tarocub CLAUDE.md

tarocub CLAUDE.md is an instructions file for coding agents from cloveric/tarocub. It costs 1,888 tokens per session, scanned A, original, MIT.

A set of project instructions for TaroCub, a local control tool for several coding agents operated through Telegram and Feishu/Lark. It defines what to read before changes and what must be checked before a release.

In plain words
What is it for?
Use it when changing Telegram, Feishu/Lark, message-bus, state, configuration, usage, budget, audit, or file-delivery behavior, and when preparing a release.
Why use it?
It prevents changes from being made in the wrong project area and prevents an incomplete implementation from being treated as finished. It also sets rules for keeping platform instructions and release work consistent.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/cloveric/tarocub/claude-md
Clone the repo
git clone --depth 1 https://github.com/cloveric/tarocub

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.

agentmods badge for tarocub CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/cloveric/tarocub/claude-md.svg)](https://agentmods.dev/instructions/cloveric/tarocub/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/cloveric/tarocub/claude-md"><img src="https://agentmods.dev/badge/instructions/cloveric/tarocub/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,888 This file is loaded in full into every session.
When invoked 1,888 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01888 $0.01888
Opus 5 $0.00944 $0.00944
Sonnet 5 $0.00378 $0.00378
Haiku 4.5 $0.00189 $0.00189

Measured 4d ago against content hash e178a8ce1080, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tarocub CLAUDE.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.

CLAUDE.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TaroCub Instructions

Read First

Before modifying Telegram flow, Feishu/Lark flow, bus flow, state/config handling, usage/budget/audit logic, or file delivery, read:

  • docs/entrypoint-map.md
  • docs/telegram-instance-agent.md when changing static Telegram transport instructions

That file is the source of truth for codebase navigation and test selection.

Static Telegram transport rules belong in instance-level ~/.cctb/<instance>/agent.md, not in resumed project AGENTS.md or CLAUDE.md. If those rules change, update docs/telegram-instance-agent.md and sync affected instance agent.md files.

Mission

This repository is not in maintenance mode. The active objective is:

make TaroCub a reliable local control surface for Codex, Claude Code, Kimi Code, and Antigravity across Telegram and Feishu/Lark, keeping parity where possible and using each platform's native strengths where it is better

Do not treat "feature implemented" as "work complete" unless the current milestone has been verified end-to-end.

Release Rule

When the operator says "commit and release", do not stop at a commit, tag, or GitHub Release. A complete TaroCub release requires:

  1. Commit the intended changes without unrelated runtime state or secrets.
  2. Create or update the GitHub Release with accurate notes.
  3. Restart and verify the Telegram and Lark fleet.

Do not include external package-registry publishing in the release flow. For Lark fleet restarts, use node dist/src/index.js lark service restart --all; do not hand-roll per-instance restart loops.

Persistence Rule

When you feel the urge to stop, summarize, or hand back partially-finished work:

  1. Run ./scripts/pre-complete-hook.sh (or .\scripts\pre-complete-hook.ps1 on Windows)
  2. If it fails, fix the failures
  3. If it passes but known parity/stability gaps remain, continue with the highest-value next task
  4. Only stop when:
    • the current milestone is actually complete, or
    • you hit a real blocker that cannot be resolved locally

Read the full file on GitHub · 139 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.

  1. 4d ago First seen · 139 lines · 1,888 tokens per session scan A e178a8ce1080

Subscribe to this mod's changes

tarocub CLAUDE.md is an instructions file published in the GitHub repository cloveric/tarocub (4 stars, last pushed 4d ago), licensed MIT. It adds 1,888 tokens to every session, about $0.0094 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 2026-08-31.