agentrigs
+ submit rig
~ / rigs / jasgr-software / agentstack

jasgr-software/agentstack

A structured multi-agent execution engine for Claude Code

↗ GitHub ★ 0 MIT updated 6mo ago project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~3.9k 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 jasgr-software/agentstack/agents ./rig-agentstack/agents
$ npx degit jasgr-software/agentstack/hooks ./rig-agentstack/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/developer.md https://raw.githubusercontent.com/jasgr-software/agentstack/main/agents/developer.md
$ curl -fsSL --create-dirs -o .claude/agents/overwatch.md https://raw.githubusercontent.com/jasgr-software/agentstack/main/agents/overwatch.md
$ curl -fsSL --create-dirs -o .claude/agents/ra.md https://raw.githubusercontent.com/jasgr-software/agentstack/main/agents/ra.md
$ curl -fsSL --create-dirs -o .claude/agents/sa.md https://raw.githubusercontent.com/jasgr-software/agentstack/main/agents/sa.md
$ curl -fsSL --create-dirs -o .claude/agents/sdet.md https://raw.githubusercontent.com/jasgr-software/agentstack/main/agents/sdet.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

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

Subagents (5)

developer
model: sonnet
>
overwatch
model: sonnet
>
ra
model: sonnet
>
sa
model: opus
>
sdet
model: sonnet
>

Similar rigs

joshido/ai-template
A project-agnostic four-agent AI development workflow template for Claude Code, Gemini CLI, and GitHub Copilot.
★ 0 project Claude CodeCodexGemini CLI 4 agents 1 hooks 9d ago
Pragmatist 1.3k tok ·
yeyo11/agentry
Run Claude Code as a service: REST API, web UI and multi-agent orchestration in one container
★ 6 project Claude Code 1 mcp 3 skills 4 agents 1 hooks 7d ago
Pragmatist 5.2k tok ·
ThinhHoang1/claude-code-agent-team
An AI dev team for Claude Code agent teams: 8 role agents, a HANDOFF protocol and 3 hook quality gates — with the TeammateIdle infinite-loop bug fixed and regression-tested.
★ 0 project Claude Code 8 agents 3 hooks 1d ago
Orchestrator 1.6k tok ·
danielfarnose/claude-code-dev-loop
A multi-agent development loop for Claude Code: five specialized subagents plan, implement, verify and merge — with a QA gate that cannot edit the code it judges.
★ 1 project Claude Code 8 skills 6 agents today
Orchestrator 1.2k tok ·
copied ✓