What is TokenGochi AGENTS.md?

A repository guide for TokenGochi, a virtual pet that runs on an M5Stack watch and responds to local Claude Code and Codex token use. It covers the watch firmware, backend, setup, current work, and known limits.

Use it when working on TokenGochi’s firmware, local bridge, backend, device setup, PlatformIO commands, or deployment. It also points agents to project status and verification requirements.

It gives coding agents the project context and operating rules they need before changing hardware, backend, deployment, or secrets. This reduces assumptions and keeps unrelated parts from being changed together.

How hugo-alves/TokenGochi configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to hugo-alves/TokenGochi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/hugo-alves/TokenGochi/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/hugo-alves/TokenGochi

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hugo-alves/tokengochi/agents-md/github.svg)](https://agentmods.dev/instructions/hugo-alves/tokengochi/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/hugo-alves/tokengochi/agents-md"><img src="https://agentmods.dev/badge/instructions/hugo-alves/tokengochi/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hugo-alves/tokengochi/agents-md"><img src="https://agentmods.dev/badge/instructions/hugo-alves/tokengochi/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,842 This file is loaded in full into every session.

When invoked 1,842 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01842	$0.01842
Opus 5	$0.00921	$0.00921
Sonnet 5	$0.00368	$0.00368
Haiku 4.5	$0.00184	$0.00184

Measured 9d ago against content hash 481721f6b672, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

TokenGochi AGENTS.md scanned grade A 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl http://localhost:8787/health

AGENTS.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Guide: TokenGochi

This repo is a hardware plus backend project for a virtual pet that lives on an M5Stack StopWatch Dev Kit and reacts to local Claude Code / Codex token usage. Treat it as production-bound hardware work: verify before changing, keep edits small, and never mix firmware, backend, deployment, and secret changes unless the user explicitly asks for that scope.

Repository Context

Work from the repository root; do not assume a machine-specific absolute path.
The default branch is main.
Use ./tools/pio for PlatformIO commands. It runs PlatformIO through uv with Python 3.12, avoiding host pio wrappers pinned to unsupported Python versions.

Status from STATUS.md is useful project context but should be re-verified before making claims about a live device, deployment, or account.

What This Project Is

TokenGochi has three runtime surfaces:

firmware/: PlatformIO Arduino firmware for the M5Stack StopWatch Dev Kit. It renders the pet on the round AMOLED, records audio from the watch mic, posts WAV audio to the backend, and polls pet state.
bridge/: zero-dependency Node 18+ local bridge. It reads local Claude Code and Codex logs, derives token totals and pet state, and can proxy audio to Groq Whisper.
cloudflare/: Cloudflare Worker plus D1 backend for public HTTPS access. The watch can talk to the Worker while the Mac publishes token totals outbound using bridge/token-ingest.mjs.

The product goal is a physical token-fed pet: it gets mood/state from usage, shows stats on the watch, and can transcribe short voice interactions.

Hardware And Host Setup

Device: M5Stack StopWatch Dev Kit C152.
MCU: ESP32-S3R8, 16 MB flash, 8 MB PSRAM.
Display: 1.75 inch round AMOLED, 466x466, modeled as radius 233 centered at (233, 233).
Controls: KEYA on G2, KEYB on G1, plus power/reset.
Audio: MEMS mic and speaker through the M5Unified/M5GFX stack.
WiFi: 2.4 GHz only. Captive portals are not supported by the firmware.
Development host: macOS for StopWatch flashing and launchd integration; Linux is supported for the optional VPS token source.

Read the full file on GitHub · 222 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.

9d ago First seen · 222 lines · 1,842 tokens per session scan A 481721f6b672

Subscribe to this mod's changes

TokenGochi AGENTS.md is an instructions file published in the GitHub repository hugo-alves/TokenGochi (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,842 tokens to every session, about $0.0092 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Claude Code Hardware and IoT cloudflare-workers codex-cli esp32 m5stack platformio

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.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

TokenGochi: Instructions file for Codex