agent-workspace-starter
AGENTS.md1 starsChanged 36 days agoMITView on GitHub
Instructions for any coding agent working in this repository, in the agents.md format. This repo is a template: the smallest working scaffold for a governed agent workspace in Claude Code. Everything here is copied verbatim into someone else's repository by "Use this template", so nothing private, machine-specific or personal ever belongs in a file. CLAUDE.md carries the working rules and is the file to read first; it is the same content Claude Code loads automatically. Humans start at README.md, contributors…
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 32,671 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.
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: line 15
Before you commit, run what CI runs locally: python -m json.tool over every JSON file under .claude/, and a py_compile pass over each hook …
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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
AGENTS.md
Instructions for any coding agent working in this repository, in the agents.md format.
This repo is a template: the smallest working scaffold for a governed agent workspace in Claude Code. Everything here is copied verbatim into someone else's repository by "Use this template", so nothing private, machine-specific or personal ever belongs in a file.
CLAUDE.md carries the working rules and is the file to read
first; it is the same content Claude Code loads automatically. Humans start at
README.md, contributors at CONTRIBUTING.md.
Before you commit, run what CI runs locally: python -m json.tool over every
JSON file under .claude/, and a py_compile pass over each hook in
.claude/hooks/. Python 3.12 is the version CI uses.
CI also runs each hook exactly as .claude/settings.json wires it, from a
directory outside the repo, and asserts exit 2 on a known-bad payload and 0 on
a benign one. That check is an inline script in the last validate step of
.github/workflows/ci.yml, so there is no local
command to run. It runs in CI on every pull request and push to main.
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.

