Mega cli
Skill ohtensorplay/mega-codex-plugin/plugins/mega/skills/mega-cli
Use the MEGA Hub CLI for local authentication, repositories, local files, Git, uploads, downloads, bulk or resumable transfer, streaming logs, scripts, long-running waits, and secret-bearing workflows. Trigger when MCP is too bounded or when the task touches the local filesystem or terminal.From its SKILL.md
npx -y skills add ohtensorplay/mega-codex-plugin --skill mega-cliAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
1.7 KB, 275 tokens by cl100k_base, as published. Nobody here has run it
MEGA CLI
Use the installed mega executable as the authority for CLI syntax. Do not guess flags from another Hub CLI.
Workflow
- Run
mega --help, then the relevant command-group help, before composing an unfamiliar command. - Check authentication without printing tokens. If authentication is missing, provide the login command shown by current help and let the user complete it.
- Resolve the canonical repository ID, resource type, revision, local path, and destination before transfer.
- Use revision-pinned and resumable behavior for large or reproducibility-sensitive transfers when current help supports it.
- Show the exact command and expected mutation before destructive, paid, or externally visible actions.
- Verify the resulting revision, commit, Job ID, or runtime state after execution.
Prefer the CLI for
- Uploading or downloading directories, binary artifacts, or large files.
- Git clone, branch, tag, commit, merge, and history workflows.
- Streaming logs and repeated status waits.
- Scripts, batch jobs, CI, and reproducible automation.
- Job or inference inputs containing secrets; use protected secret mechanisms and never command-line plaintext when a safer mechanism exists.
Never echo credentials, embed them in source, commit them, or return them in the final response. Use MCP for bounded discovery first when it reduces ambiguity.
What ships with it: 1 file
195 B alongside SKILL.md
agents/
- openai.yaml195 B