AndrewDongminYoo

AndrewDongminYoo/rn-agents-kit

Plugin Claude Code

Audit-first agent skills for React Native maintenance.

AndrewDongminYoo/rn-agents-kit

Plugin Claude Code

Audit-first agent skills for React Native maintenance: code-quality audit, New Architecture readiness, asset hygiene, project snapshot, device screen capture, and Metro console capture.

AndrewDongminYoo/rn-agents-kit

Skill Claude CodeCodex

Use when a React Native project has messy assets — unreferenced/unused image, SVG, or Lottie files, scattered or deeply-relative require() paths, or string-based asset references you want made type-safe. Audits first (read-only), then offers git-safe cleanup. Wraps the rn-typed-assets CLI.

AndrewDongminYoo/rn-agents-kit

Skill Claude CodeCodex

Use when you want a thorough, low-false-positive code-quality audit of a React Native / Expo codebase or a diff — render performance, hooks correctness, list virtualization, native boundaries, effect leaks. Fans out many agents and adversarially verifies each finding to kill false positives, so it is for breadth, not…

AndrewDongminYoo/rn-agents-kit

Skill Claude CodeCodex

Use when an agent needs to see the running React Native app — verify a screen rendered as intended, capture the iOS simulator or Android emulator, or screenshot an iOS 17+ physical device. Read-only with respect to project source; writes only a screenshot artifact. Runs the bundled device-shot.sh helper.

AndrewDongminYoo/rn-agents-kit

Skill Claude CodeCodex

Use when you need to read a running React Native app's console output — confirm a log fired, watch console.warn/error, or verify runtime behavior — without opening the DevTools GUI. Reads logs from Metro's CDP endpoint; bounded by default. Read-only with respect to project source. Runs the bundled rn-console.mjs…

AndrewDongminYoo/rn-agents-kit

Skill Claude CodeCodex

Use when planning a React Native upgrade or asking "is my app ready for the New Architecture?" — audits which dependencies and app-local native modules block enabling the New Architecture. Read-only; reports and interprets, changes nothing. Wraps the rn-newarch-ready CLI.

AndrewDongminYoo/rn-agents-kit

Skill Claude CodeCodex

Use when you want a fast, read-only snapshot of a React Native project's setup — RN/Expo version, New Architecture and Hermes flags, package manager, key config files — before deciding what to audit or upgrade. Read-only; routes to the deeper audits. A read-only reader: it surfaces stable files and commands, never…

AndrewDongminYoo/cc-agents-kit

Plugin Claude Code

Guardrails and workflow tooling for Claude Code, packaged as installable plugins.

AndrewDongminYoo/cc-agents-kit

Instructions file

Claude Code instructions for AndrewDongminYoo/cc-agents-kit, covering claude.md, what this repo is, commands, layout contract and hook contract.

AndrewDongminYoo/cc-agents-kit

Plugin Claude Code

Carry work across sessions and keep the context that carries it lean: hand off a session, export or log what it found, chart an effort too big for one sitting, and audit or garbage-collect your Claude Code config.

AndrewDongminYoo/cc-agents-kit

Skill Claude CodeCodex

Garbage collection for the active Claude config root — scans skills, memory, hooks, permissions, MCP servers, and caches for redundant, stale, or orphaned items, then walks the user through confirm-each-deletion cleanup. Use on "clean up my config", "config GC", "too many skills", "my .claude is bloated", or a…

AndrewDongminYoo/cc-agents-kit

Skill Claude CodeCodex

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.

AndrewDongminYoo/cc-agents-kit

Skill Claude CodeCodex

Use when a session's context is getting long or degrading and you need a detailed, self-contained summary to manually paste into a fresh session (or hand to another machine/tool/teammate). For a short durable fact instead, write it to the persistent memory directory (auto-loaded via MEMORY.md).

AndrewDongminYoo/cc-agents-kit

Skill Claude CodeCodex

Use when the user asks to record what a session discovered or learned ("기록해줘", "로그 남겨줘", "log this", "/log-it"), when a session ends after non-obvious findings or trial-and-error, or before /clear would lose them.

AndrewDongminYoo/cc-agents-kit

Skill Claude CodeCodex

Export a Claude Code session transcript as clean chat-style markdown with collapsed tool calls. Use when the user wants to save, archive, or re-read a session as a document — "세션 내보내줘", "export this session as markdown". For a compact continuation summary use /handoff instead.

AndrewDongminYoo/cc-agents-kit

Skill Claude CodeCodex

Chart an effort too big for one session as a map of decision tickets under docs/plans/, then resolve one ticket per session until the way to the destination is clear.

AndrewDongminYoo/cc-agents-kit

Plugin Claude Code

Eight defensive hooks: blocks recursive rm on $HOME, download-and-execute pipelines, secrets-file access, path-less formatter runs, credentials in the staged diff, and the two zsh quoting mistakes that fail silently; warns on stale lockfiles and shellcheck findings; masks credential-shaped values out of Bash output…

AndrewDongminYoo/cc-agents-kit

Hook

Runs before the agent uses a tool for Read, Edit, Write, MultiEdit, NotebookEdit, Bash, Grep, Glob and Bash tool calls, executing secrets-path-guard.sh, dangerous-command-guard.sh, zsh-quoting-guard.sh, pathless-rewriter-guard.sh and staged-secret-guard.sh via bash (5 commands). From AndrewDongminYoo/cc-agents-kit.

AndrewDongminYoo/cc-agents-kit

Hook

Runs after a tool call finishes for Edit, MultiEdit, Write and Bash tool calls, executing lockfile-drift-check.sh, shellcheck-on-edit.sh and output-secret-mask.sh via bash (3 commands). From AndrewDongminYoo/cc-agents-kit.

AndrewDongminYoo/cc-agents-kit

Plugin Claude Code

What runs between "the code works" and "it is pushed": trunk setup, conventional-commit splitting, dependency vulnerability triage, spell-check triage, and babysitting CI until it is green.

AndrewDongminYoo/cc-agents-kit

Skill Claude CodeCodex

Use after pushing a branch or opening a PR when CI needs monitoring or authorized make-green work. Keeps watch-only requests read-only, requires explicit current-request or approved-plan authority before reruns or local repairs, and stops honestly when a human or logic change is needed. Works in any ecosystem.

AndrewDongminYoo/cc-agents-kit

Skill Claude CodeCodex

Use when cspell reports unknown words or forbidden words in a repository, when adding entries to a cspell dictionary, or when a cspell config needs setting up, consolidating, or auditing.

AndrewDongminYoo/cc-agents-kit

Skill Claude CodeCodex

Use when osv-scanner or trunk check reports dependency vulnerabilities (GHSA-) in a pnpm/npm/yarn project and you need to triage and fix them.