Borrowing it
Nothing to install: this file belongs to thaitop/tamaclaude. 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/thaitop/tamaclaude/main/CLAUDE.mdgit clone --depth 1 https://github.com/thaitop/tamaclaudeWrote 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/thaitop/tamaclaude/claude-md)<a href="https://agentmods.dev/instructions/thaitop/tamaclaude/claude-md"><img src="https://agentmods.dev/badge/instructions/thaitop/tamaclaude/claude-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 | $0.06350 | $0.06350 |
| Opus 5 | $0.03175 | $0.03175 |
| Sonnet 5 | $0.01270 | $0.01270 |
| Haiku 4.5 | $0.00635 | $0.00635 |
Grade B, and why
tamaclaude CLAUDE.md scanned grade B 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 7d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `TamaCore/{Hook,Statusline}Installer.swift` | writes into `~/.claude/settings.json` | How it starts
The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this is
A desk device that shows live Claude Code session status via a blocky orange Claude mascot, and uses the same screen for four more pages — weather, crypto, stocks, calendar — that the user swipes between or lets rotate on their own. Hardware: ESP32-2432S028R ("Cheap Yellow Display"), ILI9341 320x240 landscape, XPT2046 touch (horizontal swipes only), BLE first with a sealed LAN path behind it.
Where a reason goes
Every "why" has exactly one home. Walk this in order and stop at the first match — there is no fifth bucket, and a reason that fits none of them is a reason nobody needed written down:
- Can it sit beside the code it governs? → a Thai comment there. If it can, it must — and it must not be restated in any document. A document that retells the code is a copy that ages without anyone noticing. This is where nearly everything lands: a colour, a rect, a threshold, a framework quirk, a rejected alternative.
- Must it hold in two files at once that cannot reference each other at runtime? → the
invariants list below, plus a comment on each side naming its counterpart
(
gen/calendar.py↔ct_calendar_ui.cshow the shape). - Is it a decision that is hard to undo, with alternatives worth recording? → a new
docs/adr/. ADRs are dated records, not live rules: never edit one when the world changes, write the next one and say which it reverses. - Is it a term? →
CONTEXT.md. A value measured off the real board? →docs/hardware.md.
Read the code you are about to change — the reasons are in it, at the density the
surrounding file already uses. Ordinary fixes need no entry anywhere; git history is the log.
DESIGN.md was retired for failing all of this: it had no definition, so it only ever grew.
Do not recreate it under any name.
Data flow
Claude Code hooks --> tamaclaude --hook --> Unix socket --> daemon --> BLE GATT --> board
\ ^
'-> sealed TCP ---'
(only when BLE
is 10 s gone)
Open-Meteo --> WeatherService (every 15 min) --> page frame --> the same two paths
CoinGecko --> CryptoService (every 60 s) --> page frame --> the same two paths
Finnhub --> StocksService (every 60 s, only while the US market is open)
EventKit --> CalendarService (every 5 min, this Mac only — never the network)
Claude Code statusline --> ~/.tamaclaude/statusline.sh --.
>--> ~/.claude/.statusline-usage-cache
menu bar timer --> tamaclaude --usage-poll --> claude.ai --' |
daemon reads --> "u" key --> board
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.
- 7d ago First seen · 355 lines · 6,350 tokens per session scan B c8d48b3db9c9
tamaclaude CLAUDE.md is an instructions file published in the GitHub repository thaitop/tamaclaude (39 stars, last pushed 28d ago), licensed MIT. It adds 6,350 tokens to every session, about $0.0318 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
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.
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).
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.