youtube-shorts-agent
AGENTS.md1 starsChanged 6 months agoMITView on GitHub
This repo is an agent-first YouTube Shorts upload CLI and MCP server with dry-run defaults.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,439 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository2 other files it gives its agents.
- llms.txtllms.txt
- youtube-shortsSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 1 is common, 2 are distinctive, and 0 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- could be automatic: a setting could enforce it
- Common: line 18
Never commit OAuth credentials, refresh tokens, video assets with private rights, upload logs with private account data, or local config.
- Distinctive: line 19
Keep dry-run behavior the default for agent workflows.
- Distinctive: line 21
Keep synthetic-media metadata behavior explicit.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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.
Files
Agent Development Notes
Scope
This repo is an agent-first YouTube Shorts upload CLI and MCP server with dry-run defaults.
Commands
- Install:
npm ci - Syntax check:
npm run check - Test:
npm test - Doctor:
npm run doctor - Manifest:
npm run manifest - Privacy audit:
npm run privacy
Rules
- Never commit OAuth credentials, refresh tokens, video assets with private rights, upload logs with private account data, or local config.
- Keep dry-run behavior the default for agent workflows.
- Preserve manifest, connection status, privacy audit and metadata checks.
- Keep synthetic-media metadata behavior explicit.
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
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.