Quality plugins

Refuses edits that replace code with a '... rest of the code' placeholder and tracks TODO stubs, debug prints and other leftovers above the prompt and in /slop.

Runs the test suite after every turn that changed source and keeps the result above the prompt.

Enforce the style rules Claude keeps ignoring: banned words and phrases, a comment-density cap on added code, and files that must not gain comments. Rules live in .claude/style-cop.md and are both shown to Claude and enforced on edits.

Check what Claude claims against what it ran. When an answer says the tests pass, the build is clean, or something was committed, a line under it says whether a matching command actually ran this turn and succeeded.

Standalone .NET Copilot SDK agent for analyzing and prioritizing dotnet format diagnostics.

Test-driven development workflows, automated test generation, test harness setup, and multi-perspective code review for unit, integration, and end-to-end testing

84 agents

Whole-system QA and security audit for any project, with evidence and hand-off. Point /bymax-qa:audit at a target: a Jira ticket key (verifies access, reads the acceptance criteria, reports each PASS/FAIL/BLOCKED/NOT-VERIFIABLE with evidence), a branch or ref range or PR (scopes the hunt to the change, like a code review), or nothing (the whole system via a signed scope). It maps the stack and its trust boundaries, hunts by domain (authentication, authorization and tenant isolation, injection and input, cache/Redis, database/Postgres, observability, transport and config, architecture, frontend, supply chain, and AI/LLM and agents when the project uses them) with read-only finder agents, probes the running stack against allow-listed hosts only, and admits a finding only after verification: a runnable reproduction, captured evidence and verified impact, with an independent verifier for every hunted candidate. Findings carry ASVS 5.0, CWE and API Top 10 references and a CVSS vector, and move OPEN → HANDED-OFF → FIX-CLAIMED → VALIDATED or REOPENED. The auditor never edits source: findings are handed to the owning peer session over cross-session messaging, filed as GitHub issues when no peer is live, or written back to the ticket as a comment, and re-tested before they close. A PreToolUse hook is a floor under the scope while an audit runs: network probes in command position reach only allow-listed hosts, and Write/Edit tool calls land only in .claude/qa/ (arbitrary Bash writes rest on the skill's discipline). External scanners are used when present, never bundled. Also ships Cloudflare's security-audit skill, vendored unchanged, as /bymax-qa:security-audit. Also ships /bymax-qa:security-playbooks, an on-demand index of 20 defensive playbooks from Anthropic-Cybersecurity-Skills (Apache-2.0), unchanged. Also ships /bymax-qa:personas, persona-based usability QA: it interviews the user (persona count, iPhone Simulator, Android emulator or browser, markets, days), researches

24 skills · 3 agents · hooks

設計原則 (SOLID/KISS/YAGNI/DRY と作業の原則 24 本) / 設計スケッチ (構造の異なる案の競作と統合) / コードレビュー / 複数モデルの敵対的レビュー (interrogate) / 重大バグ検出 / DB 設計 / 疑い駆動開発 / セキュリティ / 依存監査 / テスト監査の設計・レビュー系スキル

10 skills · 7 agents

13 audit skills under one plugin (/audit:audit-all, /audit:audit-security, /audit:audit-deep, …). Run any audit individually, or /audit:audit-all to orchestrate the whole suite into one combined scorecard.

13 skills

Bounded Claude + Codex code review with shared context, verified findings and correction deltas, plus TDD, specialist reviewers and security hooks. The Codex CLI is required for dual-review certification.

1 skill · 4 commands · 7 agents · hooks

Formats Java with a shipped Eclipse JDT engine and, in projects that opt in, blocks a session on violations of an opinionated Java/Spring Boot standard (syntax-tree rules, NullAway, ArchUnit) — all outside the project's build.

12 skills · hooks

The Agentic Weave skills: weave-core plus one skill per concern.

12 skills

Test strategy, TDD enforcement, contract and E2E testing, performance engineering, observability and SRE practice.

5 skills · 6 agents

Read-only engineering audits with scoped evidence and findings.

11 skills

Code review plugins for quality, security, architecture, documentation, and commit message assessment

5 commands · 5 agents

Blocks a session from ending while the files it touched still have SonarQube secrets or quality findings, and reads SonarQube Server or Cloud through the CLI's `sonar api`.

7 skills · hooks

AI-assisted web quality audit skills covering KWCAG 2.2 accessibility (33+7 items), Technical SEO (11 items), and Core Web Vitals (18 items) with integrated HTML/CSV reporting

6 skills · 1 agent

Comprehensive code review system with 5 parallel specialized agents

2 skills · 5 agents

Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification

1 command · 6 agents

Generic dev hygiene: TODO+issue enforcement, frontmatter lint, plan validation (issue+value+retrospective), spec-code drift checker, finish-and-push workflow, and pitfalls-pointer routing, plus a fact-forcing edit gate, git-state checkpoint/snapshot tooling, and council + session-handoff skills, and a compact-plan skill for plan-preserving context compaction.

4 skills · 1 command · 1 agent · hooks

Formats Python with ruff as Claude edits it, then lints with ruff and type-checks with pyright in a session-scoped fix loop; pulls in pyright-lsp for the language server.

6 skills · hooks

Test generation, execution, and failure resolution with complete test-fix loop support

3 commands · 3 agents

LLM-as-a-Judge 評価基盤のセットアップ (BINEVAL 手法準拠: 二値質問の自動生成 / 評価器 / スコアリング / プロンプト最適化ループ)

6 skills

Fast, focused review of uncommitted changes, guided reading tours of PRs and of implementation plans, plus a security-focused subagent.

4 skills · 2 agents

Quality craft: test strategy, coverage-gap analysis, unit-test authoring.

6 skills

Three-layer quality evaluation framework for Claude Code plugins with Elo ranking

1 skill · 3 commands · 2 agents

Three-layer quality evaluation framework for Claude Code plugins with Elo ranking

1 skill · 3 commands · 2 agents

Three-layer quality evaluation framework for Claude Code plugins with Elo ranking

1 skill · 3 commands · 2 agents

Static lint for Claude Code plugins and skills, with experimental LLM scoring for skills

1 skill · 3 commands · 2 agents

Web interface design, visual review, and quality assurance workflows.

6 skills