brandfile
AGENTS.md0 starsChanged 6 days agoMITView on GitHub
Agent skills for creating an AI-native brand book. - Agents are the primary reader. The brand book exists so agents can follow it. People need only a view that shows how it looks. - Decisions rest on an interview. Before proposing anything, learn what the brand and product are and collect references the person likes. Base style choices on those answers, not on defaults. The first version is written and has not been run on a real brand yet. docs/decisions.md…
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 31,774 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 repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- brand-bookSkill
- brand-directionsSkill
- brandfileSkill
- brand-interviewSkill
- brand-probeSkill
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 7
Decisions rest on an interview: Before proposing anything, learn what the brand and product are and collect references the person likes.
≈ “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
AGENTS.md
Agent skills for creating an AI-native brand book.
- Agents are the primary reader. The brand book exists so agents can follow it. People need only a view that shows how it looks.
- Decisions rest on an interview. Before proposing anything, learn what the brand and product are and collect references the person likes. Base style choices on those answers, not on defaults.
The first version is written and has not been run on a real brand yet.
docs/decisions.md records the product decisions and overrides older documents. Reports in docs/research/ hold the reasoning and evidence
behind the skills. When another document and the skills or scripts disagree, the skills and scripts
describe the current system: follow them, and point out each mismatch in your reply. A skill that
contradicts docs/decisions.md is a defect to report.
In replies, commit messages, and pull request descriptions, lead with what changed for a person making a brand book, then what the reader must decide or check. Leave out how it was done unless asked, and never present an untested effect as tested.
Where things go
- A skill lives in
skills/<name>/. Read docs/skill-authoring.md before adding or editing one. - The scripts live in
skills/brandfile/scripts/, with Node 20+ and no dependencies. Runnode --test test/after changing them or a skill. - A research report is one Markdown file in
docs/research/, with a source for every claim. Keep verified facts, practitioner opinion, and your own inference visibly separate.
Using other projects
Ideas from other repositories are welcome. Before copying files or text, check the source's license and credit it in the README. Fonts, logos, and other brand assets keep their own licenses, so do not commit them without confirming the terms.
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.