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.
npx agentmods add instructions/cloveric/tarocub/claude-mdgit clone --depth 1 https://github.com/cloveric/tarocubWrote 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/cloveric/tarocub/claude-md)<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>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 | $0.01888 | $0.01888 |
| Opus 5 | $0.00944 | $0.00944 |
| Sonnet 5 | $0.00378 | $0.00378 |
| Haiku 4.5 | $0.00189 | $0.00189 |
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.
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.mddocs/telegram-instance-agent.mdwhen 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:
- Commit the intended changes without unrelated runtime state or secrets.
- Create or update the GitHub Release with accurate notes.
- 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:
- Run
./scripts/pre-complete-hook.sh(or.\scripts\pre-complete-hook.ps1on Windows) - If it fails, fix the failures
- If it passes but known parity/stability gaps remain, continue with the highest-value next task
- Only stop when:
- the current milestone is actually complete, or
- you hit a real blocker that cannot be resolved locally
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.
- 4d ago First seen · 139 lines · 1,888 tokens per session scan A e178a8ce1080
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.
Other instructions, from other repositories
solo AGENTS.md
AGENTS.md instructions for solo-agent/solo, covering project testing rules and project service lifecycle rules.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
Polaris AGENTS.md
AGENTS.md instructions for sponge-b0b/Polaris, covering agents.md, purpose and authority, domain vocabulary, coding conduct and secrets.
AI-System-Design-Consultant CLAUDE.md
Claude Code instructions for deepanshu2711/AI-System-Design-Consultant, covering claude.md, what this is, running it, load-bearing typos — do not "fix" these paths and agent node pattern.
agent-eve CLAUDE.md
Instructions for shehryarsaroya/agent-eve, covering claude.md — agent eve (né the compact, then agent transfer), 0. 🚨 hard rules, 1. what this is, 2. doc map and 3. state of play (2026-07-26).
team-shinchan AGENTS.md
Instructions for seokan-jeong/team-shinchan, covering agents.md - team-shinchan agent map, layer architecture, agent registry, call flow and quick reference.