returned undefined.

• principle-type-system-discipline

  Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.

• python-best-practices

  Python best practices for editing and reviewing .py files, typing, docstrings, and tests.

• review-panel

  Independent adversarial review of a change by several configured reviewers in parallel, followed by a lead judgment that sorts findings into Act on, Consider, Noted, and Dismissed with an agreement map. Use for 'review panel', 'adversarial review', 'multi-model review', 'challenge this', 'stress tes

• setup-nstack

  Reviews and changes which model and reasoning effort nstack uses for each delegated role (how/why explorers and synthesizers, swarm workers, candidate-graft and architect runners, review-panel reviewers, and the implementer, hardest-task, and judgment tiers), then checks that the client actually run

• show-me-your-work

  Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human review

• swarm

  Fan out N parallel workers over a declared shape (coverage slices, a race of identical briefs, or both), wait for all of them, and return one consolidated PASS / ISSUES / BLOCKED report with explicit gaps. Use for 'swarm this', parallel test or audit coverage, races, and partitioned exploration.

• tdd

  Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.

• technical-writing

  Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.

• typescript-best-practices

  TypeScript best practices. Use when reading or editing any .ts or .tsx file.

• unslop

  Cut AI tells from any writing.

• why

  Explain why code is the way it is: design rationale, why a tradeoff was picked, motivating edge cases, regressions, postmortems, and where a threshold or number came from. Searches every available evidence category (source control, issue tracker, documents, team chat, observability, error tracking,

Hooks (2)

• SessionStart

  python3 "$CLAUDE_PLUGIN_ROOT/hooks/nstack_config.py" session-start || true

• PreToolUse

  python3 "$CLAUDE_PLUGIN_ROOT/hooks/nstack_config.py" hook || true

Similar plugins