agentmods.dev

petdex AGENTS.md

petdex AGENTS.md is an instructions file for Codex, OpenCode from crafter-station/petdex. It costs 1,180 tokens per session, scanned A, original, MIT.

Development notes for Petdex, an application with a web app, database, cache, command-line package, and Discord bot. They document its tools, environment requirements, commands, and package boundaries.

In plain words
What is it for?
Installing dependencies with Bun, starting local services, running checks and tests, building the app, and updating translations.
Why use it?
They help agents use the expected runtime and avoid confusing separate packages or running checks without required configuration.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions Codex.

not rated 4.0k +18 5d ago A scan 1,180 tokens original MIT
View the source file crafter-station/petdex petdex.dev
About the project

Petdex is a gallery, installer, and desktop application for animated pets that accompany coding agents. People browse and submit pets through its website, install them with a command-line tool, and use the desktop app to display reactions to agent activity. The catalogue includes skills and instructions for creating or using these pets with supported coding agents.

crafter-station/petdex · 4,039 stars · on GitHub · petdex.dev

Install

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.

agentmods
npx agentmods add instructions/crafter-station/petdex/agents-md
Clone the repo
git clone --depth 1 https://github.com/crafter-station/petdex

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for petdex AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/crafter-station/petdex/agents-md.svg)](https://agentmods.dev/instructions/crafter-station/petdex/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/crafter-station/petdex/agents-md"><img src="https://agentmods.dev/badge/instructions/crafter-station/petdex/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,180 This file is loaded in full into every session.
When invoked 1,180 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01180 $0.01180
Opus 5 $0.00590 $0.00590
Sonnet 5 $0.00236 $0.00236
Haiku 4.5 $0.00118 $0.00118

Measured 6d ago against content hash 193414bcc5da, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

petdex 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 6d 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.

AGENTS.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Petdex Agent Notes

Commands

  • Use Bun for repo work: bun install, not npm install. Published CLI docs mention npm/npx for end users only.
  • Recommended local app dev is bun run dev:docker; it boots local Postgres and Redis with shared Clerk dev defaults from .env.dev.
  • Maintainer dev is bun dev with .env.local copied from .env.example; this path expects Clerk, Postgres/Neon, R2, Upstash, Resend, OpenAI, and ElevenLabs credentials.
  • bun run dev:mock is deprecated and intentionally exits. Keep .env.mock only for targeted mock-backed tests or build checks.
  • Root checks: bun run check for Biome, bun run format to write Biome fixes, bun run build for the Next app, bun test for Bun tests, and bun run i18n:check after editing translation messages. There is no root typecheck script.
  • Focused tests use bun test path/to/file.test.ts. Tests that import src/lib/db/client.ts directly or indirectly, including src/lib/pet-search.test.ts and src/lib/security.test.ts, need a usable DATABASE_URL or mock env: bun test --env-file=.env.mock src/lib/security.test.ts.
  • packages/petdex-cli and packages/discord-bot are independent packages, not root workspaces; run their own bun install and package scripts from inside each directory. Root tsconfig.json excludes packages.
  • CLI package verification, run from packages/petdex-cli, is bun run build && bun run typecheck; the build emits ignored dist/petdex.js and prepends the node shebang in postbuild.
  • Discord bot work stays in packages/discord-bot; use bun run register, bun run dev, or bun run start there with env from packages/discord-bot/.env.example.

Architecture

  • Main app routes live in src/app/[locale]; API routes live in src/app/api; shared server/domain code lives in src/lib; DB schema is src/lib/db/schema.ts with SQL migrations in drizzle/.
  • This is Next 16.2.4 with newer conventions: src/proxy.ts is the middleware/proxy entrypoint, route/layout params are promises, and src/app/layout.tsx intentionally returns children while [locale]/layout.tsx owns <html>/<body> for locale lang. If touching framework APIs, prefer the installed Next docs under node_modules/next/dist/docs/ over older assumptions.
  • i18n locales are en, es, and zh; message files are under src/i18n/messages/, and next-intl is wired through src/i18n/request.ts plus the locale layout.
  • Mock DB bootstrap tolerates migration/schema drift via fixups in src/lib/mock/db.ts; if schema fields are added and mock pages fail, update those fixups until a real migration lands.
  • drizzle.config.ts hard-fails without DATABASE_URL; there are no root package scripts for migration generation or application, and many scripts/apply-* / backfill-* files are real-DB one-offs.
  • Automated review/tag/sound paths use AI SDK model strings through Vercel AI Gateway (AI_GATEWAY_API_KEY in .env.example); avoid adding raw OpenAI client wiring to server paths.

Read the full file on GitHub · 30 lines

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.

  1. 6d ago First seen · 30 lines · 1,180 tokens per session scan A 193414bcc5da

Subscribe to this mod's changes

petdex AGENTS.md is an instructions file published in the GitHub repository crafter-station/petdex (4,039 stars, last pushed 5d ago), licensed MIT. It adds 1,180 tokens to every session, about $0.0059 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.

claude-codeclerkclicodexdeveloper-toolsdrizzle-orm
Related

Other instructions, from other repositories

supermemory CLAUDE.md

Claude Code instructions for supermemoryai/supermemory, covering claude.md, repository structure, applications (apps/), development commands and root level (monorepo).

supermemoryai/supermemory · 884 tokens

create-better-t-stack AGENTS.md

AGENTS.md instructions for AmanVarshney01/create-better-t-stack, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and error handling conventions.

AmanVarshney01/create-better-t-stack · 938 tokens

Better-Fullstack AGENTS.md

AGENTS.md instructions for Marve10s/Better-Fullstack, covering guidelines, web ui, workflow and bun.

Marve10s/Better-Fullstack · 1,062 tokens

better-drizzle AGENTS.md

AGENTS.md instructions for almeidazs/better-drizzle, covering better-drizzle repository – agent field notes, architecture, design intent, api surface and performance rules.

almeidazs/better-drizzle · 5,413 tokens

kan AGENTS.md

AGENTS.md instructions for kanbn/kan, covering agents.md, project overview, setup commands, project structure and code style.

kanbn/kan · 2,672 tokens

flarestarter AGENTS.md

Instructions for FlareStarter/flarestarter, covering agents.md, what this is, structure, conventions and commands.

FlareStarter/flarestarter · 693 tokens