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.
npx agentmods add rules/backendforth/next-sanity-starter/coregit clone --depth 1 https://github.com/backendforth/next-sanity-starterWhat 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 | $0.00214 | $0.00214 |
| Opus 5 | $0.00107 | $0.00107 |
| Sonnet 5 | $0.00043 | $0.00043 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
core 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 yesterday.
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
Canonical guardrails: /AGENTS.md. Read it before writing code in this repo.
Top-level rules (do not duplicate — see AGENTS.md for the full context):
- Reuse before invention; grep
studio/schemas/objects/modules/,web/src/components/modules/,web/sanity/queries/snippets/first. - Content blocks are modules — paired Sanity object + React component, wired in 8 places. Skipping any one is a bug.
- Locale-aware at render time, never inside GROQ. Always use
pickLocalizedString/parseLocalizedTextfromweb/sanity/utils/sanityLocalizedText.ts. - After schema edits:
pnpm studio:generate→pnpm typecheck→pnpm format. Never editstudio/sanity.types.gen.tsorstudio/schema.json. web/sanity/types/*are hand-maintained; keep aligned with field changes.
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.
- yesterday First seen · 15 lines · 214 tokens per session scan A 7365cb9c8423
core is a cursor rule published in the GitHub repository backendforth/next-sanity-starter (4 stars, last pushed 25d ago), licensed ISC. It adds 214 tokens to every session, about $0.0011 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 2026-08-31.
Other cursor rules, from other repositories
cursorrules
Cursor rule "cursorrules" from KyaniteLabs/DialectOS, covering kyanitelabs — ai agent instructions, organization, code quality, security and testing.
project-structure
Project structure, conventions, and where things live.
context
Cursor rule "context" from Takt365/Takt.Wpf, covering 上下文管理规范, 上下文分类, 文件引用规范, 上下文完整性检查 and 上下文更新规范.
naming
Cursor rule "naming" from Takt365/Takt.Wpf, covering 命名规范, 类命名, 接口命名, 方法命名 and 文件命名.
prompt
Cursor rule "prompt" from Takt365/Takt.Wpf, covering 提示语编写规范, 标准结构, 任务类型标签, 完整示例 and 禁止事项.
git-workflow
Git branching and PR workflow.