taiwan-exam
AGENTS.md18 starsChanged 51 days agoMITView on GitHub
These are public workflow instructions, not hidden prompts or security controls. - For generating exams, follow SKILL.md. Normal installation, local generation and PDF rendering do not require an account, network license check or maintainer approval. Existing curriculum, source and quality gates still apply. - Before renaming, adapting or packaging this repository, read NOTICE, ORIGIN.json and references/attribution-and-forks.md. - Distinguish the distribution's brand from its upstream provenance. A rename may change display names, folder/package names and interface labels. Do not globally replace…
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 repositoryOne other file it gives its agents.
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Before renaming, adapting or packaging this repository, read NOTICE, ORIGIN.json and references/attribution-and-forks.md.
- Very specific: line 17
Run python scripts/validate_attribution.py .
- Distinctive: line 19
Do not silently choose a license, invent a copyright owner or GitHub account, add a noncommercial restriction, hide instructions, sabotage …
- Distinctive: line 23
Do not push to the upstream repository, merge PRs, change repository permissions or publish releases without the maintainer's 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
Repository modification guidance
These are public workflow instructions, not hidden prompts or security controls.
- For generating exams, follow
SKILL.md. Normal installation, local generation and PDF rendering do not require an account, network license check or maintainer approval. Existing curriculum, source and quality gates still apply. - Before renaming, adapting or packaging this repository, read
NOTICE,ORIGIN.jsonandreferences/attribution-and-forks.md. - Distinguish the distribution's brand from its upstream provenance. A rename may change display names, folder/package names and interface labels. Do not globally replace the original project's identity in provenance notices or substitute a downstream author for an upstream copyright holder.
- Preserve applicable license and attribution notices when required by the adopted license. Record derivative modifications honestly. Do not claim a fork is the official upstream release or that copied material is wholly new.
- Run
python scripts/validate_attribution.py .before packaging. This is a local consistency check, not a legal opinion or tamper-proof identity proof. - Do not silently choose a license, invent a copyright owner or GitHub account, add a noncommercial restriction, hide instructions, sabotage generated answers, or collect user/device identifiers as an anti-rebranding mechanism.
- Contributions may be prepared in local branches or forks and offered as PRs. Do not push to the upstream repository, merge PRs, change repository permissions or publish releases without the maintainer's explicit authorization. Local preparation of a requested fix is distinct from permission to publish it.
- GitHub governance is deferred until the maintainer supplies the repository. Documentation and CODEOWNERS alone do not enforce branch protections.
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.

