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 skills add slimmanolesta/mcp-bdm --skill manolestagit clone --depth 1 https://github.com/slimmanolesta/mcp-bdmWrote 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/skills/slimmanolesta/mcp-bdm/manolesta)<a href="https://agentmods.dev/skills/slimmanolesta/mcp-bdm/manolesta"><img src="https://agentmods.dev/badge/skills/slimmanolesta/mcp-bdm/manolesta/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/skills/slimmanolesta/mcp-bdm/manolesta"><img src="https://agentmods.dev/badge/skills/slimmanolesta/mcp-bdm/manolesta.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 | $0.00302 | $0.03886 |
| Opus 5.5 | $0.00121 | $0.01554 |
| Sonnet 5.5 | $0.00060 | $0.00777 |
| Haiku 4.5 | $0.00030 | $0.00389 |
Grade A, and why
manolesta 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 2mo 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ricerca su Banca Dati di Merito (bdp.giustizia.it)
Recupera il testo integrale di provvedimenti di merito civile (Tribunali e Corti d'Appello, dal 1/1/2016, testo pseudonimizzato all'origine) dalla Banca Dati di Merito pubblica del Ministero. È lo step a valle del flusso di ricerca: spesso l'estremo è già stato individuato altrove e qui se ne recupera il testo ufficiale.
Gli strumenti
Il connettore espone questi tool. Usa i tool: non c'è bisogno di conoscere percorsi o cartelle d'installazione.
| Tool | A cosa serve |
|---|---|
bdm_check_session |
Verifica che la sessione BDM sia valida. |
bdm_estremi |
Ricerca per estremi (numero, anno, ufficio, tipo) — il caso principale. |
bdm_search |
Ricerca full-text a tema (testo libero, ufficio, materia). |
bdm_get_provvedimento |
Testo integrale per id; con cartella lo salva come .md. |
bdm_get_workflow |
Legge le preferenze di flusso dell'utente. |
bdm_set_workflow |
Salva le preferenze (fine dell'onboarding). |
Su Claude Code esiste anche una CLI equivalente (
bdm …) utile per il lavoro in blocco: vedi l'appendice in fondo. Ovunque sia disponibile un tool, preferisci il tool.
Cosa contiene (e cosa NO) la BDM — guardia di instradamento
La BDM ha solo il merito civile: Tribunali e Corti d'Appello. Prima di cercare, verifica che la richiesta ricada qui:
- Cassazione / Consiglio di Stato / TAR / Corte Cost. / CGUE-CEDU → NON su BDM. Se l'estremo è di legittimità/amministrativo/costituzionale, fermati e dillo: non è su BDM, va cercato su una banca dati di legittimità/amministrativa.
- Famiglia, minori, stato/capacità delle persone → esclusi dalla BDM. Segnalalo.
- In dubbio sull'organo, chiedi in una riga prima di partire.
Prerequisito: sessione valida (login CNS)
Il login è CNS (chiavetta + PIN) e lo fa sempre l'utente — non gestire mai credenziali, non tentare di fare login tu. La sessione dura ~2h.
Chiama bdm_check_session:
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.
- 2mo ago First seen · 235 lines · 302 tokens per session scan A 5d718b3ba107
manolesta is a skill published in the GitHub repository slimmanolesta/mcp-bdm (2 stars, last pushed 1mo ago), licensed MIT. It adds 302 tokens to every session and 3,886 once invoked, about $0.0012 per session on Opus 5.5. 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.
manolesta compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| manolestaslimmanolesta/mcp-bdm | Skill | 2 | 1mo ago | MIT | A | 302 | Claude Code, Codex |
| fto-triageanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 81 | Claude Code |
| legal-holdanthropics/claude-for-legal | Skill | 9.9k | 3d ago | Apache-2.0 | A | 68 | Claude Code |
| specification-writingwanshuiyin/Auto-claude-code-research-in-sleep | Skill | 19k | 3d ago | MIT | A | 49 | Claude Code |
| terms-of-servicegenspark-ai/genoffice | Skill | 12k | 2d ago | Apache-2.0 | A | 32 | Claude Code, Codex |
| x-scorecardx-cmd/x-cmd | Skill | 4.7k | 7d ago | Apache-2.0 | A | 57 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |