Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/sanity-io/agent-toolkitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/sanity-io/agent-toolkit/typegen)<a href="https://agentmods.dev/commands/sanity-io/agent-toolkit/typegen"><img src="https://agentmods.dev/badge/commands/sanity-io/agent-toolkit/typegen/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/sanity-io/agent-toolkit/typegen"><img src="https://agentmods.dev/badge/commands/sanity-io/agent-toolkit/typegen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00014 | $0.00464 |
| Opus 5.5 | $0.00006 | $0.00186 |
| Sonnet 5.5 | $0.00003 | $0.00093 |
| Haiku 4.5 | $0.00001 | $0.00046 |
Grade A, and why
typegen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Sanity TypeGen Workflow
I'll help you generate TypeScript types from your Sanity schema.
Quick Start
npm run typegen
# or
npx sanity schemas extract && npx sanity typegen generate
What I'll Do
-
Check Configuration
- Check for
typegenconfig insanity.cli.ts(recommended) - If using deprecated
sanity-typegen.json, suggest migrating tosanity.cli.ts - Ensure
typegenscript is inpackage.json(for manual workflows)
- Check for
-
Run TypeGen
- Execute the typegen command
- Report any errors
-
Troubleshoot Issues
- Fix incorrect path globs
- Resolve schema syntax errors
- Update query imports
- Migrate deprecated
sanity-typegen.jsontosanity.cli.ts
Common Issues I Fix
| Issue | Solution |
|---|---|
| "No schema found" | Fix path glob in sanity.cli.ts typegen config |
| "Query not typed" | Wrap in defineQuery() or groq template |
| Types outdated | Re-run after schema/query changes, or enable automatic generation |
| Import errors | Check sanity.types.ts output path |
Using sanity-typegen.json |
Migrate config to sanity.cli.ts (deprecated) |
Configuration
Configure TypeGen in sanity.cli.ts:
// sanity.cli.ts
import { defineCliConfig } from 'sanity/cli'
export default defineCliConfig({
typegen: {
enabled: true, // Auto-generate during sanity dev/build
path: "./src/**/*.{ts,tsx,js,jsx,astro,svelte,vue}",
schema: "schema.json",
generates: "./sanity.types.ts",
overloadClientMethods: true,
},
})
Usage
"Run typegen" "Fix my TypeGen configuration" "Why are my types not updating?" "Enable automatic type generation"
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 70 lines · 14 tokens per session scan A 2cb7f1897fcc
typegen is a command published in the GitHub repository sanity-io/agent-toolkit (190 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 464 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
typescript-dev
Start TypeScript development workflow with architecture, implementation, review, and testing phases.
js-game-tools
Work on JavaScript or TypeScript game tooling and Firebase code.
ts-check-status
Short Claude front door for the implicit-eligible $js-static-checks status action.
stats
Show squad-mcp observability dashboard for past runs in this workspace. Bar charts, score distribution, verdict mix, sparkline trend, per-agent token + wall-clock cost breakdown. Reads .squad/runs.jsonl; never writes. Triggers: "squad stats", "run history", "score distribution", "where did the tokens go", "how much…
react
Apply React with TypeScript best practices.
typescript
Apply TypeScript best practices and coding standards.