NYCU-Chung

31 mods across 3 repositories, 580 stars between them.

my-claude-devteam

02

NYCU-Chung/my-claude-devteam

Plugin Claude Code

An engineering team in a box for Claude Code. 12 specialized subagents (planner, fullstack-engineer, refactor-specialist, migration-engineer, frontend-designer, critic, vuln-verifier, debugger, db-expert, onboarder, tool-expert, web-researcher) plus 15 automation hooks (pre-commit secret scan, MCP health tracking…

270 4mo ago A tokens not measured original MIT

critic

03

NYCU-Chung/my-claude-devteam

Agent

Code reviewer and security auditor. Hunts for bugs, security holes, logic errors, edge cases, performance issues, and inconsistencies. Every finding with file path + line number. Use before every commit, deploy, or merge. Also handles deep security review (hardcoded secrets, injection, XSS, path traversal).

270 4mo ago A 65 tokens original MIT

db-expert

04

NYCU-Chung/my-claude-devteam

Agent

Database expert: schema design, migration safety, query optimization, index advice. Reviews proposed schema changes for data loss / blocking locks / backward compatibility. Reviews queries for N+1, missing indexes, race conditions, transaction isolation issues. Read-only — analyzes and reports, never modifies. Use…

270 4mo ago A 69 tokens original MIT

debugger

05

NYCU-Chung/my-claude-devteam

Agent

Debug engineer and log analyst. Systematically finds the root cause of bugs: reads logs, narrows scope, builds hypotheses, verifies, fixes. Also analyzes PM2 / Docker / systemd / Nginx logs for error patterns. Use for any bug, service outage, test failure, or unexpected behavior. Never guesses — always traces.

270 4mo ago A 71 tokens original MIT

frontend-designer

06

NYCU-Chung/my-claude-devteam

Agent

Frontend designer who builds memorable UIs: landing pages, dashboards, components. Rejects generic AI slop, commits to a bold aesthetic direction, ships production-quality code. Use for new pages, UI redesigns, and visual upgrades.

270 4mo ago A 51 tokens original MIT

fullstack-engineer

07

NYCU-Chung/my-claude-devteam

Agent

Senior full-stack engineer operating the P7 methodology: read reality → design solution → impact analysis → implement → three-question self-review → [P7-COMPLETION] delivery. Ships features across frontend, backend, and DevOps. Use for single-feature implementation and cross-module changes.

270 4mo ago C 62 tokens original MIT

migration-engineer

08

NYCU-Chung/my-claude-devteam

Agent

Framework / library / language version upgrades. Handles breaking changes, deprecation removals, major-version bumps. Reads the upstream changelog, audits every usage of changed APIs, executes the upgrade incrementally with verification at each step. Use for Next.js 13→14, Vue 2→3, Tailwind 3→4, React 18→19…

270 4mo ago A 84 tokens original MIT

onboarder

09

NYCU-Chung/my-claude-devteam

Agent

Codebase explorer for first-time exploration. Builds a mental model of an unfamiliar codebase: architecture, entry points, key modules, external dependencies, suspicious areas. Read-only. Use when joining a new project, evaluating an open-source repo before contributing, or auditing a repo you haven't touched in…

270 4mo ago A 64 tokens original MIT

planner

10

NYCU-Chung/my-claude-devteam

Agent

Tech lead operating the P9 methodology. Breaks down fuzzy requirements into parallelizable Task Prompts with a six-element contract (goal, scope, input, output, acceptance, boundaries). Use before complex tasks touching 3+ files or 2+ modules. Never writes code — output is prompts, not implementation.

270 4mo ago A 65 tokens original MIT

refactor-specialist

11

NYCU-Chung/my-claude-devteam

Agent

Large-scale safe refactoring: rename across many files, extract module, move files, restructure folders. Differs from fullstack-engineer by being more cautious, scoped, and verification-heavy. Use for refactors that touch 10+ files where regression risk is real.

270 4mo ago A 59 tokens original MIT

tool-expert

12

NYCU-Chung/my-claude-devteam

Agent

Tool expert who picks the right tools, chains complex workflows, and troubleshoots tool failures. Knows when to use built-in tools vs MCP servers vs shell commands. Use for complex tool chaining, MCP server issues, or when you're unsure which tool fits the job.

270 4mo ago A 58 tokens original MIT

vuln-verifier

13

NYCU-Chung/my-claude-devteam

Agent

Vulnerability verifier. Takes the critic's findings and writes actual PoC code to prove each vulnerability is real (or a false positive). Produces verification reports suitable for security advisories, issues, and PRs. Use AFTER critic flags a suspected security issue.

270 4mo ago B 58 tokens original MIT

web-researcher

14

NYCU-Chung/my-claude-devteam

Agent

Technical documentation researcher. Looks up API specs, official docs, error codes, version differences, and library usage. Search-only — never writes code, never modifies files. Use whenever the team needs ground truth from the web and you're tired of guessing.

270 4mo ago A 54 tokens original MIT

PreToolUse

15

NYCU-Chung/my-claude-devteam

Hook

Runs before the agent uses a tool for Bash, Write, Edit, mcp__.* and Read tool calls, executing branch-protection.js, commit-quality.js, config-protection.js, suggest-compact.js, mcp-health.js and large-file-warner.js via node with --no-verify (10 commands). From NYCU-Chung/my-claude-devteam.

270 4mo ago C tokens not measured original MIT

PostToolUse

16

NYCU-Chung/my-claude-devteam

Hook

Runs after a tool call finishes for Bash, Write and Edit tool calls, executing log-error.sh, audit-log.js, accumulator.js, design-quality.js and test-runner.js via bash (5 commands). From NYCU-Chung/my-claude-devteam.

270 4mo ago A tokens not measured original MIT

PostToolUseFailure

17

NYCU-Chung/my-claude-devteam

Hook

Runs when a tool call fails for mcp__.* tool calls, executing mcp-health.js via node. From NYCU-Chung/my-claude-devteam.

270 4mo ago A tokens not measured original MIT

Stop

18

NYCU-Chung/my-claude-devteam

Hook

Runs when the agent finishes a response, executing batch-format.js, check-console.js, cost-tracker.js and session-summary.js via node (4 commands). From NYCU-Chung/my-claude-devteam.

270 4mo ago A tokens not measured original MIT

SessionStart

19

NYCU-Chung/my-claude-devteam

Hook

Runs when a session starts on startup and resume, running an inline shell check. From NYCU-Chung/my-claude-devteam.

270 4mo ago A tokens not measured original MIT

cc-statusline

21

NYCU-Chung/cc-statusline

Plugin Claude Code

A comprehensive statusline dashboard for Claude Code — session summary, quota bars, agent tracker, MCP health, message history, and more. All at a glance, no slash commands needed.

264 3mo ago A tokens not measured original MIT

rows

22

NYCU-Chung/cc-statusline

Command

Configure which rows cc-statusline shows (or turn it off entirely).

264 3mo ago A 14 tokens original MIT

SubagentStart

23

NYCU-Chung/cc-statusline

Hook

Runs when a subagent starts, executing subagent-tracker.js via node. From NYCU-Chung/cc-statusline.

264 3mo ago A tokens not measured original MIT

SubagentStop

24

NYCU-Chung/cc-statusline

Hook

Runs when a subagent finishes, executing subagent-tracker.js via node. From NYCU-Chung/cc-statusline.

264 3mo ago A tokens not measured copy · 91% MIT