boring-react
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
This repository publishes portable Agent Skills for production React engineering. Prefer the smallest coherent change. Add a new skill only when its trigger domain is distinct enough that loading it separately saves context or prevents conflicting instructions.
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 repository5 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- react-component-engineeringSkill
- react-motion-engineeringSkill
- react-production-engineeringSkill
- react-quality-engineeringSkill
The file
We split this AGENTS.md into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 7
Keep each skills/*/SKILL.md concise.
- Very specific: line 8
Follow the open Agent Skills directory contract: SKILL.md is required.
- Distinctive: line 9
Never duplicate large guidance across skills.
- Distinctive: line 10
Do not weaken an engineering invariant merely to satisfy an eval.
- Very specific: line 11
Run npm run check after changing skill metadata, references, scripts, fixtures, or eval cases.
- Distinctive: line 24
Prefer the smallest coherent change.
≈ “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
Agent guide
This repository publishes portable Agent Skills for production React engineering.
Start here
- Keep each
skills/*/SKILL.mdconcise; detailed doctrine belongs in itsreferences/directory. - Follow the open Agent Skills directory contract:
SKILL.mdis required;references/,scripts/, andassets/are optional. - Never duplicate large guidance across skills. Link to a focused reference instead.
- Do not weaken an engineering invariant merely to satisfy an eval.
- Run
npm run checkafter changing skill metadata, references, scripts, fixtures, or eval cases.
Repository commands
npm run validate— validate skill and eval structure.npm test— run deterministic repository tests.npm run check— run both.npm run detect -- <path>— detect a React project stack.npm run quality -- <path>— run adaptive project quality gates.npm run eval:list— list behavioral eval cases.
Change policy
Prefer the smallest coherent change. Add a new skill only when its trigger domain is distinct enough that loading it separately saves context or prevents conflicting instructions.
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.