Plugin Claude Code
A curated collection of Claude Code plugins for development workflows, code review, security, and productivity.
Plugin Claude Code
A curated collection of Claude Code plugins for development workflows, code review, security, and productivity.
Instructions file
Instructions for MinhThang1009/dotclaude, covering personal guidelines (global), language, working style, response style and code.
Plugin Claude Code
Systematic logic audit workflow: read every line of source code, find logic bugs, fix, update tests and docs, commit. Language and framework agnostic.
Hook
Runs when the agent finishes a response, executing audit-logic-gate.sh via bash. From MinhThang1009/dotclaude.
Skill Claude CodeCodex
This skill should be used when the user asks to "audit logic bugs", "read all source files and find bugs", "gate tầng 0", "logic check a module", "verify module correctness", "find business logic bugs", "audit this module before drawing diagrams", or says "read every line of code". Works on any module, language, or…
Plugin Claude Code
Audit plan files against codebase — gap detection, dead code verification, test coverage checks. Sub-commands: gaps, verify, tests.
Skill Claude CodeCodex
This skill should be used when the user asks to 'audit a plan', 'check plan coverage', 'verify cleanup grep commands', 'audit plan này', 'kiểm tra plan', 'soát plan trước khi implement', or to audit a plan document for gap/test/cleanup coverage before implementation (distinct from /plan-workflow:audit-dead's…
Plugin Claude Code
Multi-round independent quality audit for Claude Code plugins: deep 7-criteria review with self-updating criteria, finding validation, user-gated fixes, fresh-reviewer convergence loop with hard cap, optional headless benchmark.
Skill Claude CodeCodex
This skill should be used when the user asks to "audit a plugin", "review plugin quality", "audit plugin content", "đánh giá chất lượng plugin", "audit plugin này", "kiểm tra chất lượng plugin", or wants a multi-round independent content audit of a Claude Code plugin (plugin.json, SKILL.md, references, examples…
Plugin Claude Code
Build, debug, and optimize Claude API and Anthropic SDK applications.
Skill Claude CodeCodex
Build, debug, and optimize Claude API / Anthropic SDK apps. Apps built with this skill should include prompt caching. Also handles migrating existing Claude API code between Claude model versions (4.5 → 4.6, 4.6 → 4.7, retired-model replacements). TRIGGER when: code imports anthropic/@anthropic-ai/sdk; user asks for…
Plugin Claude Code
Analyze codebases and recommend tailored Claude Code automations such as hooks, skills, MCP servers, and subagents.
Skill Claude CodeCodex
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what…
Plugin Claude Code
Audit, evaluate quality, and improve CLAUDE.md files. Captures session learnings and keeps project memory up to date.
Skill Claude CodeCodex
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
Skill Claude CodeCodex
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project…
Skill Claude CodeCodex
This skill should be used when the user asks to update CLAUDE.md with learnings from the current session ('revise CLAUDE.md', 'update CLAUDE.md voi nhung gi vua hoc', 'save session learnings to project memory').
Plugin Claude Code
Architecture review and code modernization with adversarial analysis.
Agent
Reviews proposed target architectures and transformed code against modern best practice. Adversarial — looks for over-engineering, missed requirements, and simpler alternatives.
Agent
Mines domain logic, calculations, validations, and policies from legacy code into testable Given/When/Then specifications. Use when you need to separate "what the business requires" from "how the old code happened to implement it.".
Agent
Deep-reads legacy codebases (COBOL, Java, .NET, Node, anything) to build structural and behavioral understanding. Use for discovery, dependency mapping, dead-code detection, and "what does this system actually do" questions.
Agent
Adversarial security reviewer — OWASP Top 10, CWE, dependency CVEs, secrets, injection. Use for security debt scanning and pre-modernization hardening.
Agent
Writes characterization, contract, and equivalence tests that pin down legacy behavior so transformation can be proven correct. Use before any rewrite.
Skill Claude CodeCodex
This skill should be used when the user asks to assess a legacy system for modernization ('modernize assess', 'danh gia he thong legacy') - full discovery and portfolio analysis: inventory, complexity, technical debt, effort estimation.