neelamsanthoshkumar/kiro-university-task-api
🎓 Task Management REST API - Kiro University Challenge submission demonstrating all 7 lessons: spec-driven development, steering documents, hooks, property-based testing, powers, MCP, and custom agents. Built with Node.js, Express, JWT auth
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
$ git clone --depth 1 https://github.com/neelamsanthoshkumar/kiro-university-task-api MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
Merge into .claude/settings.json (project) or ~/.claude/settings.json (user). Hook commands reference scripts in the source repo — copy those too.
{
"hooks": {
"PreToolUse": [
{
"matcher": "fs_write|str_replace",
"hooks": [
{
"type": "prompt",
"command": "Review this file write operation. ONLY review if the file path matches src/**/*.js (actual source code). SKIP and allow without review if the file is: documentation (*.md, docs/**), configuration (*.json, *.config.js, .env*, .kiro/**), or t"
}
]
}
]
}
} Subagents (3)
| backend-dev | Backend API development specialist |
| docs-agent | Documentation specialist |
| testing-agent | Testing and quality assurance specialist |
Hooks (3)
| event | matcher | runs |
|---|---|---|
| PostFileSave | \\.(js|ts)$ | npm run lint -- --fix |
| PreToolUse | fs_write|str_replace | Review this file write operation. ONLY review if the file path matches src/**/*.js (actual source code). SKIP and allow without review if the file is: documentation (*.md, docs/**), configuration (*.json, *.config.js, .env*, .kiro/**), or t |
| PostTaskExec | * | npm test |
Kiro (4 steering · 1 specs · 3 hook files)
api-standards · always · 1.1k tokcode-style · always · 3.3k tokerror-handling · always · 2.0k toksecurity-standards · always · 2.9k tok
Specs: task-management-api (loaded on demand, not counted in context tax)
How Kiro files are scored: methodology.
Permissions
deny (0)
—
ask (0)
—
allow (5)
shell(npm *)
shell(node *)
shell(npm test*)
shell(npm run test*)
shell(jest*)
Similar rigs
namanrajpal/acp-to-agui
A protocol bridge that sits between any coding agent(supporting ACP) and any web frontend
Minimalist 129 tok · · Q0
nirholas/PAI
A complete private computer on a USB stick. PAI is a bootable Debian 12 Linux distro that runs Ollama locally on any x86_64 or ARM64 machine — full desktop, local AI, hardened networking, all in RAM. Plug in, boot in seconds, work anywhere,
Pragmatist 660 tok · · Q0
qshanx/docs-governance
Claude Code、Codex 与 ChatGPT 的文档驱动开发治理插件:防文档腐烂、维护上下文与决策、契约协作、测试与回归证据。
Orchestrator 716 tok · · Q0
GinVlad/claude-saas-template
Claude Code template for building SaaS with agentic AI coordination. 5-stage workflow
Orchestrator 612 tok · · Q0