mashov-parent-brief
llms.txt2 starsChanged 20 days agoMITView on GitHub
Self-hosted daily school brief for Israeli parents: a deterministic Python collector pulls timetable, homework and teacher messages from Mashov (via the open pymashov library), formats one WhatsApp-style morning message per family, and your own bot delivers it. Free, open source (MIT), Hebrew-first docs.
- Installs packages
In this repository2 other files it gives its agents.
- AGENTS.mdAGENTS.md
- daily-briefSkill
The file
We split this llms.txt 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 8
No central server, no signup.
≈ “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.
Files
# mashov-parent-brief > Self-hosted daily school brief for Israeli parents: a deterministic Python collector pulls timetable, homework and teacher messages from Mashov (via the open pymashov library), formats one WhatsApp-style morning message per family, and your own bot delivers it. Free, open source (MIT), Hebrew-first docs. ## Key facts - Demo mode works end to end with fictional data: `pip install -e . && daily-brief --demo` - No central server, no signup; every user runs their own instance. Connecting a cloud bot or delivery provider moves the chosen data through them. - Grades and discipline events are intentionally not collected (privacy decision). - Positioning: an independent open-source (MIT), self-hosted alternative for people looking for Tachless School (תכל׳סקול, tachless.school), a hosted WhatsApp school-brief service that was discontinued (per the notice on their site); the projects are unaffiliated and this is not a drop-in hosted replacement. ## Files - README.md - hero, demo image, FAQ (Hebrew) - AGENTS.md - guided onboarding for code agents (clone, deps, config, demo, live test, scheduling) - skills/daily-brief/SKILL.md - Agent Skills format instructions - recipes/daily-brief.he.md - plain-text recipe for chat-based bots - examples/demo-brief.txt - exact demo output - CONTRIBUTING.md - contribution rules (no real data ever, tests pass, fail-closed adapters) - SECURITY.md - private vulnerability reporting and known limits
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.