sanity-io/agent-toolkit
Collection of resources to help AI agents build better with Sanity.
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http Sanity https://mcp.sanity.io $ npx degit sanity-io/agent-toolkit/commands ./rig-agent-toolkit/commands $ npx degit sanity-io/agent-toolkit/skills ./rig-agent-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.
$ claude mcp add --transport http Sanity https://mcp.sanity.io $ npx degit sanity-io/agent-toolkit/skills/content-experimentation-best-practices .claude/skills/content-experimentation-best-practices $ npx degit sanity-io/agent-toolkit/skills/content-modeling-best-practices .claude/skills/content-modeling-best-practices $ npx degit sanity-io/agent-toolkit/skills/portable-text-conversion .claude/skills/portable-text-conversion $ npx degit sanity-io/agent-toolkit/skills/portable-text-serialization .claude/skills/portable-text-serialization $ npx degit sanity-io/agent-toolkit/skills/sanity-best-practices .claude/skills/sanity-best-practices $ npx degit sanity-io/agent-toolkit/skills/sanity-migration .claude/skills/sanity-migration $ npx degit sanity-io/agent-toolkit/skills/sanity-studio-upgrade .claude/skills/sanity-studio-upgrade $ npx degit sanity-io/agent-toolkit/skills/seo-aeo-best-practices .claude/skills/seo-aeo-best-practices
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 *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| mcp.sanity.io · "Sanity" | remote · remote | 2.5k |
Skills (8)
content-experimentation-best-practicescontent-modeling-best-practicesportable-text-conversionportable-text-serializationsanity-best-practicessanity-migrationsanity-studio-upgradeseo-aeo-best-practices
Slash commands (4)
/deploy-schema/sanity-review/sanity/typegen
Similar rigs
opencue/cuecards
Agent profile manager for Claude Code & Codex. Per-directory profiles select which skills, MCP servers, and plugins load — automatically, before launch. Install: npm install -g cue-ai
Orchestrator 12.5k tok ·
waseemnasir2k26/skynetlabs-all-claude-code
44 production-grade Claude Code skills from a real one-person AI agency - reels and video, SEO/AEO content engines, client delivery, code review, n8n automation, proposals, token efficiency. Battle-tested on paid work, scrubbed of client da
MCP Hoarder 43.1k tok ·
Tekkiiiii/the-agency
Open-source multi-agent command center for Claude Code. 244 skills, 200+ agents across 14 departments, PD-driven autonomous workflows, SQLite task store, file-based memory. Installs to ~/.claude/ — zero cloud dependencies.
Orchestrator 7.8k tok ·
anomalyco/opencode
The open source coding agent.
Pragmatist 4.2k tok ·