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 agentmods add commands/chaunsin/agent-skills/rclone_copyurlgit clone --depth 1 https://github.com/chaunsin/agent-skillsWrote 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/chaunsin/agent-skills/rclone_copyurl)<a href="https://agentmods.dev/commands/chaunsin/agent-skills/rclone_copyurl"><img src="https://agentmods.dev/badge/commands/chaunsin/agent-skills/rclone_copyurl.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 | $0.00012 | $0.00804 |
| Opus 5 | $0.00006 | $0.00402 |
| Sonnet 5 | $0.00002 | $0.00161 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade A, and why
rclone_copyurl 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 4d 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.
- `--user agent curl` - some sites have whitelists for curl's user-agent - try that This is a copy
89% identical to rclone_copyurl — 11 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Official documentation: https://rclone.org/commands/rclone_copyurl/
rclone copyurl
Copy the contents of the URL supplied content to dest:path.
Synopsis
Download a URL's content and copy it to the destination without saving it in temporary storage.
Setting --auto-filename will attempt to automatically determine the
filename from the URL (after any redirections) and used in the
destination path.
With --header-filename in addition, if a specific filename is
set in HTTP headers, it will be used instead of the name from the URL.
With --print-filename in addition, the resulting file name will be
printed.
Setting --no-clobber will prevent overwriting file on the
destination if there is one with the same name.
Setting --stdout or making the output file name -
will cause the output to be written to standard output.
Setting --urls allows you to input a CSV file of URLs in format: URL,
FILENAME. If --urls is in use then replace the URL in the arguments with the
file containing the URLs, e.g.:
rclone copyurl --urls myurls.csv remote:dir
Missing filenames will be autogenerated equivalent to using --auto-filename.
Note that --stdout and --print-filename are incompatible with --urls.
This will do --transfers copies in parallel. Note that if --auto-filename
is desired for all URLs then a file with only URLs and no filename can be used.
Troubleshooting
If you can't get rclone copyurl to work then here are some things you can try:
--disable-http2rclone will use HTTP2 if available - try disabling it--bind 0.0.0.0rclone will use IPv6 if available - try disabling it--bind ::0to disable IPv4--user agent curl- some sites have whitelists for curl's user-agent - try that- Make sure the site works with
curldirectly
rclone copyurl https://example.com dest:path [flags]
Options
-a, --auto-filename Get the file name from the URL and use it for destination file path
--header-filename Get the file name from the Content-Disposition header
-h, --help help for copyurl
--no-clobber Prevent overwriting file with same name
-p, --print-filename Print the resulting name from --auto-filename
--stdout Write the output to stdout rather than a file
--urls Use a CSV file of links to process multiple URLs
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.
- 4d ago First seen · 92 lines · 12 tokens per session scan A 6115b8ad2312
rclone_copyurl is a command published in the GitHub repository chaunsin/agent-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 804 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 89% identical to rclone_copyurl, differing in 11 lines, and is treated as a copy.
Other commands, from other repositories
ink-art
Hand-drawn ink-on-white doodle animation — a character that draws itself then walks/dances/waves, or a deadpan contraption explainer. Vector, deterministic, rendered via HyperFrames to MP4.
animated-drawing
Animate a SUPPLIED drawing/photo of a character with real motion capture (Meta AnimatedDrawings) → raster GIF/MP4 of that drawing moving. To CREATE a vector doodle from scratch, use /ink-art.
backlot
Open the Backlot living storyboard — the browser board that shows pipeline stages, script, scene plan, and generated assets live as a production runs.
README
Codex only scans /.codex/prompts/ (user home) for custom prompts — it does not read project-level .codex/prompts/. These files are versioned here as the source of truth; to use them in Codex, copy or symlink them into your home dir.
create-spec
Generate comprehensive feature specifications using a contract-first approach that ensures complete alignment between developer and AI before creating any supporting files. This command eliminates presumptuous file creation by establishing a clear "contract" through structured clarification rounds.
create-adr
Create comprehensive Architecture Decision Records (ADRs) that systematically document architectural decisions with clear rationale, alternatives considered, and consequences through a structured analysis and review process.