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/alvinunreal/openpets/agents-mdgit clone --depth 1 https://github.com/alvinunreal/openpetsWrote 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/alvinunreal/openpets/agents-md)<a href="https://agentmods.dev/instructions/alvinunreal/openpets/agents-md"><img src="https://agentmods.dev/badge/instructions/alvinunreal/openpets/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 | $0.02089 | $0.02089 |
| Opus 5 | $0.01045 | $0.01045 |
| Sonnet 5 | $0.00418 | $0.00418 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
openpets 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 4d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Map
A full codemap is available at codemap.md in the project root.
Before working on any task, read codemap.md to understand:
- Project architecture and entry points
- Directory responsibilities and design patterns
- Data flow and integration points between modules
For deep work on a specific folder, also read that folder's codemap.md.
Documentation Map
docs/ holds the maintained, conceptual documentation — the narrative layer on
top of the codemaps. It explains concepts and contracts and points at the files
that own each behavior (it deliberately avoids pasting code, which rots). Start
at docs/README.md, then read the doc for the area you're touching:
docs/architecture.md— system overview, runtime topology, package spine, end-to-end flows, cross-cutting invariants, glossary. Read first.docs/desktop.md— the Electron app: process model, tray/Control Center, windows, app state, lifecycle, security, logging, CSP.docs/ipc.md— local IPC protocol +@open-pets/client: discovery, transports, the lease model, request surface, security.docs/pets.md— pet model, reactions→animations→speech, installation, Codex pets, motion.docs/catalog.md— pet/plugin catalog contracts (v3/v2), pagination, search, R2 ZIP hosting, and how the app consumes them.docs/agent-integrations.md— Claude/MCP/OpenCode/Cursor/Pi + the CLI.docs/plugins.md— plugin platform: manifest, permissions, runtime, sandbox, install paths, packaging/publishing, troubleshooting.docs/official-plugins.md— companion-first direction, official lineup, bundling/enabled defaults, right-click action strategy.docs/sdk.md— public SDK v3 contract + the deterministic test harness.docs/i18n.md— translations across host UI, reaction speech, and plugins.docs/development.md— DX: layout, command surface, dev modes, releases.docs/testing-and-validation.md— tests, contracts, release validators, catalog verification, and what "production-valid" means before shipping.
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.
- 4d ago First seen · 148 lines · 2,089 tokens per session scan A 8e24daa7eacf
openpets AGENTS.md is an instructions file published in the GitHub repository alvinunreal/openpets (1,149 stars, last pushed 5d ago), licensed MIT. It adds 2,089 tokens to every session, about $0.0104 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
the-polyglot-protocol AGENTS.md
AGENTS.md instructions for sabir-gbs/the-polyglot-protocol: Read SKILL.md first. Then follow docs/workflow/dev-workflow.md, docs/language-guidelines.md, and the relevant language file under docs/languages/.
plannotator AGENTS.md
AGENTS.md instructions for backnotprop/plannotator, covering plannotator, project structure, server runtimes, installation and environment variables.
solo AGENTS.md
AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
ephemeral-sandbox CLAUDE.md
Instructions for Ephemeral-AI-Lab/ephemeral-sandbox, covering claude.md, project, engineering practice (required), build & test and sandbox tools.
superset CLAUDE.md
Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.