ai-buildcraft
AGENTS.md0 starsChanged 43 days agoMITView on GitHub
The owner approved the public release of this collection and its consolidated learning guide on 2 October 2026. Keep publication limited to reviewed collection content; do not import private source material or publish live application deployments without authorization.
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 repository3 other files it gives its agents.
- deck-from-templateSkill
- keelSkill
- power-codingSkill
The file
We split this AGENTS.md into the rules it gives an agent
3 rules. About 1 is common, 2 are distinctive, and 0 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈2
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
- Common: line 5
Keep examples synthetic or based on redistributable public sources.
- Distinctive: line 8
Run relevant tests for functional changes.
- Distinctive: line 10
Do not claim that prepared examples or contract tests establish a successful live provider run.
≈ “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
AI Buildcraft contributor instructions
The owner approved the public release of this collection and its consolidated learning guide on 2 October 2026. Keep publication limited to reviewed collection content; do not import private source material or publish live application deployments without authorization.
- Keep examples synthetic or based on redistributable public sources. Do not include private company data, credentials, local session exports or personal context.
- Preserve upstream licenses and attribution. Distinguish copied references from original work.
- Each app, skill or lab must explain setup, implemented behavior, verification scope and limitations.
- Run relevant tests for functional changes. Do not make paid model requests without a bounded authorization for that verification.
- Migrated application media integrations use the Gemini API. The separately attributed PixelBin API skill retains its public API identity.
- Do not claim that prepared examples or contract tests establish a successful live provider run.
- Root commits and remote operations are coordinated by the primary task owner; parallel workers edit only their assigned directories.
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.