Borrowing it
Nothing to install: this file belongs to hybroai/hybro. 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/hybroai/hybro/main/AGENTS.mdgit clone --depth 1 https://github.com/hybroai/hybroWrote 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/hybroai/hybro/agents-md)<a href="https://agentmods.dev/instructions/hybroai/hybro/agents-md"><img src="https://agentmods.dev/badge/instructions/hybroai/hybro/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/hybroai/hybro/agents-md"><img src="https://agentmods.dev/badge/instructions/hybroai/hybro/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 | $0.02353 | $0.02353 |
| Opus 5.5 | $0.00941 | $0.00941 |
| Sonnet 5.5 | $0.00471 | $0.00471 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
hybro 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.
How it starts
The opening of the file, as written. The whole thing — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Rules
Conversational Style
- Keep answers short and concise.
- No emojis in commits, issues, PR comments, or code.
- Use direct technical prose without cheerful filler.
- Prefer clear, simple language. Define unavoidable jargon.
- Explain non-trivial work as: problem, concrete example or short trace, then solution. Distinguish required work from optional complexity.
- When the user asks a question, answer it before making edits or running implementation commands.
- When responding to feedback or analysis, explicitly say whether you agree or disagree before describing changes.
Repository Scope
These rules apply to the entire hybro repository. More specific rules in frontend/AGENTS.md and backend/AGENTS.md apply within those directories.
The product flow is:
frontend/ -> backend/ -> A2A agents, Hub relay, and external services
frontend/: Next.js 16, React 19, and TypeScript UI.backend/: Python 3.12 FastAPI platform backend.default_agents/: bundled A2A agents and their manifest.scripts/: thehybroCLI (POSIX shell), its tests, and the image, migration, and functional-test helpers.install.sh: installs the releasedhybroscript.Dockerfile: the single product image (UI, API, MCP, embedded MongoDB, and bundled agents behind Caddy on one port).
Do not inspect or treat paths outside this repository as product source unless the task explicitly requires it.
Code Quality
- Read files in full before wide-ranging changes, before editing files not yet fully inspected, and when asked to investigate or audit. Do not base broad changes on search snippets alone.
- Reuse existing services, repositories, adapters, components, hooks, stores, and UI primitives before adding abstractions.
- Keep changes focused on requested behavior. Do not refactor unrelated code opportunistically.
- Prefer the simplest design that satisfies the current requirements. Keep changes minimal and focused; do not add speculative abstractions, fallback paths, or compatibility layers.
- Add defensive handling at untrusted or failure-prone boundaries, such as user input, network calls, persistence, concurrency, and third-party APIs. Do not add redundant guards for states already excluded by validated internal contracts.
- Always ask before removing functionality or code that appears intentional.
- Do not add backward-compatibility layers unless required by an existing public contract or explicitly requested.
- Do not guess third-party APIs. Inspect installed package types, local framework documentation, or official upstream documentation.
- Avoid TypeScript
any; use it only when the boundary cannot be typed more precisely and document why. - Use typed, async-aware Python for I/O paths. Keep HTTP route adapters thin and business behavior in the existing domain/service layers.
- Add or update focused tests for behavior changes. Mock network, LLM, database, wallet, and webhook calls unless explicitly testing integration behavior.
- Treat explicitly marked generated regions as outputs. Update their source and regenerate them instead of editing them directly.
- For review-only requests, do not edit files.
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.
- 6d ago Changed · -3 lines · +142 tokens per session 6974052618b4
- 1mo ago Changed · +6 lines · +345 tokens per session 17a20e3b90e2
- 2mo ago Changed · +72 lines · +972 tokens per session de9065b45949
- 2mo ago First seen · 69 lines · 894 tokens per session scan A 7f1a5987d72e
hybro AGENTS.md is an instructions file published in the GitHub repository hybroai/hybro (18 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,353 tokens to every session, about $0.0094 per session on Opus 5.5. 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.
hybro AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hybro AGENTS.mdhybroai/hybro | Instructions file | 18 | 3d ago | Apache-2.0 | A | 2,353 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |