publish-mcp-server-claude-chatgpt
AGENTS.md1 starsChanged 7 days agoMITView on GitHub
This repo is a set of agent skills, not an app. Rules that keep it installable in both Claude Code and Codex and listable in both stores' directories: - One folder per skill under skills/, with SKILL.md whose name equals the folder name. - Front matter uses only the Agent Skills fields: name, description, license, compatibility, metadata (and the experimental allowed-tools). Claude-Code-only fields break uploads to claude.ai and the API. - Keep SKILL.md under 500 lines; put detail in the…
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 31,542 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 repository8 other files it gives its agents.
- mcp-app-cardsSkill
- mcp-server-for-pluginsSkill
- plugin-oauthSkill
- plugin-packageSkill
- plugin-prerequisitesSkill
- publish-mcp-serverSkill
- submit-to-chatgptSkill
- submit-to-claudeSkill
The file
We split this AGENTS.md into the rules it gives an agent
4 rules. About 1 is common, 1 is distinctive, and 2 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈1
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 10
Keep SKILL.md under 500 lines.
- Common: line 12
No hooks (they rule a plugin out of OpenAI's directory), no symlinks, no secrets, no submodules.
- Distinctive: line 16
Every factual claim about a store should be something a store page or a real submission showed.
- Very specific: line 18
Run python3 scripts/validate_skills.py before committing.
≈ “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
Working in this repo
This repo is a set of agent skills, not an app. Rules that keep it installable in both Claude Code and Codex and listable in both stores' directories:
- One folder per skill under
skills/, withSKILL.mdwhosenameequals the folder name. - Front matter uses only the Agent Skills fields:
name,description,license,compatibility,metadata(and the experimentalallowed-tools). Claude-Code-only fields break uploads to claude.ai and the API. - Keep
SKILL.mdunder 500 lines; put detail in the skill's ownreferences/and tools in itsscripts/. Don't share files across skills: per-skill installs copy only the skill's folder. - No hooks (they rule a plugin out of OpenAI's directory), no symlinks, no secrets, no submodules.
- Bump
versionin.claude-plugin/plugin.json,.codex-plugin/plugin.jsonand the marketplace together. - Every factual claim about a store should be something a store page or a real submission showed. Note the month it was checked.
- Run
python3 scripts/validate_skills.pybefore committing.
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.