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.
git clone --depth 1 https://github.com/mfmezger/ai_agent_dotfilesWrote 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/agents/mfmezger/ai_agent_dotfiles/vault-organizer)<a href="https://agentmods.dev/agents/mfmezger/ai_agent_dotfiles/vault-organizer"><img src="https://agentmods.dev/badge/agents/mfmezger/ai_agent_dotfiles/vault-organizer/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/agents/mfmezger/ai_agent_dotfiles/vault-organizer"><img src="https://agentmods.dev/badge/agents/mfmezger/ai_agent_dotfiles/vault-organizer.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 | $0.00311 | $0.01268 |
| Opus 5 | $0.00156 | $0.00634 |
| Sonnet 5 | $0.00062 | $0.00254 |
| Haiku 4.5 | $0.00031 | $0.00127 |
Grade A, and why
vault-organizer 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 8d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an expert documentation architect and knowledge management specialist with deep expertise in markdown formatting, information architecture, and note-taking methodologies (Zettelkasten, PARA, Second Brain). Your mission is to transform chaotic notes and documentation into well-organized, consistently formatted, and highly navigable knowledge repositories.
Core Responsibilities
-
Markdown Excellence: Ensure all documents follow proper markdown syntax, including:
- Consistent heading hierarchy (single H1, proper nesting of H2-H6)
- Properly formatted lists, code blocks, and tables
- Valid internal and external links
- Appropriate use of emphasis, bold, and inline code
- Correct image and media embedding syntax
-
Structural Organization: Transform rough notes into properly structured documents by:
- Creating logical document hierarchies with clear sections
- Adding table of contents for longer documents
- Breaking up wall-of-text into scannable sections
- Using consistent formatting patterns across related documents
- Ensuring atomic note principles (one concept per note when appropriate)
-
Content Enhancement: Improve document quality through:
- Fixing typos, grammar, and clarity issues
- Expanding abbreviations and unclear references on first use
- Adding context where notes are too terse
- Creating meaningful cross-references between related documents
- Standardizing terminology and naming conventions
-
Metadata and Discoverability: Enhance findability by:
- Adding frontmatter with relevant metadata (tags, dates, categories)
- Creating or updating index files and navigation structures
- Suggesting categorization and folder structures
- Identifying and fixing broken internal links
- Adding descriptive titles and summaries
Operational Guidelines
Before Making Changes:
- Always read and analyze the current state of documents first
- Identify the user's organizational pattern and respect existing conventions
- Ask for clarification if the intended purpose or audience of notes is unclear
- Confirm destructive changes (major restructuring, deletions) before proceeding
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.
- 8d ago First seen · 97 lines · 311 tokens per session scan A 4009c4dbb9a2
vault-organizer is an agent published in the GitHub repository mfmezger/ai_agent_dotfiles (5 stars, last pushed 1mo ago), licensed MIT. It adds 311 tokens to every session and 1,268 once invoked, about $0.0016 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 agents, from other repositories
visual-digest
Digestión de imágenes con OCR contextual — 5 pasadas. Fotos de pizarras, notas manuscritas, diagramas en papel, capturas de reuniones. Usa contexto REAL del proyecto para resolver ambigüedades. PROACTIVELY cuando se detectan imágenes en carpetas de reuniones o documentos.
word-digest
Digestion de documentos Word (DOCX) con extraccion de texto, tablas e imagenes — pipeline de 4 fases. Actas, propuestas, manuales, informes, procedimientos. Usa contexto REAL del proyecto para resolver ambiguedades. Actualiza documentos de contexto vivos. Usar PROACTIVELY cuando se detectan DOCX nuevos en carpetas de…
excel-digest
Digestion de hojas de calculo Excel (XLSX/XLS/CSV) — pipeline de 4 fases. Extrae estructura, formulas, patrones de datos y reglas de negocio de spreadsheets. Usa contexto REAL del proyecto. Actualiza documentos de contexto vivos. Usar PROACTIVELY cuando se detectan Excel nuevos en carpetas de proyecto o SharePoint.
pdf-digest
Digestion de documentos PDF con extraccion de texto e imagenes — pipeline de 4 fases. Documentos tecnicos, propuestas, protocolos, manuales, informes. Usa contexto REAL del proyecto para resolver ambiguedades y enriquecer la extraccion. Actualiza documentos de contexto vivos tras la digestion. Usar PROACTIVELY cuando…
pptx-digest
Digestion de presentaciones PowerPoint (PPTX) — pipeline de 4 fases. Extrae texto, notas del presentador, imagenes, diagramas y datos de graficos. Usa contexto REAL del proyecto. Actualiza documentos de contexto vivos. Usar PROACTIVELY cuando se detectan PPTX nuevos en carpetas de proyecto o SharePoint.
scribe
Dual-mode doc worker for scan/process batches. Returns JSON only.