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/jezweb/vite-flare-starter/agents-mdgit clone --depth 1 https://github.com/jezweb/vite-flare-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/jezweb/vite-flare-starter/agents-md)<a href="https://agentmods.dev/instructions/jezweb/vite-flare-starter/agents-md"><img src="https://agentmods.dev/badge/instructions/jezweb/vite-flare-starter/agents-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 5.1 | $0.00657 | $0.00657 |
| Opus 5 | $0.00329 | $0.00329 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
vite-flare-starter 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 5d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vite Flare Starter — agent guide
Pattern library + production starter for Cloudflare Workers apps.
React 19 + Vite, Hono, D1 (Drizzle), R2, better-auth, AI SDK v6 with
the Cloudflare agents SDK. Modules are reference implementations —
read the closest existing module before building a new one, and disable
unwanted modules with VITE_FEATURE_* flags instead of deleting them.
This file is deliberately compact.
CLAUDE.mdis the canonical deep context (module map, AI stack, auth model) and stays current — read it next. This file only carries what every coding agent needs on turn one.
Commands
pnpm dev # dev server (Docker must run — sandbox container builds)
pnpm build # production build
pnpm run deploy # build + deploy (NEVER bare `wrangler deploy` — stale dist)
pnpm test # unit tests (Vitest, Workers pool)
pnpm test:e2e # Playwright killer flows (against live deploy)
pnpm type-check # tsc --noEmit
pnpm db:generate:named "x" # create migration
pnpm db:migrate:local # apply migrations locally
pnpm db:migrate:remote # apply migrations to production
pnpm doctor:auth # diagnose better-auth setup issues
pnpm doctor:models # check Workers AI model ids against live catalogue
Conventions that bite if missed
- Design tokens only — semantic classes (
bg-background,border-hairline), never raw palette classes or.dark {}overrides. See DESIGN.md. - Tenancy: scope reads AND write-guards with
scopeUser()(src/server/lib/tenancy.ts); polymorphic lookups go throughcanAccessEntity(). R2 keys gate onisOwnedR2Key(). - New agent tools follow the one-file
ToolDefinitioncontract (.claude/rules/one-file-tool-definitions.md) — server execute + client render metadata in one object. - New DO/agent classes must declare an
AGENT_ACCESS_POLICYentry insrc/server/index.ts(fail-closed) and be exported for wrangler. - shadcn components are Base UI (
renderprop, notasChild); icons are Phosphor; charts are Kumo ECharts.
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.
- 5d ago First seen · 54 lines · 657 tokens per session scan A 3c6c17c88483
vite-flare-starter AGENTS.md is an instructions file published in the GitHub repository jezweb/vite-flare-starter (48 stars, last pushed 10d ago), licensed MIT. It adds 657 tokens to every session, about $0.0033 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
PowerPlatform-PowerPagesSPA
Instructions for tchinnin/powerplatform-vibecoding-samples, covering power pages spa development guide, important notes, 1. prerequisites, verify pac cli authentication and 2. create power pages spa project.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
awsmux AGENTS.md
Instructions for 0hardik1/awsmux, covering agents.md, what awsmux is, build, test, verify, layout and the safety model — invariants you must not weaken.
pip-web CLAUDE.md
Claude Code instructions for playpip/pip-web, covering claude.md — agent guide for pip, read first (by task), the three layers (respect the boundaries), non-negotiables and commands / definition of done.
plan-forge naming.instructions.md
Azure naming conventions — Microsoft CAF abbreviations, constraints, uniqueness, tagging.
agent-skills fortrabbit.instructions.md
Instructions for fortrabbit/agent-skills, covering fortrabbit — github copilot instructions, what fortrabbit is, configuration lookup, available operations and mcp server (optional).