agentleFS
Sign inStart free
davidmosiahdavidmosiah/youtube-shorts-agent/llms.txt

youtube-shorts-agent

llms.txt1 starsChanged 6 months agoMITView on GitHub

Agent-first YouTube Shorts upload CLI and MCP server. OAuth-authenticated, dry-run safe by default, never returns tokens to the agent. Repository: https://github.com/davidmosiah/youtube-shorts-agent NPM: https://www.npmjs.com/package/youtube-shorts-agent Docs: https://github.com/davidmosiah/youtube-shorts-agent#readme Primary command: npm exec --yes --package=youtube-shorts-agent -- youtube-shorts-agent doctor MCP command: youtube-shorts-mcp Core tools: - youtube_agent_manifest — runtime contract, tool list, supported clients - youtube_connection_status — credentials present, token age, dry-run mode - youtube_capabilities — supported uploads, max file size, regions - youtube_privacy_audit — what is logged locally vs sent to YouTube - youtube_oauth_authorize_url —…

The file

We split this llms.txt into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Call youtube_connection_status before any upload to verify credentials.

    line 28
  2. Distinctive:

    If dry_run is true, the agent should warn the user that nothing will go live.

    line 29
  3. Distinctive:

    Always preview title, description, and tags with the user before uploading.

    line 30
  4. Distinctive:

    Not affiliated with or endorsed by Google or YouTube.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 3,592 llms.txt files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
llms.txt
# YouTube Shorts Agent

Agent-first YouTube Shorts upload CLI and MCP server. OAuth-authenticated, dry-run safe by default, never returns tokens to the agent.

Repository: https://github.com/davidmosiah/youtube-shorts-agent
NPM: https://www.npmjs.com/package/youtube-shorts-agent
Docs: https://github.com/davidmosiah/youtube-shorts-agent#readme
Primary command: npm exec --yes --package=youtube-shorts-agent -- youtube-shorts-agent doctor
MCP command: youtube-shorts-mcp

Core tools:
- youtube_agent_manifest — runtime contract, tool list, supported clients
- youtube_connection_status — credentials present, token age, dry-run mode
- youtube_capabilities — supported uploads, max file size, regions
- youtube_privacy_audit — what is logged locally vs sent to YouTube
- youtube_oauth_authorize_url — generates the consent URL for the user
- youtube_upload_short — uploads a short with title, description, tags, visibility
- youtube_list_recent_videos — lists recent uploads for confirmation

OAuth env vars:
- YOUTUBE_CLIENT_ID, YOUTUBE_CLIENT_SECRET — from Google Cloud Console (YouTube Data API v3)
- YOUTUBE_REDIRECT_URI — must match exactly what you registered
- YOUTUBE_TOKEN_PATH — defaults to ~/.youtube-shorts-agent/tokens.json
- YOUTUBE_DRY_RUN=true — default; set to false to publish for real
- YOUTUBE_PRIVACY_MODE — default "private"; "public" or "unlisted" allowed

Workflow for agents:
1. Call youtube_connection_status before any upload to verify credentials.
2. If dry_run is true, the agent should warn the user that nothing will go live.
3. Always preview title, description, and tags with the user before uploading.
4. AI-generated content defaults to containsSyntheticMedia=true (YouTube policy).

Safety:
- OAuth tokens stored locally, never returned in tool output.
- Dry-run on by default; flipping to live requires explicit user intent.
- AI-generated uploads tagged as synthetic per YouTube guidelines.
- Quota usage logged locally so the agent can warn before hitting daily limits.
- Not affiliated with or endorsed by Google or YouTube.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free