PageproPagepro/nexity/AGENTS.md

nexity

AGENTS.md19 starsChanged 9 days agoMITView on GitHub

This repository holds two independent starters, base/ and theme-meridian/, plus the agent layer in .agents/. Each starter has its own AGENTS.md, DESIGN.md and BRAND.md; work inside one starter by its own files. - A fix goes into both starters in the same change (schemas, GROQ, preview, SEO, a section bug, a rule in AGENTS.md or docs/agents/). Only the look and content of one starter stay in one folder. See CONTRIBUTING.md → "Fixes go to both starters". - Neither starter mentions…

In this repository21 other files it gives its agents.
- base/AGENTS.mdAGENTS.md
- theme-meridian/AGENTS.mdAGENTS.md
- base/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- theme-meridian/CLAUDE.mdCLAUDE.md
- blog-post-quality-reviewSkill
- blog-post-updateSkill
- brand-kitSkill
- create-sectionSkill
- generate-altsSkill
- internal-linksSkill
- link-fixSkill
- marketing-setupSkill
- product-mockSkill
- project-setupSkill
- pr-writeupSkill
- sanity-module-catalogSkill
- sanity-optimizationsSkill
- site-contradictionsSkill
- source-reviewSkill
- work-humanizerSkill

The file

Create a free account to mount

Files

AGENTS.md

AGENTS.md (repository)

This repository holds two independent starters, base/ and theme-meridian/, plus the agent layer in .agents/. Each starter has its own AGENTS.md, DESIGN.md and BRAND.md; work inside one starter by its own files.

A fix goes into both starters in the same change (schemas, GROQ, preview, SEO, a section bug, a rule in AGENTS.md or docs/agents/). Only the look and content of one starter stay in one folder. See CONTRIBUTING.md → "Fixes go to both starters".
Neither starter mentions the other. A project is made from one of them and never sees the other folder.
No comments that restate the code, in the starters and in .agents/ scripts alike: only workarounds, must-know constraints and "change it here" hints (each starter's AGENTS.md → "Code design").
Skills and reviewers live in .agents/; .claude/ holds only symlinks to it. base/.agents/ and theme-meridian/.agents/ are generated snapshots: edit the root source, then run node .agents/export.mjs and commit both snapshots.
A marketer asking to set up the marketing skills ("Help me setup these skills for marketers") gets .agents/skills/marketing-setup/SKILL.md, even when the agent does not list it (a ZIP can break the .claude/skills link). See MARKETING-SKILLS-README.md.
Keep each starter's root + web/ AGENTS.md under ~30 KB together: Codex reads 32 KiB per directory chain, this file included.

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free