ManceRayder42ManceRayder42/jarvis-os/AGENTS.md

jarvis-os

AGENTS.md5 starsChanged 43 days agoMITView on GitHub

You can set this plugin up for the user without the browser page. Paths are relative to the plugin root ($CLAUDE_PLUGIN_ROOT inside Claude Code). Exit code 0 = done, 1 = something failed (the output says what), 2 = bad usage. - Each plan item has who: agent (run it), ask (installs software — get the user's yes first, one question for the batch), person (keys, sign-ins, apps — hand these to the user). - Never handle a secret. connect…

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 31,700 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 repository12 other files it gives its agents.
- councilSkill
- defuddleSkill
- doneSkill
- eli5Skill
- grill-meSkill
- learnSkill
- media-genSkill
- memory-consolidationSkill
- qmdSkill
- research-notebookSkill
- setup-for-meSkill
- wiki-articleSkill

The file

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Never handle a secret. connect reads a key from a hidden prompt, or with --from-clipboard from the clipboard.
line 23

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

AGENTS.md

For agents working with Jarvis OS

You can set this plugin up for the user without the browser page.

node setup/agent.mjs plan --json     # what is left, in order, and who has to do it
node setup/agent.mjs setup           # create memory, history, default skills, free tools
node setup/agent.mjs enable <id>     # switch a skill on (disable <id> to switch off)
node setup/agent.mjs install <id>    # install a program from the Tools list
node setup/agent.mjs connect <id>    # connect an MCP server
node setup/agent.mjs status          # one-screen summary

Paths are relative to the plugin root ($CLAUDE_PLUGIN_ROOT inside Claude Code). Exit code 0 = done, 1 = something failed (the output says what), 2 = bad usage.

Rules:

Each plan item has who: agent (run it), ask (installs software — get the user's yes first, one question for the batch), person (keys, sign-ins, apps — hand these to the user).
Never handle a secret. connect reads a key from a hidden prompt, or with --from-clipboard from the clipboard; the user runs that one command themselves (in Claude Code: ! + command). Never run it or read the clipboard yourself.
Report from the command output, not from what you expected.

Data the commands read, if you need to look directly:

File	What it is
`setup/profile.json`	title, step order, closing text
`setup/tools-catalog.json`	every tool: what it is, how it is detected, installed or connected
`setup/skills-catalog.json`	every skill: default on/off, what it needs
`memory-template/`	what a new memory folder starts with

The setup-for-me skill wraps all of this for Claude Code.

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