agentrigs
+ submit rig
~ / rigs / ApurvBazari / claude-plugins

ApurvBazari/claude-plugins

A curated collection of plugins for Claude Code — powering AI-driven development and agentic workflows

↗ GitHub ★ 0 mit updated 1d ago collection Claude Code Claude plugin
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~4.4k tokens
Moderate · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit ApurvBazari/claude-plugins/.claude ./rig-claude-plugins  # 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 ApurvBazari/claude-plugins/.claude/skills/doc-audit .claude/skills/doc-audit
$ npx degit ApurvBazari/claude-plugins/.claude/skills/feature-done .claude/skills/feature-done
$ npx degit ApurvBazari/claude-plugins/.claude/skills/progressive-disclosure .claude/skills/progressive-disclosure
$ npx degit ApurvBazari/claude-plugins/.claude/skills/release-docs .claude/skills/release-docs
$ npx degit ApurvBazari/claude-plugins/.claude/skills/test-plugins-locally .claude/skills/test-plugins-locally
$ npx degit ApurvBazari/claude-plugins/.claude/skills/validate .claude/skills/validate
$ npx degit ApurvBazari/claude-plugins/handoff/skills/check .claude/skills/check
$ npx degit ApurvBazari/claude-plugins/handoff/skills/discard .claude/skills/discard
$ npx degit ApurvBazari/claude-plugins/handoff/skills/pickup .claude/skills/pickup
$ npx degit ApurvBazari/claude-plugins/handoff/skills/save .claude/skills/save
$ npx degit ApurvBazari/claude-plugins/lens/skills/capability .claude/skills/capability
$ npx degit ApurvBazari/claude-plugins/lens/skills/engine .claude/skills/engine
$ npx degit ApurvBazari/claude-plugins/lens/skills/render-review .claude/skills/render-review
$ npx degit ApurvBazari/claude-plugins/lens/skills/review .claude/skills/review
$ npx degit ApurvBazari/claude-plugins/notify/skills/setup .claude/skills/setup
$ npx degit ApurvBazari/claude-plugins/notify/skills/uninstall .claude/skills/uninstall
$ npx degit ApurvBazari/claude-plugins/notify/skills/wizard .claude/skills/wizard
$ npx degit ApurvBazari/claude-plugins/onboard/skills/adopt .claude/skills/adopt
$ npx degit ApurvBazari/claude-plugins/onboard/skills/evolve .claude/skills/evolve
$ npx degit ApurvBazari/claude-plugins/onboard/skills/generate .claude/skills/generate
$ npx degit ApurvBazari/claude-plugins/onboard/skills/generation .claude/skills/generation
$ npx degit ApurvBazari/claude-plugins/onboard/skills/maintain .claude/skills/maintain
$ npx degit ApurvBazari/claude-plugins/onboard/skills/research .claude/skills/research
$ npx degit ApurvBazari/claude-plugins/onboard/skills/start .claude/skills/start
$ npx degit ApurvBazari/claude-plugins/onboard/skills/update .claude/skills/update
$ npx degit ApurvBazari/claude-plugins/onboard/skills/verify .claude/skills/verify
$ npx degit ApurvBazari/claude-plugins/walkthrough/skills/create .claude/skills/create
$ npx degit ApurvBazari/claude-plugins/walkthrough/skills/document .claude/skills/document
$ npx degit ApurvBazari/claude-plugins/walkthrough/skills/render .claude/skills/render
$ curl -fsSL --create-dirs -o .claude/agents/docs-verifier.md https://raw.githubusercontent.com/ApurvBazari/claude-plugins/develop/.claude/agents/docs-verifier.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

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

Skills (29)

doc-auditfeature-doneprogressive-disclosurerelease-docstest-plugins-locallyvalidatecheckdiscardpickupsavecapabilityenginerender-reviewreviewsetupuninstallwizardadoptevolvegenerategenerationmaintainresearchstartupdateverifycreatedocumentrender

Subagents (1)

docs-verifier
model: opus
Adversarial, read-only verifier for /release-docs. Given the diff of the doc files a sync changed and the source files behind them, it tries to refute every added or changed claim against the source a

Similar rigs

JuliusBrussee/cavekit
Frozen — compressed spec-driven development plugin for Claude Code. Still works; active development moved to JuliusBrussee/caveman.
★ 1,148 project Claude Code 8 skills 2mo ago
Pragmatist 75 tok ·
onurpolat05/ALBA
Turn Claude Code into a personal AI agent with persistent memory. Interactive setup, 9 skills, 8 hooks, role-agnostic. Verified against v2.1.220.
★ 22 project Claude Code 9 skills 5 agents 18 hooks 2mo ago
Fort Knox 3.9k tok ·
Q00/ouroboros
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
★ 6,169 project Claude CodeCodex 1 mcp 23 skills 2 hooks 7d ago
Skill Collector 5.1k tok ·
chengxuniucode/ForgeTeam
AI coding framework — one person, full team delivery. Pure Shell+Markdown, zero dependencies, works with Claude Code / Cursor / Codex / OpenCode. 开源 AI 编码框架，一人全栈交付。
★ 0 project Claude Code 13 skills 1 hooks 2mo ago
Skill Collector 748 tok ·
copied ✓