exaltedo2/agent-crew
A reusable Claude Code agent team: orchestrator + subagents, cost ledger, hooks, and hire/retire/retro skills.
stack: PowerShell
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
Copy this rig
# review before running: this installs third-party code $ npx degit exaltedo2/agent-crew/agents ./rig-agent-crew/agents $ npx degit exaltedo2/agent-crew/skills ./rig-agent-crew/skills $ npx degit exaltedo2/agent-crew/hooks ./rig-agent-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.
$ npx degit exaltedo2/agent-crew/skills/crew-bootstrap .claude/skills/crew-bootstrap $ npx degit exaltedo2/agent-crew/skills/crew-hire .claude/skills/crew-hire $ npx degit exaltedo2/agent-crew/skills/crew-retire .claude/skills/crew-retire $ npx degit exaltedo2/agent-crew/skills/crew-retro .claude/skills/crew-retro
$ curl -fsSL --create-dirs -o .claude/agents/architect.md https://raw.githubusercontent.com/exaltedo2/agent-crew/main/agents/architect.md $ curl -fsSL --create-dirs -o .claude/agents/coder.md https://raw.githubusercontent.com/exaltedo2/agent-crew/main/agents/coder.md $ curl -fsSL --create-dirs -o .claude/agents/lead.md https://raw.githubusercontent.com/exaltedo2/agent-crew/main/agents/lead.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/exaltedo2/agent-crew/main/agents/reviewer.md $ curl -fsSL --create-dirs -o .claude/agents/scout.md https://raw.githubusercontent.com/exaltedo2/agent-crew/main/agents/scout.md $ curl -fsSL --create-dirs -o .claude/agents/thinker.md https://raw.githubusercontent.com/exaltedo2/agent-crew/main/agents/thinker.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 (4)
Subagents (6)
| architect model: opus | Design and reasoning only, no code. Use for unclear requirements, cross-system interactions and architecture decisions; returns options, a recommendation and a numbered task list for the coder. |
| coder model: sonnet | Implements a given plan or a clearly defined change, runs all the project's checks, and can commit, push a branch and open a pull request. Does not make design decisions. |
| lead model: opus | Orchestrator. Talks with the user, clarifies the goal, and delegates the work to the other agents, choosing the model and effort of every call. Does not edit project files itself. |
| reviewer model: sonnet | Adversarial reviewer that tries to disprove that a change or system works, and reports concrete bugs with file and line. Use after every coding task and for bugs whose cause is unknown. Does not edit |
| scout model: haiku | Fast read-only search that finds files, definitions and usages ("where is X used?") and returns a short factual summary with paths and line numbers. |
| thinker model: sonnet | Challenges ideas and plans for logic flaws, contradictions, exploits and missing cases, and comes up with alternatives. Thinks only; never writes code. Use before designing something new, to stress-te |
Similar rigs
AegeanWorks/AIKit
Crash-resilient governance and delivery gates for AI coding agents: versioned task ledger, commit-level verification, secret scanning and per-project gates. Free for personal use under AL-1.1; commercial use under ACL-1.0.
Orchestrator 4.2k tok · · Q23
jmigual/dotfiles
Personal dotfiles
Pragmatist 479 tok · · Q0
ilfroloff/snapback
Terminal board for Claude Code: every session and background agent across your repos and worktrees, live. See which agent needs you, reply or stop it without leaving, and find any session by what was said.
Pragmatist 6.5k tok · · Q3
Gildaciolopes/agentic-dev-stack
Smart vibe coding with Claude Code: multi-agent orchestration (Opus plans; Sonnet, Haiku, Gemini, Codex and free models execute), Spec Kit SDD, caveman + RTK + graphify token savings, sandboxed secrets, self-healing free models and a Hermes
Minimalist 1.2k tok · · Q10