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/mikececco/mastro/claude-mdgit clone --depth 1 https://github.com/mikececco/mastroWrote 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/mikececco/mastro/claude-md)<a href="https://agentmods.dev/instructions/mikececco/mastro/claude-md"><img src="https://agentmods.dev/badge/instructions/mikececco/mastro/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 | $0.01105 | $0.01105 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
mastro 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 5d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — istruzioni di progetto per Mastro
Questo file è il punto d'ingresso per chiunque lavori su Mastro, umano o agente. Contiene i vincoli che non cambiano da una sessione all'altra. Per il resto, i file linkati sono la fonte di verità — non duplicare qui il loro contenuto.
Cos'è Mastro
Copilota fiscale open-source (MIT) per l'Italia — regime forfettario (v1, verificato) ed
edizione SRL (v2, in costruzione) — plugin per Claude Code. Cita-o-rifiuta, calcolo
deterministico, nessun dato lasciato il dispositivo dell'utente. Dettagli: README.md.
Il vincolo che non si negozia: il confine legale
Mastro si posiziona fuori dal perimetro dell'esercizio abusivo della professione
(art. 348 c.p.) per struttura: gratuito, locale, anonimo, a sessioni isolate, nessun atto
riservato ai commercialisti. Questo non è marketing — è un vincolo di design verificato in
docs/posizionamento-legale.md e codificato in
knowledge/regole.md §8.
Prima di implementare qualunque funzionalità, controlla se introduce anche uno solo di questi quattro elementi — se sì, fermati e chiedi, non procedere autonomamente:
- Un pagamento legato a una risposta fiscale personalizzata.
- Un rapporto continuativo con un cliente identificato (account, storico, "presa in carico").
- Un atto riservato: firma, certificazione, asseverazione, deposito, trasmissione (SdI, F24, dichiarazioni), rappresentanza davanti ad AdE o Corti tributarie.
- Una conclusione vincolante al posto di una citazione + un calcolo (es. "sei idoneo").
Questo è anche il fondamento legale (non solo strategico) del "confine che non attraversiamo"
in docs/strategia-opensource.md §5: mai il ledger, mai la
trasmissione SdI/F24. Le due ragioni — posizionamento di mercato e diritto penale/professionale
— puntano nella stessa direzione, e nessuna delle due si aggira con un'interpretazione furba.
Direzione strategica
"Il cervello fiscale aperto, non il ledger" — intelligence layer + open rules layer, beachhead
SRL. Deciso il 2026-08-06, verificato con ricerca competitiva. Non ripetere la valutazione da
zero: leggi docs/strategia-opensource.md e
docs/landscape-2026-08.md prima di proporre un cambio di
direzione (es. "costruiamo il ledger", "diventiamo un intermediario SdI").
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.
- 5d ago First seen · 58 lines · 1,105 tokens per session scan A c504d43bf4f9
mastro CLAUDE.md is an instructions file published in the GitHub repository mikececco/mastro (4 stars, last pushed 25d ago), licensed MIT. It adds 1,105 tokens to every session, about $0.0055 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
authbox AGENTS.md
Instructions for MARUCIE/authbox, covering agents.md - ai 编程助手角色定义, 0 · 关于用户与你的角色, 1 · 总体推理与规划框架（全局规则）, 1.1 依赖关系与约束优先级 and 1.1.1 工作资产（强制）.
cukaimax-agent GEMINI.md
Gemini CLI instructions for jakzaizzat/cukaimax-agent: Use the cukaimax-tax-authority MCP server when the user asks about Malaysian individual income tax, Form BE, Form B, sole-proprietor records, deductible business expenses, tax reliefs, or HASiL source requirements.
legal-audit-de AGENTS.md
AGENTS.md instructions for FutureRootsDE/legal-audit-de, covering agents.md — legal-audit-de, haftungsausschluss — keine rechtsberatung, was macht das plugin?, plattform-layouts and commands / prompts.
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).
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.
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.