agents
AGENTS.md8 starsChanged 26 days agoApache-2.0View on GitHub
Use this information to guide your writing with empathy toward the user: In chat, plans, and PR bodies:
We split this AGENTS.md into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 3
When you open a pull request, fill the body from .github/pull_request_template.md.
- Distinctive: line 9
Use this information to guide your writing with empathy toward the user:
- Distinctive: line 20
Use short paragraphs or bullets, one idea each.
≈ “Common” is an estimate: at least 1 in 5 of the 36,368 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
Pull requests
- When you open a pull request, fill the body from
.github/pull_request_template.md.
Writing for the user
Who the user is
Use this information to guide your writing with empathy toward the user:
- The user is a busy engineer.
- The user didn't see your exploration.
- The user doesn't necessarily have full context on the codebase.
Style
In chat, plans, and PR bodies:
- Lead with the answer, then give only the detail needed to act on it.
- Use short paragraphs or bullets, one idea each.
- Explain any term or finding from the codebase or your exploration the first time you use it, or leave it out.
- Say each thing once. Don't repeat reasoning across sections.
- Take longer to think and rewrite if it makes the writing clearer.
- Limit lines of text to approximately 80 characters. Add a new line as appropriate.
- This helps keep the git diffs more readable.
- In shell commands, you can use the \ character to wrap the line.
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 28,693 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 repository21 other files it gives its agents.
- mongodb-atlas-stream-processingSkill
- mongodb-connectionSkill
- mongodb-mcp-setupSkill
- mongodb-natural-language-queryingSkill
- mongodb-qe-size-estimationSkill
- mongodb-query-optimizerSkill
- mongodb-schema-designSkill
- mongodb-search-and-aiSkill
- mongodb-connectionSkill
- mongodb-natural-language-queryingSkill
- mongodb-query-optimizerSkill
- mongodb-schema-designSkill
- mongodb-search-and-aiSkill
- agent-engine-feature-validationsSkill
- agent-engine-troubleshoot-deploySkill
- atlas-agent-engine-docsSkill
- atlas-agent-engineSkill
- chat-sdk-add-adapterSkill
- chat-sdkSkill
- deploy-mongodb-agentsSkill
- gh-stackSkill
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.