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/olorehq/olore/rclone_copyurlgit clone --depth 1 https://github.com/olorehq/oloreWrote 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/olorehq/olore/rclone_copyurl)<a href="https://agentmods.dev/commands/olorehq/olore/rclone_copyurl"><img src="https://agentmods.dev/badge/commands/olorehq/olore/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 | $0.00883 |
| Opus 5 | $0.00006 | $0.00441 |
| Sonnet 5 | $0.00002 | $0.00177 |
| Haiku 4.5 | $0.00001 | $0.00088 |
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 yesterday.
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 Copies of this mod
1 near-identical copy found in the catalogue:
- rclone_copyurl — 89% identical, 11 lines differ
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
Each FILENAME in the CSV file can start with a relative path which will be appended
to the destination path provided at the command line. For example, running the command
shown above with the following CSV file will write two files to the destination:
remote:dir/local/path/bar.json and remote:dir/another/local/directory/qux.json
https://example.org/foo/bar.json,local/path/bar.json
https://example.org/qux/baz.json,another/local/directory/qux.json
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
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.
- yesterday First seen · 99 lines · 12 tokens per session scan A a08056a7b176
rclone_copyurl is a command published in the GitHub repository olorehq/olore (103 stars, last pushed today), licensed MIT. It adds 12 tokens to every session and 883 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.