qivora-labs/agentinit
ESLint + Prettier for AI coding agent rules.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code
$ npx degit qivora-labs/agentinit/.claude ./rig-agentinit # inspect, then merge into .claude/ 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.
$ npx degit qivora-labs/agentinit/.claude/skills/commit-changes .claude/skills/commit-changes $ npx degit qivora-labs/agentinit/.claude/skills/implement-task .claude/skills/implement-task $ npx degit qivora-labs/agentinit/.claude/skills/new-feature .claude/skills/new-feature $ npx degit qivora-labs/agentinit/.claude/skills/pr-summary .claude/skills/pr-summary $ npx degit qivora-labs/agentinit/.claude/skills/refactor .claude/skills/refactor $ npx degit qivora-labs/agentinit/.claude/skills/review-arch .claude/skills/review-arch $ npx degit qivora-labs/agentinit/.claude/skills/review-task .claude/skills/review-task $ npx degit qivora-labs/agentinit/.claude/skills/write-fragment .claude/skills/write-fragment $ npx degit qivora-labs/agentinit/.claude/skills/write-tests .claude/skills/write-tests
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 *)"
]
}
} Skills (9)
commit-changesimplement-tasknew-featurepr-summaryrefactorreview-archreview-taskwrite-fragmentwrite-tests
Cursor rules (6)
agentinit-vitestgit-commits · alwaysio-safetypure-modulesregistry-contenttests
Similar rigs
berkekcay/link-shortener-agent-ready
Link shortener made agent-ready: AGENTS.md, scoped test rules, an implement-task skill, and a custom alias feature built in plan, implement and review stages. AI-Augmented Software Engineering, Week 4.
Minimalist 728 tok · · Q0
sjhalani7/vaen
Package your AI coding harness into a portable .agent file, and share it across repos, teams, & the community without ever having to copy-paste instructions, skills, MCP config, or secrets.
Minimalist 20 tok · · Q0
voltek/GameStack
Android game backlog app on the IGDB API (Kotlin, Compose, MVI, Clean Architecture) — and a live case study in disciplined AI-assisted development: built entirely with AI agents (mainly Claude Code), governed by CLAUDE.md, 14 Skills, ADRs a
Fort Knox 9.8k tok · · Q29
Anyesh/skillprobe
Automated end-to-end testing for AI agent skills(agentskills.io). Launches Claude Code and Cursor as subprocesses, runs scenarios in real workspaces, and asserts what the model actually does.
Minimalist 54 tok · · Q0