~ / rigs / cremich / promptz

cremich/promptz

Resource Library for AI-assisted software development with kiro

↗ GitHub ★ 111 MIT-0 updated 9mo ago project Kiro
share on X
ARCHETYPE
Automator
Hooks on every lifecycle event: format, lint, notify, log.
CONTEXT TAX · EVERY TURN
~26.8k tokens
Context hog · median rig: 2.3k · breakdown
GUARDRAILS
1/5
No YOLO mode · details
Quality 15/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ claude mcp add context7 -- npx -y @upstash/context7-mcp
$ claude mcp add chrome-devtools -- npx chrome-devtools-mcp@latest
$ claude mcp add next-devtools -- npx -y next-devtools-mcp@latest
$ claude mcp add shadcn -- npx shadcn@latest mcp

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.

$ claude mcp add context7 -- npx -y @upstash/context7-mcp
$ claude mcp add chrome-devtools -- npx chrome-devtools-mcp@latest
$ claude mcp add next-devtools -- npx -y next-devtools-mcp@latest
$ claude mcp add shadcn -- npx shadcn@latest mcp

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(./.env.*)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(git push --force:*)",
      "Read(**/*.pem)",
      "Read(.env)",
      "Read(~/.aws/**)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Bash(rm -rf *)",
      "Bash(sudo *)",
      "Bash(sudo:*)",
      "Bash(rm -rf /)",
      "Bash(git push -f:*)",
      "Read(.env.*)",
      "Bash(git reset --hard*)",
      "Bash(rm -rf /*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(gh pr merge *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(gh pr merge:*)",
      "Bash(gh pr create *)",
      "Bash(git reset --hard:*)",
      "Bash(npm publish:*)",
      "Bash(git rebase *)"
    ]
  }
}

MCP servers (4)

serversourceest. tokens
Context7 npm 1.2k
Chrome DevTools MCP · "chrome-devtools" npm 9.0k
Next.js DevTools · "next-devtools" npm 2.5k
shadcn/ui · "shadcn" npm 2.0k

Subagents (1)

review-agentCode review agent for validating PR implementations against specs and guardrails

Hooks (5)

eventmatcherruns
Stop*Review the conversation that just completed and identify any new information that should be added to your long-term memory. You must: 1. Establish entities for: - The user that interacted with you (if not already established) - Any c
Stop*npm run lint && npm run test
Manual*Please follow this session initialization workflow: 1. **Retrieve from Memory**: - Use the memory MCP server tools to retrieve all relevant information from your knowledge graph - Always refer to your knowledge graph as your "memory
AgentSpawn*git diff main...HEAD --name-only
AgentSpawn*git log main..HEAD --oneline

Kiro (9 steering · 1 specs · 3 hook files)

Specs: global-search (loaded on demand, not counted in context tax)

MCP config: 10 auto-approved tool(s) · 26 disabledTools

How Kiro files are scored: methodology.

Permissions

deny (0)
—
ask (0)
—
allow (13)
fs_read(.kiro/steering/**)
fs_read(.kiro/rules/**)
fs_read(app/**)
fs_read(lib/**)
fs_read(public/**)
fs_read(__tests__/**)
fs_write(.kiro/reviews/**)
shell(git diff)
shell(git log)
shell(grep)
shell(find)
web_search
web_fetch

Similar rigs

copied ✓