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 mayank-io/mstack --skill save-local-filegit clone --depth 1 https://github.com/mayank-io/mstackWrote 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/mayank-io/mstack/save-local-file)<a href="https://agentmods.dev/skills/mayank-io/mstack/save-local-file"><img src="https://agentmods.dev/badge/skills/mayank-io/mstack/save-local-file/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/mayank-io/mstack/save-local-file"><img src="https://agentmods.dev/badge/skills/mayank-io/mstack/save-local-file.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 | $0.00073 | $0.00799 |
| Opus 5.5 | $0.00029 | $0.00320 |
| Sonnet 5.5 | $0.00015 | $0.00160 |
| Haiku 4.5 | $0.00007 | $0.00080 |
Grade A, and why
save-local-file 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Save Local File
Copy a file already on disk into the vault's attachments and write a clipping note that embeds it.
Input
$ARGUMENTS — a path to a local file, optionally followed by extra instructions (a title, a project to tag, a folder). Honour those after filing.
Step 1 — Locate the vault
Walk up from the current working directory looking for a .obsidian/ directory. The first ancestor containing one is the vault root.
d="$PWD"
while [ "$d" != "/" ]; do
[ -d "$d/.obsidian" ] && { echo "$d"; break; }
d="$(dirname "$d")"
done
If none is found, stop and say so — never write outside a vault. There is no config file.
Step 2 — Read the vault's conventions
If the vault root has a CLAUDE.md, read it and follow what it says about clippings folder, attachments folder, frontmatter, tags, and daily-note updates. The vault's own conventions win. The defaults below apply only when it is silent.
Defaults: clippings in Clippings/, attachments in Clippings/attachments/.
Step 3 — Validate and copy
Confirm the file exists and is readable. Copy it into the attachments folder, keeping the original filename so the source stays identifiable. If a file of that name already exists, append a timestamp (report-20260824-143022.pdf) rather than overwriting.
Step 4 — Read the file before writing about it
Read the file's contents. For a PDF, check for a text layer first (pdftotext) and fall back to the Read tool's pages: parameter; for an image, look at it. Never write a summary of a file you have not opened — a filed-but-unexamined attachment is worse than no note, because it looks complete.
Step 5 — Write the clipping note
Title from the filename: strip the extension, replace underscores and dashes with spaces, title-case it. quarterly_report_2024.pdf → Quarterly Report 2024.
---
tags:
- clippings
- inbox
source: <origin if known, else "local file">
date_captured: YYYY-MM-DD
---
# <Title>
![[<original-filename.ext>]]
---
## Summary
<what the file actually contains, from having read it>
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 · 86 lines · 73 tokens per session scan A 1329c9896d72
save-local-file is a skill published in the GitHub repository mayank-io/mstack (6 stars, last pushed 3d ago), licensed MIT. It adds 73 tokens to every session and 799 once invoked, about $0.0003 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.
Other skills, from other repositories
apify-youtube-transcript-scraper
Get YouTube captions, timestamped quotations, SRT/VTT and translated transcripts for videos, channels and playlists through the harshmaur/youtube-transcript-scraper Apify Actor.
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
meta-web-to-pdf-briefing
Render a topic into a distributable PDF briefing in three steps: web search → bullet summary → styled PDF. Trigger when the user asks for a PDF briefing on a single topic.
paper-reader
A reading assistant for computer-vision and deep-learning research papers. It can work with PDF files, arXiv papers, and papers stored in Zotero, a reference-management app.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…