Borrowing it
Nothing to install: this file belongs to pollen-robotics/reachy_mini_conversation_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/pollen-robotics/reachy_mini_conversation_app/main/AGENTS.mdgit clone --depth 1 https://github.com/pollen-robotics/reachy_mini_conversation_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/pollen-robotics/reachy_mini_conversation_app/agents-md)<a href="https://agentmods.dev/instructions/pollen-robotics/reachy_mini_conversation_app/agents-md"><img src="https://agentmods.dev/badge/instructions/pollen-robotics/reachy_mini_conversation_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 | $0.02702 | $0.02702 |
| Opus 5 | $0.01351 | $0.01351 |
| Sonnet 5 | $0.00540 | $0.00540 |
| Haiku 4.5 | $0.00270 | $0.00270 |
Grade A, and why
reachy_mini_conversation_app 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 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.
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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents (and the humans driving them) working in this repository.
Read this before writing code. It is not optional, and it does not replace CONTRIBUTING.md. It enforces it.
This repository is an application built on the Reachy Mini SDK (reachy_mini), not a standalone system. Changes must stay compatible with it (see Engineering excellence).
This is a small project maintained by a small team. Low-quality, auto-generated, unreviewed changes cost us real time. Follow the rules below or stop.
Read this first
- Read before you write. Match the existing structure, naming, and patterns of the module you touch.
- Don't touch
.github/pull_request_template.md,CONTRIBUTING.md,CODE_OF_CONDUCT.md, or CI workflows, unless that is the task. - Minimal diff. One PR = one fix/feature. Prefer deleting code to adding it.
- No dead code, no LLM verbosity in code, comments, or PR text.
- Errors are logged, never swallowed. Use
logger, notprint. - Run the full gate before review. Don't waste a reviewer's time, and never open a PR with a red pipeline.
Everything below expands these.
Engineering excellence
The bar we hold, and the why behind the rules:
- Built on the Reachy Mini SDK. This app runs on top of
reachy_mini(declared inpyproject.toml, locked inuv.lock, installed alongside it). Build on the SDK's public API. Don't fork, vendor, or monkey-patch its internals, and keep the app working when the SDK version bumps. - Design before code. Think non-trivial changes through and state the trade-offs. The realtime conversation loop lives in
huggingface_realtime.py; keep shared behaviour there. - Graceful degradation. A tool returns
{"error": ...}rather than crashing the conversation loop. - Tests cover essential behavior, not every line.
- The CI gate is the floor, not the ceiling. Never degrade quality to land faster.
- Reuse over duplication. No copy-paste, no single-use helpers, no secrets in code.
- Build for the merged project, not the PR. A PR is temporary. Once it lands, its context is gone, so write features and comments that read as a natural part of the whole codebase, never as a diff.
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 · 150 lines · 2,702 tokens per session scan A 921609fc9a8b
reachy_mini_conversation_app AGENTS.md is an instructions file published in the GitHub repository pollen-robotics/reachy_mini_conversation_app (304 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,702 tokens to every session, about $0.0135 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
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.