Borrowing it
Nothing to install: this file belongs to marcelomartins/bun-hono-vue-cloudflare. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/marcelomartins/bun-hono-vue-cloudflare/main/AGENTS.mdgit clone --depth 1 https://github.com/marcelomartins/bun-hono-vue-cloudflareWrote 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/marcelomartins/bun-hono-vue-cloudflare/agents-md)<a href="https://agentmods.dev/instructions/marcelomartins/bun-hono-vue-cloudflare/agents-md"><img src="https://agentmods.dev/badge/instructions/marcelomartins/bun-hono-vue-cloudflare/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/marcelomartins/bun-hono-vue-cloudflare/agents-md"><img src="https://agentmods.dev/badge/instructions/marcelomartins/bun-hono-vue-cloudflare/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01032 | $0.01032 |
| Opus 5 | $0.00516 | $0.00516 |
| Sonnet 5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
bun-hono-vue-cloudflare 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 10d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Instructions
- Act as a Senior Full-Stack Software Engineer with experience in TypeScript, Bun, Hono, Cloudflare Workers, D1, Vue 3, and web application security.
- IMPORTANT: Critically evaluate all prompts, requirements, and proposed solutions. If anything is incomplete, incorrect, insecure, inconsistent with the existing architecture, unnecessarily complex, or otherwise open to improvement, you MUST raise the concern, clearly explain the issue, and propose the most appropriate alternative before implementing it.
- Only do what is explicitly requested. Do not create features that were not requested.
- Only add comments when they explain decisions, risks, or non-obvious invariants; comments that merely describe the code are not necessary.
- There should be no unnecessary or unused code, and no unused files.
- Do not create documentation files unless they are clearly requested.
- Do not use Git to commit changes. Git may only be used to view or inspect changes.
- If
scripts/init.tsstill exists, this project has not been initialized yet: followSETUP.mdbefore any other work. - Read
README.mdfor the stack, the architecture, the routing model, and the API surface before changing code.
Architecture Invariants
- Keep
wrangler.jsoncat the repository root and the Worker entrypoint atworker-api/src/index.ts. - Derive every routing decision from the route registry in
worker-shared/contracts/src/router/routes.ts; never duplicate route lists. - Never pre-render a protected page, never serve the SPA shell before the Worker has checked the session, and keep
/index-spa*returning 404 to direct browser requests. - Keep the
__Host-prefix,HttpOnly,Secure,Path=/, andSameSite=Laxon the session cookie. - Revocation is deliberate and must not be weakened: logout increments
session_versionand invalidates every token of that user on every device; a password change does the same and reissues a token for the current session only. - Keep the optional integrations optional: disabled by default, validated by
assertRuntimeConfigurationonly when enabled, failing closed once enabled, and never required by a default flow. - Validate the host and the
Originheader in the Worker (validateHostAndOrigin) on every mutation. Frontend controls never replace authorization or validation in the Worker. - Keep
assertRuntimeConfigurationrejecting missing or inconsistentENVIRONMENT,SESSION_SECRET,APP_HOST, andAPP_ORIGIN. Absence of secrets must never enable permissive fallbacks. - Use D1 prepared statements with
.bind()for all external values. Never build SQL by concatenation. - Never accept numeric database ids from clients; the UUID v7
uuidcolumn is the only public identifier. - Read external bodies through
readJsonwith the shared Zod schemas, neverrequest.json()directly. - Keep API error codes stable and in English; user-facing messages belong in the frontend i18n map.
- Do not log request/response bodies, passwords, tokens, cookies, codes, or raw email addresses. Use
structuredLogwith non-sensitive diagnostic fields andsanitizedRequestPath. - Keep everything in English: technical names, code, tests, logs, documentation, and visible application text. Never hardcode a locale.
- Use Bun for package management, scripts, and unit tests. Do not switch the package manager or generate another lockfile.
- Prefer Web and Workers APIs. Node.js compatibility is enabled, but Node-specific APIs require a concrete need.
- Do not add browser dependencies casually:
check-client-buildenforces the forbidden-dependency list and the client JavaScript budget. - Treat existing migrations as applied. Schema changes require a new additive migration, unless the user explicitly confirms the database can be recreated.
- Do not put secrets in
wrangler.jsonc, code, or committed files. - Declare every optional binding in
worker-api/vitest.config.tsso integration tests never depend on the developer's.dev.vars. - Keep the Worker CSP in
http/middleware.tsaligned with the static CSP inweb-vue/static/_headers; they cover different responses of the same site. scripts/init.tsholds the identifiers it rewrites, so it must keep excluding itself from the walk. Update it whenever a new starter identifier is introduced.- Do not add remote bindings, deploy, use remote D1, set secrets, or change DNS without explicit authorization.
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.
- 10d ago First seen · 46 lines · 1,032 tokens per session scan A a2cd33176cc4
bun-hono-vue-cloudflare AGENTS.md is an instructions file published in the GitHub repository marcelomartins/bun-hono-vue-cloudflare (10 stars, last pushed 3d ago), licensed MIT. It adds 1,032 tokens to every session, about $0.0052 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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 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).
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.