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_lsd)<a href="https://agentmods.dev/commands/chaunsin/agent-skills/rclone_lsd"><img src="https://agentmods.dev/badge/commands/chaunsin/agent-skills/rclone_lsd/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_lsd"><img src="https://agentmods.dev/badge/commands/chaunsin/agent-skills/rclone_lsd.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 | $0.00011 | $0.01312 |
| Opus 5 | $0.00005 | $0.00656 |
| Sonnet 5 | $0.00002 | $0.00262 |
| Haiku 4.5 | $0.00001 | $0.00131 |
Grade A, and why
rclone_lsd 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 5d 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
86% identical to rclone_lsd — 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Official documentation: https://rclone.org/commands/rclone_lsd/
rclone lsd
List all directories/containers/buckets in the path.
Synopsis
Lists the directories in the source path to standard output. Does not
recurse by default. Use the -R flag to recurse.
This command lists the total size of the directory (if known, -1 if not), the modification time (if known, the current time if not), the number of objects in the directory (if known, -1 if not) and the name of the directory, E.g.
$ rclone lsd swift:
494000 2018-04-26 08:43:20 10000 10000files
65 2018-04-26 08:43:20 1 1File
Or
$ rclone lsd drive:test
-1 2016-10-17 17:41:53 -1 1000files
-1 2017-01-03 14:40:54 -1 2500files
-1 2017-07-08 14:39:28 -1 4000files
If you just want the directory names use rclone lsf --dirs-only.
Any of the filtering options can be applied to this command.
There are several related list commands
lsto list size and path of objects onlylslto list modification time, size and path of objects onlylsdto list directories onlylsfto list objects and directories in easy to parse formatlsjsonto list objects and directories in JSON format
ls,lsl,lsd are designed to be human-readable.
lsf is designed to be human and machine-readable.
lsjson is designed to be machine-readable.
Note that ls and lsl recurse by default - use --max-depth 1 to stop the recursion.
The other list commands lsd,lsf,lsjson do not recurse by default -
use -R to make them recurse.
List commands prefer a recursive method that uses more memory but fewer
transactions by default. Use --disable ListR to suppress the behavior.
See --fast-list for more details.
Listing a nonexistent directory will produce an error except for remotes which can't have empty directories (e.g. s3, swift, or gcs - the bucket-based remotes).
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.
- 5d ago First seen · 128 lines · 11 tokens per session scan A 45c4664a850b
rclone_lsd is a command published in the GitHub repository chaunsin/agent-skills (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,312 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to rclone_lsd, 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.