~ / rigs / ByteBoyy / agentic-dev-orchestrator

ByteBoyy/agentic-dev-orchestrator

Repository-native workflows for planning, delegating, reviewing, and shipping software with coding agents

↗ GitHub ★ 0 MIT updated 21d ago project Claude CodeCodex
stack: Python
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~1.3k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details
Quality 3/100 Guardrails v2

Copy this rig

# review before running: this installs third-party code
$ npx degit ByteBoyy/agentic-dev-orchestrator/.claude ./rig-agentic-dev-orchestrator  # 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 ByteBoyy/agentic-dev-orchestrator/.claude/skills/handoff .claude/skills/handoff
$ npx degit ByteBoyy/agentic-dev-orchestrator/.claude/skills/orchestrate .claude/skills/orchestrate
$ npx degit ByteBoyy/agentic-dev-orchestrator/.claude/skills/plan .claude/skills/plan
$ npx degit ByteBoyy/agentic-dev-orchestrator/.claude/skills/review .claude/skills/review
$ npx degit ByteBoyy/agentic-dev-orchestrator/.claude/skills/ship .claude/skills/ship
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/ByteBoyy/agentic-dev-orchestrator/main/.claude/agents/architect.md
$ curl -fsSL --create-dirs -o .claude/agents/backend-implementer.md https://raw.githubusercontent.com/ByteBoyy/agentic-dev-orchestrator/main/.claude/agents/backend-implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/code-reviewer.md https://raw.githubusercontent.com/ByteBoyy/agentic-dev-orchestrator/main/.claude/agents/code-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/explorer.md https://raw.githubusercontent.com/ByteBoyy/agentic-dev-orchestrator/main/.claude/agents/explorer.md
$ curl -fsSL --create-dirs -o .claude/agents/frontend-implementer.md https://raw.githubusercontent.com/ByteBoyy/agentic-dev-orchestrator/main/.claude/agents/frontend-implementer.md
$ curl -fsSL --create-dirs -o .claude/agents/verifier.md https://raw.githubusercontent.com/ByteBoyy/agentic-dev-orchestrator/main/.claude/agents/verifier.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 *)"
    ]
  }
}

Skills (5)

Subagents (6)

architect
model: opus
Read-only planner for multi-file features, refactors, and architecture decisions. Use after discovery and before implementation.
backend-implementer
model: sonnet
Implements an approved backend milestone with exclusive ownership of named server-side files. Use only after plan approval.
code-reviewer
model: opus
Independent read-only reviewer for integrated changes. Use after implementation and before verification or shipping.
explorer
model: haiku
Read-only repository investigator for architecture, dependencies, call paths, and high-volume search. Use before planning unfamiliar work.
frontend-implementer
model: sonnet
Implements an approved frontend milestone with exclusive ownership of named client files. Use only after plan approval.
verifier
model: haiku
Runs declared acceptance checks and reports exact evidence without editing implementation files. Use after blocking review findings are resolved.

Similar rigs

copied ✓