claude

squabble

A panel of expert reviewers that argues over the design of a tool, model, spec, plan, or decision while it is still cheap to change — and hands back one record of what the panel agreed on, disputed, and withdrew.

1 on GitHubby Cory Kingv0.2.0MITupdated 20 days ago
/

Plugin squabble from marketplace coryking-plugins in coryking/coryking-plugins. Commands read from the repo's manifest — 20 days ago.

What it installs

Skills (1)

  • squabble

    Convene a panel of expert reviewers to argue over the design of a tool, model, spec, plan, or decision before it is built. Use when a design or idea needs scrutiny from several angles at once before committing to it. Not for reviewing finished, working code.

Subagents (9)

  • auditor

    Squabble design-panel role — traces where every number and assumption in a design came from. Convene whenever a design rests on inputs, rates, defaults, or estimates — to find the ones that were guessed, smuggled in as structure, or baked so deep nobody sees them anymore. Dispatched by the squabble

  • calibrator

    Squabble design-panel role — quantifies the uncertainty in a design. Convene whenever a plan rests on estimates — growth rates, timelines, costs, demand, longevity — to check which way each assumption leans, whether they all stack the same way, and where the conclusion breaks. Dispatched by the squa

  • engineer

    Squabble design-panel role — decides whether a design can actually be built as described, and whether its structure can even represent the reality it claims to model. Convene whenever a design proposes a tool, model, or data structure, or when an approach needs a reality check before anyone commits

  • framer

    Squabble design-panel role — guards the question. Makes sure the panel is answering the right problem, not just answering well; owner of the premise challenge. Convene in nearly every squabble; essential whenever a goal was inherited from an earlier conversation or a request jumps straight to a solu

  • historian

    Squabble design-panel role — brings the outside view. Convene to check a plan's inside-view optimism against base rates, the project's own track record, and how similar situations actually turned out — and to keep a fresh analysis from repeating a mistake an earlier one already made. Dispatched by t

  • recorder

    Squabble design-panel recorder — assembles the record of a completed squabble from the reviewers' verbatim contributions. A note-taker, not a judge. Dispatched by the squabble panel workflow after the debate ends.

  • skeptic

    Squabble design-panel role — reads a design for what isn't there. Convene to hunt the negative space — the dimension left out, the case never mentioned, the part that would fail without making a sound, and the places where the design quietly disagrees with itself. Dispatched by the squabble skill.

  • stress-tester

    Squabble design-panel role — breaks a design by running it into reality. Convene to pressure-test a concrete plan or decision — what proves it wrong, what it costs to reverse, what the strongest alternative is, where its most-likely path leads, and how it behaves in the ugly cases. Dispatched by the

  • wildcard

    Squabble design-panel role — the idea engine. Convene when an idea is still fuzzy, when the room has anchored on a single answer or a binary, or whenever a design needs new options and reframings on the table rather than more critique. Generative, not critical. Dispatched by the squabble skill.

View source on GitHub

More from coryking/coryking-plugins

All 4 plugins →

engineering-loop

claudecodex

Slim parallel-review and curated research agents for solo development. The parts of compound-engineering's workflow that actually compound for a single operator, without the team-scale scaffolding.

3 skills · 20 agents

1

project-mining

claudecodex

Mine project histories for behavioral evidence. Search chat logs, git history, docs, and code for concrete examples of specific patterns, values, or skills.

3 skills · 2 agents · 1 MCP server

1

Reference guidance for writing MCP tool descriptions, server instructions, parameter schemas, output schemas, and annotations that LLMs actually use well.

1 skill

1

Similar plugins

Convex

claude

Official Convex plugin for Claude Code with bundled Convex skills, the convex-expert subagent for code-writing, a runtime-error monitor, and MCP access for backend development, schema design, real-time features, auth, file storage, scheduled jobs, and AI agents.

16 skills · 1 command · 2 agents · 1 MCP server · hooks

anthropics/claude-plugins-official 47,076

32 engineering skills: architecture, frontend, backend, fullstack, QA, DevOps, security, AI/ML, data engineering, Playwright (9 sub-skills), self-improving agent, Stripe integration, TDD guide, tech stack evaluator, Google Workspace CLI, a11y audit (WCAG 2.2), Azure cloud architect, GCP cloud architect, security pen testing, Snowflake development, adversarial-reviewer, ai-security, cloud-security, incident-response, red-team, threat-detection. v2.8.1 audits senior-fullstack / senior-frontend / senior-backend against karpathy-coder + Matt Pocock — each ships a 7-question forcing-question library, 4 customization profiles (JSON), deterministic decision engine, composition map into POWERFUL specialists, plus cs-fullstack-engineer / cs-frontend-engineer / cs-backend-engineer orchestrator agents (context: fork) + /cs-fullstack-review, /cs-frontend-review, /cs-backend-review, /cs-engineer-grill slash commands.

35 skills · hooks

alirezarezvani/claude-skills 29,725

Essential development subagents for everyday coding tasks - backend, frontend, fullstack, mobile, and API design

VoltAgent/awesome-claude-code-subagents 26,513

PowerPoint generation and editing plugin with text-only QA (no vision required). Uses subagents for cover, TOC, content, section dividers, summary slides, and template-based PPT editing workflows.

5 skills · 5 agents

MiniMax-AI/skills 13,828

Triages a repository's open GitHub issues and pull requests via the gh CLI: optionally merges ready bot and maintainer-approved PRs and spawns review subagents for unreviewed ones, closes already-resolved issues with referenced explanations, cross-links issues with pending fix PRs, and assigns local-only priority and change-size estimates.

1 skill

trailofbits/skills 8,166

Skills plus explorer and reviewer subagents for building, scaffolding, debugging, understanding, and auditing applications with the Atomic Agents Python framework. Progressive-disclosure references for schemas, agents, tools, context providers, prompts, orchestration, memory, hooks, providers, project structure, and testing — plus a troubleshoot diagnostic, isolated-context subagents for codebase mapping and code review, and a new-app scaffolder.

7 skills · 2 agents

Eigenwise/atomic-agents 6,328

Maintain squabble?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins4 plugins