jotpy
AGENTS.md0 starsChanged 39 days agoMITView on GitHub
When what the server or the browser can do changes, update the description in the same commit: The text for the agent (agentInstructions in public/app.js and public/sheet.js, copied by the "for agent" buttons in the Share dialog and by the robot on a shared page) gives the agent only the skill's address and the share link. Do not put API instructions in it; they belong in the skill. Change it only when the way of handing over to the agent…
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.
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 5
When what the server or the browser can do changes, update the description in the same commit:
≈ “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
Working on jotpy
When you add or change a feature
When what the server or the browser can do changes, update the description in the same commit:
README.md: what jotpy does, the API and the data format. It describes the current state, not the history.skill-jot/SKILL.md: the skill for an agent that works with a note or table through a share link. The server serves it at/skill/jot/SKILL.md. It must match what the API under/api/share/…really accepts and returns.
The text for the agent (agentInstructions in public/app.js and public/sheet.js, copied by the "for agent" buttons in the Share dialog and by the robot on a shared page) gives the agent only the skill's address and the share link. Do not put API instructions in it; they belong in the skill. Change it only when the way of handing over to the agent changes.
Cover new server behaviour with a test in tests/.
Inline scripts
Pages may run only the inline scripts listed in CONTENT_SECURITY_POLICY in src/jotpy/pages.py, allowed by their hash. Put new code in a file under public/; if an inline script is unavoidable, add its constant to that list.
Tests
uv run pytestDoes 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.