Borrowing it
Nothing to install: this file belongs to Fupete/design-system-italia-mcp. 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/Fupete/design-system-italia-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/Fupete/design-system-italia-mcpWrote 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/fupete/design-system-italia-mcp/claude-md)<a href="https://agentmods.dev/instructions/fupete/design-system-italia-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fupete/design-system-italia-mcp/claude-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.
<a href="https://agentmods.dev/instructions/fupete/design-system-italia-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/fupete/design-system-italia-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.09706 | $0.09706 |
| Opus 5 | $0.04853 | $0.04853 |
| Sonnet 5 | $0.01941 | $0.01941 |
| Haiku 4.5 | $0.00971 | $0.00971 |
Grade A, and why
design-system-italia-mcp 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 11d 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 — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — design-system-italia-mcp
Istruzioni e decisioni architetturali per Claude Code. Leggere prima di modificare il codice.
Contesto del progetto
Filo è un server MCP remoto non ufficiale che espone i dati del Design system .italia ad assistenti AI (Claude, Cursor, VS Code). Progetto personale sperimentale e non ufficiale a cura di Daniele Tabellini (Fupete).
Riferimento tecnico: italia/dati-semantic-mcp
Struttura
design-system-italia-mcp/
├── src/
│ ├── index.ts # Entry point — HTTP + stdio transport, /health, /cache/invalidate, ping
│ ├── cache.ts # In-memory cache — three TTL buckets: snapshot (24h) + snapshotDegraded (15min) + githubIssues (15min)
│ ├── constants.ts # URL e costanti condivise — SNAPSHOT_* + upstream + BETA_WARNING — unica source of truth
│ ├── fetch.ts # Shared fetch helpers (fetchJson, fetchText) per i loader
│ ├── schemas.ts # Zod output schemas per structuredContent — copertura parziale, vedi sotto
│ ├── slugify.ts # Normalizzazione slug + SLUG_ALIASES + slugsToTry()
│ ├── types.ts # Tipi TypeScript condivisi — ResolvedHop, TokenRole, DevKitEntry, UnionRow, ecc.
│ ├── utils.ts # Utility condivise (formatTimestamp)
│ ├── loaders/
│ │ ├── bsi.ts # Sorgenti #1 #2 #3 — markup, status, token BSI (da snapshot), classifyValue/matchSingleVarRef/containsVarRef, consolidateAmbiguous
│ │ ├── designers.ts # Sorgente #5 — JSON linee guida (da snapshot, no yaml a runtime)
│ │ ├── devkit.ts # Sorgenti #7 #8 #9 — index + stories + props Dev Kit (da snapshot)
│ │ ├── devkit-parser.ts # Parser argTypes/props da stories.ts — usato da snapshot-static.ts (CI) e come fallback runtime in devkit.ts
│ │ ├── github.ts # Sorgente #10 — GitHub Issues REST API (unica sorgente live)
│ │ ├── meta.ts # Sorgente #11 — versioni + componenti/foundations con URL verificati + DsMeta.ok (successo/fallimento fetch snapshot-meta.json, usato da health.ts)
│ │ └── tokens.ts # Sorgente #4 + #6 — bridge BSI→IT, DTI, resolveToken/findComponentsByToken/resolveTokenValues/searchDesignTokens, roleFor/hopFor, resolveComposite/findEmbeddedRefs (composedOf), resolveSingleValue (ambiguousValues)
│ └── tools/
│ ├── helpers.ts # buildMeta(), buildComponentUnion()/unionRows(), devKitUrlMismatch() — shared tool helpers
│ ├── dsi-list-components.ts # dsi_list_components — unione vera BSI ∪ Dev Kit
│ ├── dsi-search-components.ts # dsi_search_components — ricerca sulla stessa unione
│ ├── bsi-list-component-variants.ts # bsi_list_component_variants
│ ├── bsi-get-component-markup.ts # bsi_get_component_markup
│ ├── bsi-list-components-by-status.ts # bsi_list_components_by_status
│ ├── devkit-list-component-variants.ts # devkit_list_component_variants
│ ├── devkit-get-component-markup.ts # devkit_get_component_markup
│ ├── devkit-list-component-props.ts # devkit_list_component_props
│ ├── tokens-list-component-vars.ts # tokens_list_component_vars
│ ├── tokens-list-globals.ts # tokens_list_globals
│ ├── tokens-resolve.ts # tokens_resolve
│ ├── tokens-find-components.ts # tokens_find_components
│ ├── tokens-search.ts # tokens_search
│ ├── docs-get-component-guide.ts # docs_get_component_guide
│ ├── github-get-component-issues.ts # github_get_component_issues
│ └── github-get-project-repo-links.ts # github_get_project_repo_links
├── scripts/
│ ├── canary.ts # Canary runner — upstream health + snapshot freshness
│ ├── canary_config.ts # Config canary: UPSTREAM_HEALTH + SNAPSHOT_FRESHNESS
│ ├── snapshot-static.ts # CI: fetch sorgenti statiche + props DevKit → data-fetched/
│ ├── snapshot-devkit.ts # CI: Playwright → markup HTML da Storybook → data-fetched/devkit/stories/
│ ├── find-slug-mismatches.ts # Cross-source slug discovery
│ └── check-version.ts # Verifica allineamento package.json + publiccode.yml + tag
├── *_test.ts # node:test — cache, health, devkit-parser, helpers, tokens (pure functions: unionRows, roleFor/hopFor, normalizeTokenName, resolveChain)
├── .github/workflows/
│ ├── ci.yml # Typecheck + build su push/PR
│ ├── test.yml # Typecheck + npm run test su push/PR su main
│ ├── release.yml # Docker multiarch + npm publish su tag
│ ├── upstream-snapshot.yml # Weekly safety-net 04:00 UTC dom + workflow_dispatch → popola data-fetched
│ ├── version-check.yml # Nightly 03:00 UTC: controlla versioni npm/dsnav, triggera snapshot
│ └── upstream-canary.yml # Daily canary 07:00 UTC — apre issue su failure
├── Dockerfile
├── publiccode.yml
├── package.json # Version source of truth — letta da index.ts a runtime
└── tsconfig.json
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.
- 11d ago First seen · 624 lines · 9,706 tokens per session scan A 7c6eac9c6d81
design-system-italia-mcp CLAUDE.md is an instructions file published in the GitHub repository Fupete/design-system-italia-mcp (4 stars, last pushed yesterday), licensed BSD-3-Clause. It adds 9,706 tokens to every session, about $0.0485 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
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.
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).
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.
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).