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/lightsound/tanstack-start-start/agents-mdgit clone --depth 1 https://github.com/lightsound/tanstack-start-startWhat 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 | $0.00593 | $0.00593 |
| Opus 5 | $0.00296 | $0.00296 |
| Sonnet 5 | $0.00119 | $0.00119 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
tanstack-start-start AGENTS.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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using Vite+ (vp)
Vite+ is one CLI for dev, build, tests, lint, format, and package management—it wraps Vite and related bundled tooling. vp dev and vp build invoke Vite. Explore with vp help, vp <command> --help, and vp --version.
Common commands: vp install, vp dev, vp check, vp lint, vp test, vp build, vp run <script>, vp add / vp remove / vp update.
Workflow: After pulling, run vp install when dependencies or lockfiles may have changed. Before calling work done, run vp check and vp test.
Common Pitfalls
- Using the package manager directly: Do not use pnpm, npm, or Yarn directly. Vite+ can handle all package manager operations.
- Always use Vite commands to run tools: Don't attempt to run
vp vitestorvp oxlint. They do not exist. Usevp testandvp lintinstead. - Running scripts: Vite+ commands take precedence over
package.jsonscripts. If there is atestscript defined inscriptsthat conflicts with the built-invp testcommand, run it usingvp run test. - Do not install Vitest, Oxlint, Oxfmt, or tsdown directly: Vite+ wraps these tools. They must not be installed directly. You cannot upgrade these tools by installing their latest versions. Always use Vite+ commands.
- Use Vite+ wrappers for one-off binaries: Use
vp dlxinstead of package-manager-specificdlx/npxcommands. - Import JavaScript modules from
vite-plus: Instead of importing fromviteorvitest, all modules should be imported from the project'svite-plusdependency. For example,import { defineConfig } from 'vite-plus';orimport { expect, test, vi } from 'vite-plus/test';. You must not installvitestto import test utilities. - Type-Aware Linting: There is no need to install
oxlint-tsgolint,vp lint --type-awareworks out of the box.
Supplementary project tools
Not part of vp check. Use vp run so installs stay routed through Vite+.
- Fallow (
vp run fallow) — unused files, dependencies, and exports. Use when trimming deps or refactoring entry points (.fallowrc.jsonconfigures the project). - react-doctor (
vp run doctor) — React-focused health checks. The script uses--no-lint; keep ordinary linting onvp lint.
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.
- 2d ago First seen · 25 lines · 593 tokens per session scan A 866557c304df
tanstack-start-start AGENTS.md is an instructions file published in the GitHub repository lightsound/tanstack-start-start (24 stars, last pushed 2mo ago), licensed MIT. It adds 593 tokens to every session, about $0.0030 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 instructions, from other repositories
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.