A local knowledge base that converts files into clean Markdown notes and lets an AI search and answer questions over them. The original files remain available as the sources to check.

It is for turning PDFs, office files, spreadsheets, images, web pages, text, code, and audio or video into searchable notes, then finding and answering questions from those notes.

It removes the need to search many different file types manually while keeping answers linked to the underlying documents. It can handle both importing files and retrieving information from an existing collection.

local-vault — Skill for Claude Code by genli-ai

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 genli-ai/market-research-skills --skill local-vault

Clone the repo

git clone --depth 1 https://github.com/genli-ai/market-research-skills

Made for: Claude Code.

Or install market-research-skills, the plugin that ships this one along with the rest of its 4 skills, 1 hook.

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/genli-ai/market-research-skills/local-vault/github.svg)](https://agentmods.dev/skills/genli-ai/market-research-skills/local-vault)

Your own site

<a href="https://agentmods.dev/skills/genli-ai/market-research-skills/local-vault"><img src="https://agentmods.dev/badge/skills/genli-ai/market-research-skills/local-vault/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/genli-ai/market-research-skills/local-vault"><img src="https://agentmods.dev/badge/skills/genli-ai/market-research-skills/local-vault.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,243 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	$0.00227	$0.03243
Opus 5	$0.00113	$0.01622
Sonnet 5	$0.00045	$0.00649
Haiku 4.5	$0.00023	$0.00324

Measured 13d ago against content hash 7e572527130b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

local-vault 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 13d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/config.py, scripts/mineru_client.py, scripts/sync.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.

skills/local-vault/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

local-vault

Turn a folder of raw files into a Markdown vault that an LLM can grep, and then answer questions over that vault responsibly.

Mental model: SOURCE = raw files (source of truth). VAULT = one .md per source file, carrying retrieval frontmatter (abstract / tags / synonyms) + a source backlink. The vault is the layer the LLM reads; the raw files are where the user goes to verify.

There are two distinct jobs — figure out which the user wants:

A. Convert / sync — they dropped files in and want them in the vault → run the pipeline (scripts/sync.py).
B. Retrieve / answer — they want answers from an existing vault → follow the Retrieval & feedback protocol below. Do not run the pipeline for this.

A. Convert / sync

One-time setup (do this for the user if not already done)

Python deps (user-level, no venv):

python3 -m pip install --user requests python-dotenv pypdf pymupdf4llm openpyxl python-pptx

pandoc (for docx/rtf/odt/epub): brew install pandoc (macOS) / distro pkg.
ffmpeg (only for audio/video transcription): brew install ffmpeg (macOS) / distro pkg. The whisper engine is auto-selected by platform — mlx-whisper on Apple Silicon (GPU), faster-whisper elsewhere (cross-platform CPU/CUDA) — and auto-installed after the user consents at the first-run prompt (no manual pip needed). On that first run with audio/video present, the tool shows the model-size options (tiny ~75 MB / small ~480 MB / turbo ~1.6 GB / large-v3 ~3 GB) and lets the user pick or skip; the choice is saved to .env (KB_WHISPER_MODEL) so it never re-asks. Fully local — no token/quota; the model downloads once, then offline.
claude CLI on PATH — the pipeline shells out to claude -p for frontmatter enrichment and PPT-image OCR. If absent, those steps are skipped (not fatal).
Configure paths — two ways:
- Guided (recommended for the user): just run python3 scripts/sync.py in a terminal. On first run (when paths aren't configured yet) it launches an interactive wizard: it asks for the raw-files folder + the vault folder (+ optional MinerU token), creates them, writes scripts/.env, and prints how to use the tool. Then they re-run to convert.
- Manual: copy scripts/.env.example → scripts/.env and set KB_SOURCE_DIR (raw files) and KB_TARGET_DIR (the Markdown vault), both absolute. MINERU_TOKEN is optional (only for legacy .doc/.ppt, .html, scanned PDFs, images — get one at https://mineru.net).
- When you (Claude) run the setup for the user, prefer the manual path: ask them for the two folders, then write scripts/.env directly (the wizard only fires on an interactive TTY, which a claude -p subprocess is not).

Read the full file on GitHub · 216 lines

Files

What ships with it

6 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.

13d ago First seen · 216 lines · 227 tokens per session scan A 7e572527130b

Subscribe to this mod's changes

local-vault is a skill published in the GitHub repository genli-ai/market-research-skills (62 stars, last pushed 3mo ago), licensed MIT. It adds 227 tokens to every session and 3,243 once invoked, about $0.0011 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 2026-08-30.

Claude Code Documents Memory and context agent-skills claude-skill skills-sh

obsidian

Obsidian vault: search/read/write notes, backlinks, Bases, Canvas.

steipete/agent-scripts · 19 tokens

mindos-zh

A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.

GeminiLight/MindOS · 490 tokens

excel-author

Create and edit Excel (.xlsx) workbooks with openpyxl. Supports formulas, charts, formatting, and data analysis.

fuyuxiang/echo-agent · 28 tokens

ppt-author

Create and edit PowerPoint (.pptx) presentations programmatically. Requires python-pptx.

fuyuxiang/echo-agent · 22 tokens

knowledge_base

Manage the user's personal knowledge base — knowledge graph, documents, and wiki vault.

siddsachar/row-bot · 19 tokens

gdoc-to-markdown

Internal fetcher module for Google Docs and Sheets. Fetches content via MCP (preferred, when available), Google API with bearer token or public URL export (fallback), or browser DOM extraction via Claude in Chrome (last resort) and returns Markdown. Used by /bedrock:teach and /bedrock:sync — not intended for direct…

ccplugins/awesome-claude-code-plugins · 76 tokens

local-vault

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

local-vault

A. Convert / sync

One-time setup (do this for the user if not already done)

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

obsidian

mindos-zh

excel-author

ppt-author

knowledge_base

gdoc-to-markdown