cablate/ai-toolkit
Battle-tested Claude Code skills for relentless AI delivery
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 cablate/ai-toolkit/agents ./rig-ai-toolkit/agents $ npx degit cablate/ai-toolkit/skills ./rig-ai-toolkit/skills
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 cablate/ai-toolkit/skills/agentskill-expertise .claude/skills/agentskill-expertise $ npx degit cablate/ai-toolkit/skills/handoff .claude/skills/handoff $ npx degit cablate/ai-toolkit/skills/project-docs .claude/skills/project-docs $ npx degit cablate/ai-toolkit/skills/self-growth .claude/skills/self-growth $ npx degit cablate/ai-toolkit/skills/thorough .claude/skills/thorough $ npx degit cablate/ai-toolkit/skills/vector-memory .claude/skills/vector-memory
$ curl -fsSL --create-dirs -o .claude/agents/agent-factory.md https://raw.githubusercontent.com/cablate/ai-toolkit/master/agents/agent-factory.md $ curl -fsSL --create-dirs -o .claude/agents/analyst.md https://raw.githubusercontent.com/cablate/ai-toolkit/master/agents/analyst.md $ curl -fsSL --create-dirs -o .claude/agents/builder.md https://raw.githubusercontent.com/cablate/ai-toolkit/master/agents/builder.md $ curl -fsSL --create-dirs -o .claude/agents/doc-sync.md https://raw.githubusercontent.com/cablate/ai-toolkit/master/agents/doc-sync.md $ curl -fsSL --create-dirs -o .claude/agents/investigator.md https://raw.githubusercontent.com/cablate/ai-toolkit/master/agents/investigator.md $ curl -fsSL --create-dirs -o .claude/agents/reviewer.md https://raw.githubusercontent.com/cablate/ai-toolkit/master/agents/reviewer.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 (6)
Subagents (6)
| agent-factory model: opus | Design and generate new agent prompts. Use when: creating a new specialized agent from scratch, converting a workflow into an agent, or improving an existing agent's prompt quality. |
| analyst model: sonnet | Architecture design, implementation planning, codebase audit. Use when: deciding HOW to build something, evaluating approaches, auditing codebase health. Read-only — produces analysis and plans, never |
| builder model: sonnet | Code implementation, modification, and test writing/fixing. Use when: writing new code, changing existing code, writing tests, fixing tests, implementing a plan. Write mode — creates and modifies file |
| doc-sync model: haiku | Documentation initialization and sync. Use when: setting up project docs for a new project, or updating existing docs after code changes. |
| investigator model: haiku | Codebase search, module exploration, root cause diagnosis, external research. Use when: finding WHERE something is, understanding HOW something works, diagnosing WHY something fails. Read-only — produ |
| reviewer model: sonnet | Code quality review and dead code cleanup. Use when: reviewing changes for bugs/security issues, finding unused code, cleaning up after implementation. Can auto-fix mechanical issues (unused imports, |
Similar rigs
RandallLiuXin/GodotMaker
Autonomous text-to-game pipeline for Godot, powered by Claude Code,Codex,Opencode
Orchestrator 1.5k tok ·
yourconscience/tackroom
Dotfiles for your AI agents: one ~/.agents repo for skills, MCP servers, hooks, agent roles, and memory — synced natively to Claude Code, Codex, OMP/Pi, OpenCode, Droid, and Hermes. Commit-pinned and audited externals.
Orchestrator 1.4k tok ·
arbindpd96/archkeeper
Keeps your AI coding agent on course: a living architecture map, decision memory that survives compaction, enforced code standards and design-system sync. One command for Claude Code, Codex, Cursor and more.
Fort Knox 1.6k tok ·
orynvn/claude-workspace-setup
A project template for Claude Code CLI — opinionated, token-efficient, and built for multi-agent workflows.
Orchestrator 22.3k tok ·