What is dataroom-prep?

A tool for organising a large set of business documents into a structured M&A data room. An M&A data room is a controlled document collection used during a company sale or investment review.

Use it to classify and organise files, detect exact duplicates and obsolete versions, rename documents, build request checklists, and enrich missing-document checks with company and legal, tax, or accounting context.

It reduces manual sorting and helps identify duplicate, outdated, missing, and incorrectly named documents before they are uploaded for review.

dataroom-prep — Skill for Claude Code and Codex by Hectelion-SA

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.

Any agent

npx skills add Hectelion-SA/claude-dataroom-prep --skill skill

Clone the repo

git clone --depth 1 https://github.com/Hectelion-SA/claude-dataroom-prep

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/hectelion-sa/claude-dataroom-prep/skill/github.svg)](https://agentmods.dev/skills/hectelion-sa/claude-dataroom-prep/skill)

Your own site

<a href="https://agentmods.dev/skills/hectelion-sa/claude-dataroom-prep/skill"><img src="https://agentmods.dev/badge/skills/hectelion-sa/claude-dataroom-prep/skill/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/hectelion-sa/claude-dataroom-prep/skill"><img src="https://agentmods.dev/badge/skills/hectelion-sa/claude-dataroom-prep/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,962 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00154	$0.05962
Opus 5	$0.00077	$0.02981
Sonnet 5	$0.00031	$0.01192
Haiku 4.5	$0.00015	$0.00596

Measured 9d ago against content hash 7731085ee8a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dataroom-prep 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/enrich_checklist.py, scripts/run_pipeline.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skill/SKILL.md · 380 lines

How it starts

The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.

dataroom-prep — Skill de préparation de dataroom M&A

Quand utiliser ce skill

Déclencher quand l'utilisateur demande de :

Trier / organiser / structurer des documents en vrac en dataroom DD
Préparer une dataroom M&A pré-upload VDR (Ansarada, Datasite, Drooms, etc.)
Renommer en masse des documents avec convention Project X - Intitulé du document - yyyymmdd
Détecter et archiver les doublons / versions obsolètes d'un dossier
Générer une checklist des documents à demander client

Confidentialité & zéro exfiltration (RÈGLE ABSOLUE)

🔒 Les documents et leur contenu ne quittent JAMAIS le PC de l'utilisateur. Toute la persistance se fait en local (workdir + dossier destination) ; rien n'est envoyé vers un serveur externe.

Règles non négociables :

Traitement local par défaut. Extraction, classification, dedup, build, Excel mapping et le Top 50 des documents manquants sont 100% hors-ligne (scripts Python, listes DD locales dans data_sources/). Aucun appel réseau n'est requis pour produire une dataroom complète.
Ne JAMAIS envoyer de contenu de document — ni un fichier, ni un snippet extracted.json, ni un titre/chemin issu des documents — vers un outil externe : pas de Firecrawl, pas de data.gouv, pas de WebSearch/WebFetch, pas de MCP tiers, pas d'upload. Ces données restent strictement dans la session et sur le disque local.
Aucune donnée client dans la mémoire persistante. Ne rien écrire dans MEMORY.md ni dans les fichiers memory/ qui contienne un nom de société cible, un chiffre, un titre de document ou tout élément du mandat. La mémoire ne sert qu'aux notes de process génériques.
Seule exception réseau = Étape 8 (checklist enrichie), strictement opt-in. Cette étape appelle firecrawl_scrape sur le site web public de la société + des sources juridiques (data.gouv / Légifrance / Fedlex). Elle n'envoie QUE l'URL publique et des requêtes secteur/droit — jamais le contenu des documents. Avant de la lancer, prévenir l'utilisateur : « cette étape contacte des serveurs externes (le site public de la société + sources légales) ; veux-tu la lancer ou rester 100% hors-ligne ? ». Si l'utilisateur veut le zéro-réseau total, sauter l'Étape 8 et se contenter du Top 50 local (étape 5bis), qui couvre déjà la liste des documents à demander sans aucune connexion.
Nettoyage des résidus. Écrire les fichiers de travail (extracted.json, decisions.json) dans un workdir temporaire isolé, jamais dans scripts/. Ne pas laisser traîner de fichier contenant des titres/snippets de documents client dans le dossier du skill après le run.

Read the full file on GitHub · 380 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

9d ago First seen · 380 lines · 154 tokens per session scan A 7731085ee8a5

Subscribe to this mod's changes

dataroom-prep is a skill published in the GitHub repository Hectelion-SA/claude-dataroom-prep (2 stars, last pushed 1mo ago), licensed MIT. It adds 154 tokens to every session and 5,962 once invoked, about $0.0008 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.

Claude Code Documents claude claude-ai claude-skills dataroom document-classification

topical-authority-map

Builds a 4-cluster Topical Authority Map from a seed keyword. Outputs an .xlsx spreadsheet with five tabs (Core Pages, AOR Pages, Linking Map, Buyer Journey, Publishing Order) plus a markdown strategy document. Interactive, asks the user to confirm central entity, source context, persona, classification, and gaps at…

lhitches/claude-seo-skills · 110 tokens

markitdown

Converts files (PDF, DOCX, PPTX, XLSX, images, audio, HTML, CSV/JSON/XML, ZIP, YouTube URLs) to clean Markdown using Microsoft's markitdown CLI, and optionally reviews the result for extraction artifacts (fragmented sentences, missing headings, ligature glitches, spelling errors). Use this skill whenever the user…

ErickRamirezAU/claude-skills · 141 tokens

investment-report-reader

Read and extract content from PDF investment reports — sell-side notes (GS/MS/JPM/UBS/Citi/BofA), 10-Ks, annual reports, fund factsheets, manager commentaries, and macro outlooks. Specialises in CHARTS, TABLES, and IMAGES that text-only extraction silently misses (most research charts are vector and invisible to…

HHFinAi/claude-equity-research-skills · 221 tokens

rtl-document-translation

Translate structured documents (DOCX) to RTL languages (Arabic, Hebrew, Urdu) while preserving exact formatting, table structures, colors, and layouts. Handles quote normalization, multi-pass translation matching, and RTL-specific formatting patterns.

belumume/claude-skills · 50 tokens

docx-advanced-patterns

Advanced python-docx patterns for handling nested tables, complex cell structures, and content extraction beyond basic .text property. Complements the official docx skill with specialized techniques for forms, checklists, and complex layouts.