DENT
AGENTS.md2 starsChanged 3 days agoApache-2.0View on GitHub
This repository is a skill. If you're an AI agent editing it:
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 32,671 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.
- site/llms.txtllms.txt
- dentSkill
- modern-web-guidanceSkill
The file
We split this AGENTS.md into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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 15
Run python scripts/validate.py after every change.
- Very specific: line 17
Don't put user-specific DESIGN.md files in this repo.
≈ “Common” is an estimate: at least 1 in 5 of the 41,581 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 — working on the DENT repository
This repository is a skill. If you're an AI agent editing it:
- The skill lives in
skills/dent/.SKILL.mdis always loaded by agents that use DENT; keep it lean and put task-specific detail inskills/dent/references/. - Label guidance [Law], [Rule] or [Convention]. Never weaken a [Rule].
- New style →
skills/dent/references/styles/<name>.mdfrom_style-template.md+ a row in_styles-index.md+ update the style count inSKILL.mdfrontmatter/§9.2 andREADME.md. - New reference file → add a row to
SKILL.md§9.2 and to the add-on routing table inreferences/workflow-questions-and-effort.md§4. - Commands are generated: edit
COMMANDSinscripts/build_commands.py, run it (writesskills/dent/commands/, rootcommands/anddocs/COMMANDS.md), and add a routing row inreferences/workflow/orchestration.md. Never hand-edit generated files. - Catalogue rows need a link, licence and status (
✓ <date>only after checking the official source, elseK). - Changing
verify_page.py? Add a case toevals/fixtures/bad.htmland runpython scripts/test_tools.py(needs Playwright). - Modern Web Guidance (MWG) is the authority for web implementation.
skills/modern-web-guidance/is Google's skill vendored verbatim: never edit it; refresh withpython scripts/sync_mwg.py. In DENT files, don't write HTML/CSS/JS technique that MWG covers; keep the design layer and point to the guide asmwg:<id>(validate checks the ids). DENT text that contradicts MWG is a bug: fix it and list it inreferences/modern-web-guidance.md§6. - README visuals come from
assets/build_assets.py; regenerate, don't hand-edit the SVGs. - Architecture:
docs/ARCHITECTURE.md. DENT 2.0 audit/plan/progress:docs/dent-2/. - Run
python scripts/validate.pyafter every change; it must printOK. Keep SKILL.md under ~450 lines (router only). - Bump the version in
SKILL.mdmetadata,.claude-plugin/plugin.jsonand.claude-plugin/marketplace.jsontogether, and add aCHANGELOG.mdentry. - Don't put user-specific
DESIGN.mdfiles in this repo.
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.

