Borrowing it
Nothing to install: this file belongs to hoangsonww/PetSwipe-Match-App. 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/hoangsonww/PetSwipe-Match-App/master/AGENTS.mdgit clone --depth 1 https://github.com/hoangsonww/PetSwipe-Match-AppWrote 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/hoangsonww/petswipe-match-app/agents-md)<a href="https://agentmods.dev/instructions/hoangsonww/petswipe-match-app/agents-md"><img src="https://agentmods.dev/badge/instructions/hoangsonww/petswipe-match-app/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 | $0.03567 | $0.03567 |
| Opus 5 | $0.01784 | $0.01784 |
| Sonnet 5 | $0.00713 | $0.00713 |
| Haiku 4.5 | $0.00357 | $0.00357 |
Grade C, and why
PetSwipe-Match-App AGENTS.md scanned grade C with 1 finding 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
2. **No destructive git commands**: `git reset --hard`, `git clean -fd`, `rm -rf`, `git push --force` are forbidden unless the human explicitly requests them. How it starts
The opening of the file, as written. The whole thing — 320 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md -- PetSwipe Flywheel Operating Manual
Single source of truth for every AI coding agent working on the PetSwipe project. Read this file at session start and after every context compaction.
Rule 0: Override Prerogative
The human operator's instructions override everything in this file. If a human tells you to do something that contradicts a rule below, follow the human.
Rule 1: Core Safety Rules
- Never delete files without explicit human permission.
- No destructive git commands:
git reset --hard,git clean -fd,rm -rf,git push --forceare forbidden unless the human explicitly requests them. - All work happens on the main branch unless the human instructs otherwise.
- No script-based code changes: always edit files manually through your editor tools. Do not generate and execute sed/awk/perl one-liners to modify source code.
- No file proliferation: do not create
mainV2.ts,app-backup.ts, or similar variants. Edit in place. - Compiler and lint checks after every change: run the appropriate validation command (see Validation Guidance below) before declaring work complete.
- Multi-agent awareness: never stash, revert, or overwrite changes made by other agents. Treat other agents' uncommitted and committed work as your own. If you encounter a merge conflict, stop and notify the human.
Project Overview
PetSwipe is a full-stack pet adoption platform. Users browse adoptable pets via a swipe interface, match with pets they like, and connect with shelters. The codebase spans a Next.js frontend, an Express API backend, Kubernetes manifests, Terraform IaC, and operational scripts.
Repo Map
| Path | Purpose |
|---|---|
frontend/pages/ |
Next.js Pages Router -- main UI routes and API routes |
frontend/components/ |
Shared layout, Navbar, chart wrapper, shadcn UI primitives |
frontend/components/ui/ |
46 shadcn/Radix UI primitives (button, card, dialog, form, table, etc.) |
backend/src/routes/ |
Express route definitions: auth, chat, matches, pets, swipes, users |
backend/src/controllers/ |
Request handlers: authController, chatController, matchController, petController, swipeController, userController |
backend/src/services/ |
Business logic: geocodeService, imageService, userService |
backend/src/entities/ |
TypeORM entities: Pet, User (AppUser), Match, Swipe |
backend/src/middlewares/ |
auth.ts (JWT verification), errorHandler.ts |
backend/src/app.ts |
Express app setup, route mounting, Swagger, health endpoints |
k8s/base/ |
Default Kubernetes stack |
k8s/overlays/production/ |
Production Kustomize overlay |
terraform/ |
AWS-oriented IaC + optional Vault/Consul/Nomad modules |
scripts/ |
Deployment and operations scripts |
mcp_server/ |
MCP (Model Context Protocol) server for AI-assisted features |
docs/ |
DEPLOYMENT.md, DEVOPS_GUIDE.md, and other operator docs |
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.
- 8d ago First seen · 320 lines · 3,567 tokens per session scan C 7e61c19c5e58
PetSwipe-Match-App AGENTS.md is an instructions file published in the GitHub repository hoangsonww/PetSwipe-Match-App (24 stars, last pushed 23d ago), licensed MIT. It adds 3,567 tokens to every session, about $0.0178 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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).
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.
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.