Skip to main content
NeVibeCode · repository · 35 items

my-claude-code-setup: a set by centminmod

The centminmod/my-claude-code-setup repository on GitHub: 35 cards with a description and an install command. Inside: 13 commands, 9 prompts and 7 skills and more. They install into Claude Code, Codex and GitHub Copilot.

About the repository

GitHub
centminmod/my-claude-code-setup
Stars
★ 2,744
License
MIT
Source updated
2026-10-08
In the catalog since
2026-10-30
get-current-datetime subagent get-current-datetime — a subagent that runs the date command with a specified timezone and returns only the raw output. Use it when you need the current date and time in a prompt without extra commentary. CX Codex ★ 2,744repo stars 10_instruction_stress prompt 10_instruction_stress is a Claude Code prompt that tests whether a model follows four simultaneous constraints while describing an imaginary coffee shop. GP ChatGPT ★ 2,744repo stars 05_tool_heavy_task prompt The 05_tool_heavy_task prompt has Claude Code read three files one at a time, then sum up Meridian’s testing strategy in a single paragraph. It also tests whether the agent makes separate tool calls. GP ChatGPT ★ 2,744repo stars codex-cli subagent Calls OpenAI Codex CLI from inside Claude Code. Handy when you want a GPT-5.2 take on code without switching tools. CX Codex ★ 2,744repo stars zai-cli subagent Routes code analysis requests to the GLM 4.7 model via the z.ai CLI directly from your Claude Code workflow. CX Codex ★ 2,744repo stars 09_typescript_refactor prompt 09_typescript_refactor is a Claude Code prompt that makes TypeScript functions easier to read. It asks for a code block and a short explanation. GP ChatGPT ★ 2,744repo stars 02_english_prose prompt 02_english_prose rewrites an English paragraph to remove every comma. You can restructure sentences and use other punctuation while preserving the meaning. GP ChatGPT ★ 2,744repo stars 08_csv_transform prompt 08_csv_transform aggregates tabular order entries into customer spending totals and returns raw CSV without conversational filler. GP ChatGPT ★ 2,744repo stars 04_stack_trace_debug prompt The 04_stack_trace_debug prompt asks Claude Code to find the cause of a Python stack trace, identify the failing call, and suggest a fix. Use it when you need a compact diagnosis. GP ChatGPT ★ 2,744repo stars 07_json_reshape prompt 07_json_reshape — a prompt that rebuilds a JSON sample against a fixed rubric and returns nothing but parseable JSON. GP ChatGPT ★ 2,744repo stars 03_code_review prompt 03_code_review — a prompt for reviewing Python diffs. It forces Claude to return exactly three concrete issues as a bulleted list without conversational filler. GP ChatGPT ★ 2,744repo stars ccusage-daily command This command runs ccusage daily -b and turns Claude Code usage figures into a Markdown report. Use it to review costs, token totals, and daily spending. CX Codex +1 ★ 2,744repo stars create-readme-section command The create-readme-section command for Claude Code generates README sections based on project files. Create installation instructions, API references, or contribution guides. CX Codex +1 ★ 2,744repo stars 01_claudemd_summarise prompt 01_claudemd_summarise — a Claude Code prompt that compresses CLAUDE.md documentation into exactly 120 words in a single paragraph, without headings or lists. Use it to standardize project architecture summaries for AI coding context. GP ChatGPT ★ 2,744repo stars security-audit command The security-audit command scans a codebase for vulnerabilities and unsafe patterns across a project or a specific module. CX Codex +1 ★ 2,744repo stars check-best-practices command The check-best-practices command reviews code against language-specific standards, conventions, and best practices. It spots issues from critical bugs to style violations and suggests concrete improvements. CX Codex +1 ★ 2,744repo stars claude-docs-consultant skill claude-docs-consultant pulls official Claude Code documentation directly from code.claude.com on demand. Fetches only the markdown files needed for the active task. CX Codex +1 ★ 2,744repo stars explain-architecture-pattern command The explain-architecture-pattern command identifies architecture and design patterns in a codebase, then explains the structure behind them. Use it when the project’s organization needs a clear rationale. CX Codex +1 ★ 2,744repo stars convert-to-test-driven-prompt command convert-to-test-driven-prompt turns a plain request into a TDD-style prompt with test cases, expected outcomes, and success criteria. Useful when behavior needs to be pinned down before code exists. CX Codex +1 ★ 2,744repo stars batch-operations-prompt command batch-operations-prompt transforms bulk code modification requests into structured plans with parallel stages and sequential tasks. It optimizes Claude Code execution through TodoWrite checklists. CX Codex +1 ★ 2,744repo stars memory-bank-synchronizer subagent memory-bank-synchronizer is a Claude Code subagent that checks memory-bank files against the codebase and refreshes documentation when CLAUDE-*.md diverges from the implementation. CX Codex ★ 2,744repo stars ux-design-expert subagent ux-design-expert audits user flows, builds Tailwind design systems and themes Highcharts charts. Useful when the interface is done but people still get lost. CX Codex ★ 2,744repo stars code-searcher subagent code-searcher navigates codebases, tracks vulnerabilities, and returns exact file and line references. CX Codex ★ 2,744repo stars cleanup-context command cleanup-context — a Claude Code command that audits project documentation files (CLAUDE-*.md, CLAUDE.md, README.md) to identify redundant content, obsolete materials, and overlapping coverage. CX Codex +1 ★ 2,744repo stars audit-session-metrics skill Reads a session-metrics JSON export and reports on token-usage waste. Invoke it with /audit-session-metrics quick or detailed against a finished export file. CX Codex +1 ★ 2,744repo stars task-breakdown skill task-breakdown groups turns from a Claude Code session into semantic tasks and generates an audit report with waste verdicts. CX Codex +1 ★ 2,744repo stars apply-thinking-to command The apply-thinking-to command reshapes a prompt file with Anthropic-style extended-thinking patterns. Use it when an analysis needs clearer stages, checks, and trade-off review. CX Codex +1 ★ 2,744repo stars create-release-note command create-release-note generates two versions of release documentation from recent commits: one for customers, one for engineers. Analyzes changes, groups them by theme, and traces each change back to specific commit hashes. CX Codex +1 ★ 2,744repo stars consult-zai skill consult-zai pairs z.ai GLM 5.2 with Claude code-searcher for two-model code reviews. Delivers a second opinion on bugs and architecture questions. CX Codex +1 ★ 2,744repo stars consult-codex skill The consult-codex skill sends code questions to OpenAI Codex and Claude code-searcher, then combines their cited findings. Use it for difficult debugging, design questions, or code review. CX Codex +1 ★ 2,744repo stars convert-to-todowrite-tasklist-prompt command convert-to-todowrite-tasklist-prompt transforms verbose slash commands with heavy context into TodoWrite tasks that run in parallel via subagents. Speed gain: 60–70%. CX Codex +1 ★ 2,744repo stars refactor-code command refactor-code audits code and generates a step-by-step refactoring blueprint without modifying repository files. Useful before breaking up legacy monolithic modules. CX Codex +1 ★ 2,744repo stars secure-prompts command secure-prompts scans files or supplied text for prompt injection, concealed instructions, and suspicious content. Use it before exposing untrusted material to an agent. CX Codex +1 ★ 2,744repo stars session-metrics skill session-metrics adds up token usage and estimated cost for a Claude session from its JSONL log, turn by turn, with a running total. CX Codex +1 ★ 2,744repo stars ai-image-creator skill ai-image-creator generates PNG graphics, edits images from references, and inspects media via OpenRouter or Cloudflare AI Gateway in Claude Code. CX Codex +1 ★ 2,744repo stars

More in NeVibeCode

Project sponsors

Companies that keep this analytics open