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 binary16labs/prime-silo --skill file-downloadgit clone --depth 1 https://github.com/binary16labs/prime-siloWrote 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/binary16labs/prime-silo/file-download)<a href="https://agentmods.dev/skills/binary16labs/prime-silo/file-download"><img src="https://agentmods.dev/badge/skills/binary16labs/prime-silo/file-download.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00914 |
| Opus 5 | $0.00011 | $0.00457 |
| Sonnet 5 | $0.00004 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00091 |
Grade A, and why
File Download scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
If the external URL is public and CORS allows direct access from the browser, you can skip the proxy and fetch it directly with `fetch(externalUrl)` and the same Blob pattern above. This is a copy
100% identical to File Download — 37 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill when the user asks how to let the browser download a file — whether it lives in the app filesystem, is generated at runtime, or comes from an external URL.
Downloading App Filesystem Files
The server serves authenticated files directly at their layer paths. Use a URL built from location.href so the request carries the session cookie and the server enforces read permissions.
From the authenticated user's home folder (~/)
/~/... maps to L2/<username>/... for the currently logged-in user.
const u = new URL(location.href);
u.pathname = "/~/BTC_ETH_ratio_chart.pdf";
const a = document.createElement("a");
a.href = u.toString();
a.download = "BTC_ETH_ratio_chart.pdf";
a.click();
From a specific layer path (/L0/, /L1/, /L2/)
Use the full layer path directly. The server checks that the authenticated user has read access before serving.
function downloadAppFile(layerPath, filename) {
// layerPath example: 'L0/_all/mod/_core/reports/template.pdf'
const u = new URL(location.href);
u.pathname = `/${layerPath}`;
const a = document.createElement("a");
a.href = u.toString();
a.download = filename;
a.click();
}
// Examples:
downloadAppFile("L0/_all/mod/_core/reports/template.pdf", "template.pdf");
downloadAppFile("L2/alice/exports/summary.csv", "summary.csv");
Read permissions follow the same rules as the file APIs:
L2/<username>/— own files onlyL0/<group>/andL1/<group>/— group members only- Unauthenticated requests return 401; unauthorized paths return 403
Downloading Runtime-Generated In-Memory Content
For files generated on the fly (CSV exports, JSON dumps, dynamically built text), create a Blob, make an object URL, and revoke it after the click.
function downloadBlob(content, filename, mimeType = "text/plain") {
const blob = new Blob([content], { type: mimeType });
const url = URL.createObjectURL(blob);
const a = document.createElement("a");
a.href = url;
a.download = filename;
a.click();
URL.revokeObjectURL(url);
}
// Plain text
downloadBlob("hello world", "note.txt", "text/plain");
// CSV
const csv = "name,value\nalice,42\nbob,17";
downloadBlob(csv, "data.csv", "text/csv");
// JSON
const json = JSON.stringify({ status: "ok", items: [1, 2, 3] }, null, 2);
downloadBlob(json, "result.json", "application/json");
// Binary data from a Uint8Array or ArrayBuffer
const bytes = new Uint8Array([0x25, 0x50, 0x44, 0x46]); // %PDF header
downloadBlob(bytes, "output.pdf", "application/pdf");
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.
- 7d ago First seen · 113 lines · 22 tokens per session scan A 47eb0432d469
File Download is a skill published in the GitHub repository binary16labs/prime-silo (5 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 914 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to File Download, differing in 37 lines, and is treated as a copy.
Other skills, from other repositories
xh
Use when the agent or user needs to make an HTTP request from the shell - GET a URL, POST JSON to an API, check a webhook with auth, test a REST endpoint, fetch and inspect headers, or upload a file.
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.
browser_cdp
Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.
browser_visible
Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…