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/NetMindAI-Open/NarraNexusWrote 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/commands/netmindai-open/narranexus/file_download.rs)<a href="https://agentmods.dev/commands/netmindai-open/narranexus/file_download.rs"><img src="https://agentmods.dev/badge/commands/netmindai-open/narranexus/file_download.rs.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 | $0.00000 | $0.01209 |
| Opus 5 | $0.00000 | $0.00605 |
| Sonnet 5 | $0.00000 | $0.00242 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
file_download.rs 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
file_download.rs — Save a backend file to the OS Downloads folder
Why it exists
Two local download surfaces were broken with the standard
<a href download> approach:
-
Tauri DMG: the webview origin is
https://tauri.localhost(HTTPS) while the backend serves onhttp://localhost:8000(HTTP). WKWebView classifies HTTP navigations from an HTTPS document as "active mixed content" and blocks them silently. Thedownloadattribute is also ignored for cross-origin URLs in all modern browsers. -
Local browser (
bash run.sh, Vite:5173→ backend:8000): cross-origin, so thedownloadattribute is silently ignored. Workspace files additionally requireX-User-Id/Authorizationheaders that<a>elements cannot send.
HTTP requests originated by Rust are not subject to WKWebView's
mixed-content rules. This command fetches file bytes via reqwest,
optionally attaching auth headers, writes them to the OS Downloads
directory, and returns the absolute saved path so the frontend can
display a "Saved to: …" confirmation.
This file does not do
- Streaming large files progressively — bytes are buffered in memory before writing. This is acceptable for the artifact and workspace file sizes this command targets.
- Serving bytes back to the JS side for in-page rendering — that is
artifact_fetch.rs's job (returns base64 for iframe display). This command always writes to disk.
Upstream / Downstream
- Registered in:
lib.rsinvoke_handler!macro ascommands::file_download::download_file_via_backend. - Called by:
frontend/src/lib/tauri.ts::downloadFileViaTauri(), which is in turn called byfrontend/src/lib/download.ts::downloadFile()when running inside Tauri. - Depends on:
reqwest(HTTP),dirscrate (resolves~/Downloadswithout a new Tauri plugin),url(URL parsing for the SSRF validator).
Security: SSRF guard
Mirrors the guard in artifact_fetch.rs. Before reqwest sees the
URL the validate() function enforces:
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 · 116 lines · 0 tokens per session scan A b2b70cc0ad44
file_download.rs is a command published in the GitHub repository NetMindAI-Open/NarraNexus (86 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,209 tokens. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.