~ / rigs / ManeeshJupalle / claude-build-crew

ManeeshJupalle/claude-build-crew

Claude Code plugin: agents plan, build, review and ship; code gates decide what merges. macOS, Linux and Windows.

↗ GitHub ★ 2 MIT updated 9d ago project Claude Code Claude plugin
stack: Python
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~563 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 0/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit ManeeshJupalle/claude-build-crew/agents ./rig-claude-build-crew/agents
$ npx degit ManeeshJupalle/claude-build-crew/commands ./rig-claude-build-crew/commands
$ npx degit ManeeshJupalle/claude-build-crew/hooks ./rig-claude-build-crew/hooks

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.

$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/ManeeshJupalle/claude-build-crew/main/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/debugger.md https://raw.githubusercontent.com/ManeeshJupalle/claude-build-crew/main/agents/debugger.md
$ curl -fsSL --create-dirs -o .claude/agents/deployer.md https://raw.githubusercontent.com/ManeeshJupalle/claude-build-crew/main/agents/deployer.md
$ curl -fsSL --create-dirs -o .claude/agents/planner.md https://raw.githubusercontent.com/ManeeshJupalle/claude-build-crew/main/agents/planner.md
$ curl -fsSL --create-dirs -o .claude/agents/pr-creator.md https://raw.githubusercontent.com/ManeeshJupalle/claude-build-crew/main/agents/pr-creator.md
$ curl -fsSL --create-dirs -o .claude/agents/pr-reviewer.md https://raw.githubusercontent.com/ManeeshJupalle/claude-build-crew/main/agents/pr-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/release-manager.md https://raw.githubusercontent.com/ManeeshJupalle/claude-build-crew/main/agents/release-manager.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/ManeeshJupalle/claude-build-crew/main/agents/researcher.md

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 *)"
    ]
  }
}

Subagents (8)

architect
model: opus
Use at the start of a project or before a big feature. Writes docs/HOW_IT_WORKS.md — one short, human-readable page a person can use to understand and verify the system. Captures only what code can't
debugger
model: opus
Use when something is broken (bug report, failing test, error, wrong behavior). Reproduces it, proves the root cause, writes a failing regression test, applies the smallest fix, and lets checks.py con
deployer
model: sonnet
Use to deploy. Mode "staging" deploys the default-branch commit with the repo's own deploy method and smoke-tests it. Mode "production" promotes the SAME verified commit, and only when the caller pass
planner
model: opus
Use right after architect. Writes docs/PLAN.md — small, ordered phases (Phase 0, 1, 2…), each one PR, each ending in "Done when" commands that code runs to prove it's done. Never writes application co
pr-creator
model: sonnet
Use when work is finished locally and needs to become a pull request. Code gates scan for secrets and run the checks; this agent groups commits, writes the PR, and opens it. Never reviews or merges.
pr-reviewer
model: opus
Use to review an open PR before merge. Strict and evidence-based, with no file-writing tools. Judges what code can't (logic, security, design, test quality) and posts one verdict tied to the exact hea
release-manager
model: sonnet
Use to cut a release. Mode "prepare": code computes the version; you update version files and write human-readable release notes on a release branch for /ship. Mode "publish": after that PR merges, cr
researcher
model: sonnet
Use before choosing a library, framework, API, service, or approach. Compares current options with live, cited sources and returns one recommendation. Writes no files; the caller records the decision

Slash commands (9)

/build-phase/deploy/deps/fix/handoff/kickoff/release/research/ship

Similar rigs

copied ✓