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 instructions/backendforth/next-sanity-starter/claude-mdgit clone --depth 1 https://github.com/backendforth/next-sanity-starterWrote 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/instructions/backendforth/next-sanity-starter/claude-md)<a href="https://agentmods.dev/instructions/backendforth/next-sanity-starter/claude-md"><img src="https://agentmods.dev/badge/instructions/backendforth/next-sanity-starter/claude-md.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 | $0.00316 | $0.00316 |
| Opus 5 | $0.00158 | $0.00158 |
| Sonnet 5 | $0.00063 | $0.00063 |
| Haiku 4.5 | $0.00032 | $0.00032 |
Grade A, and why
next-sanity-starter CLAUDE.md 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 3d 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
Claude Code — repo entrypoint
Project guardrails: @AGENTS.md (canonical for all AI coding tools).
Claude Code additionally auto-loads scoped rules from subtree CLAUDE.md files based on the current working directory. Each one focuses on subtree-specific gotchas; the canonical rules stay in AGENTS.md:
web/CLAUDE.md— Next.js app rulesstudio/CLAUDE.md— Sanity Studio rulesstudio/schemas/objects/modules/CLAUDE.md— schema half of the module patternweb/src/components/modules/CLAUDE.md— component half of the module patternweb/sanity/CLAUDE.md— query/type layer rules
IMPORTANT: When subtree rules conflict with AGENTS.md, AGENTS.md wins. Update AGENTS.md first, then propagate.
Quick reminders (the full versions live in AGENTS.md)
- YOU MUST run all 8 module wiring points when adding/renaming a module. Skipping any is a bug.
- YOU MUST run
pnpm studio:generateafter schema edits, thenpnpm check:wiring, thenpnpm typecheck. - NEVER edit
studio/sanity.types.gen.ts,studio/schema.json, or any*.gen.*file. - NEVER filter locale inside GROQ. Locale resolves at render time via
pickLocalizedString/parseLocalizedText.
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.
- 3d ago First seen · 21 lines · 316 tokens per session scan A 3a60131e8a51
next-sanity-starter CLAUDE.md is an instructions file published in the GitHub repository backendforth/next-sanity-starter (4 stars, last pushed 27d ago), licensed ISC. It adds 316 tokens to every session, about $0.0016 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 instructions, from other repositories
qrcodly CLAUDE.md
Instructions for FloB95/qrcodly, covering claude.md, project overview, monorepo structure, commands and development.
fastapi-react-admin CLAUDE.md
Instructions for yilecoding/fastapi-react-admin, covering claude.md, 按任务导航, 让这套文档不腐烂：pnpm ctx:check, 这套文档怎么自己长大 and 结构.
react-tool AGENTS.md
AGENTS.md instructions for beixiyo/react-tool, covering 开发规范, 设计 token 系统, 设计 token 配置, token 同步机制 and 使用规范.
DONGCHIMI-CLIENT AGENTS.md
AGENTS.md instructions for TEAM-DONGCHIMI/DONGCHIMI-CLIENT, covering dongchimi-client agent guide, 저장소 정체, 기본 순서, 먼저 볼 문서 and 작업 유형별 라우팅.
superspec-ai-workflow AGENTS.md
AGENTS.md instructions for itokun99/superspec-ai-workflow, covering project name — ai agent guidelines, projects, opencode + omo agent directives, 1. firewall protocol (critical boundaries) and 2. sub-agent delegation (omni-routing).
fullstack-starter AGENTS.md
AGENTS.md instructions for first-fluke/fullstack-starter, covering oh-my-agent, architecture, per-agent dispatch, code search and workflows.