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/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_test_speed)<a href="https://agentmods.dev/commands/chaunsin/agent-skills/rclone_test_speed"><img src="https://agentmods.dev/badge/commands/chaunsin/agent-skills/rclone_test_speed/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/commands/chaunsin/agent-skills/rclone_test_speed"><img src="https://agentmods.dev/badge/commands/chaunsin/agent-skills/rclone_test_speed.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 | $0.00007 | $0.00541 |
| Opus 5 | $0.00003 | $0.00270 |
| Sonnet 5 | $0.00001 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
rclone_test_speed 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 6d 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.
This is a copy
92% identical to rclone_test_speed — 2 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Official documentation: https://rclone.org/commands/rclone_test_speed/
rclone test speed
Run a speed test to the remote
Synopsis
Run a speed test to the remote.
This command runs a series of uploads and downloads to the remote, measuring and printing the speed of each test using varying file sizes and numbers of files.
Test time can be innaccurate with small file caps and large files. As it uses the results of an initial test to determine how many files to use in each subsequent test.
It is recommended to use -q flag for a simpler output. e.g.:
rclone test speed remote: -q
NB This command will create and delete files on the remote in a randomly named directory which will be automatically removed on a clean exit.
You can use the --json flag to only print the results in JSON format.
rclone test speed <remote> [flags]
Options
--ascii Fill files with random ASCII printable bytes only
--chargen Fill files with a ASCII chargen pattern
--file-cap int Maximum number of files to use in each test (default 100)
-h, --help help for speed
--json Output only results in JSON format
--large SizeSuffix Size of large files (default 1Gi)
--medium SizeSuffix Size of medium files (default 10Mi)
--pattern Fill files with a periodic pattern
--seed int Seed for the random number generator (0 for random) (default 1)
--small SizeSuffix Size of small files (default 1Ki)
--sparse Make the files sparse (appear to be filled with ASCII 0x00)
--test-time Duration Length for each test to run (default 15s)
--zero Fill files with ASCII 0x00
See the global flags page for global options not listed here.
See Also
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.
- 6d ago First seen · 67 lines · 7 tokens per session scan A ff4041d8c112
rclone_test_speed is a command published in the GitHub repository chaunsin/agent-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 541 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to rclone_test_speed, differing in 2 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.
deploy-setup
Wire CI + secrets for a fresh storefront. Run once after /init-store before the first push to main.
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.