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/sanity-review)<a href="https://agentmods.dev/commands/sanity-io/agent-toolkit/sanity-review"><img src="https://agentmods.dev/badge/commands/sanity-io/agent-toolkit/sanity-review.svg" alt="Measured on agentmods" 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 | $0.00015 | $0.00331 |
| Opus 5 | $0.00008 | $0.00166 |
| Sonnet 5 | $0.00003 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
sanity-review 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 7d 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 Code Review
I'll review your Sanity code for best practices. Here's what I check:
Schema Review
-
Definition Syntax
- Using
defineType,defineField,defineArrayMember - Icons assigned from
@sanity/icons - Proper validation rules
- Using
-
Data Modeling
- "Data > Presentation" philosophy (no
bigHero,redButton) - Correct use of references vs nested objects
- Proper deprecation pattern for removed fields
- "Data > Presentation" philosophy (no
-
Organization
- File naming conventions (kebab-case)
- Schema directory structure
Query Review
-
TypeGen Compatibility
- Queries wrapped in
defineQuery - SCREAMING_SNAKE_CASE naming
- Proper field projections (not
*)
- Queries wrapped in
-
Performance
- No unnecessary deep expansions
- Using query parameters (not string interpolation)
Frontend Review
-
Visual Editing
- Using
_keyfor array item keys (not index) stegaCleanfor logic-critical values- No stega in
<head>tags
- Using
-
Type Safety
- Using generated types from
sanity.types.ts - No manual typing of query results
- Using generated types from
Usage
Just ask me to review specific files or your whole Sanity setup:
"Review my post schema" "Check my GROQ queries for issues" "Review my Sanity frontend integration"
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.
- 7d ago First seen · 54 lines · 15 tokens per session scan A fc0ba3a9968b
sanity-review is a command published in the GitHub repository sanity-io/agent-toolkit (181 stars, last pushed 3d ago), licensed MIT. It adds 15 tokens to every session and 331 once invoked, about $0.0001 per session on Opus 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
implement
Multi-agent advisory squad workflow for implementing code changes: classify → score risk → select agents → planner → Gate 1 (plan approval) → advisory squad → Gate 2 (Blocker halt) → implementer → consolidator → verdict. Auto-detects depth (quick/normal/deep) from risk + file count; pass --quick or --deep to override.…
inventory
Codebase inventory skill — scans the repo for a named pattern (inline SQL, fetch calls, feature flags, debug leftovers, deprecated APIs, etc.) and emits a structured Markdown inventory cross-referenced with framework metadata (routes, handlers). Language-agnostic and pack-driven — the engine matches whatever a YAML…
brainstorm
Pre-implementation brainstorm + parallel web research. Spawns specialist agents in parallel with targeted web queries; synthesizes findings into an options matrix with cited sources and a recommendation. Exploratory only — never writes code or files. Use BEFORE /squad:implement to decide what to build, compare…
grillme
Socratic plan validation. Grills your plan one question at a time against the project's CONTEXT.md glossary and prior ADRs; resolves terminology and decisions inline. WRITES to CONTEXT.md and docs/adr/ (with per-write confirmation) — use --no-write for dry-run. Triggers: "grill my plan", "stress-test this plan"…
review
Multi-agent advisory review of an existing branch, PR, diff, or current uncommitted changes — same agents and severity model as /squad:implement but review-only. Auto-detects depth (quick/normal/deep) from risk + file count; pass --quick or --deep to override. Never implements, commits, or pushes. Triggers: "review…
debug
Read-only bug investigation. Dispatches code-explorer + debugger to emit N ranked hypotheses (1/3/5 on --quick/--normal/--deep) with file:line evidence, verification steps, and confidence labels. Never writes code, never commits. Triggers: "investigate this bug", "what could cause X", "help me debug", "why is X…