mcp-email-management
AGENTS.md0 starsChanged 2 months agoMITView on GitHub
Guidance for AI agents working in this repository is found within the .agents directory at the root of the repository. Files which define the repo-specific instructions, conventions, and guardrails you should follow. If you're looking for "how to behave in this repo", start with the files in .agents/rules/. Use the rules as constraints and process guidance whenever you: AI agent skills can be found within the .agents/skills/ directory.
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 repositoryOne other file it gives its agents.
- dotnetSkill
The file
We split this AGENTS.md into the rules it gives an agent
10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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 18
If you're looking for "how to behave in this repo", start with the files in .agents/rules/.
- Distinctive: line 30
Use the rules as constraints and process guidance whenever you:
- Distinctive: line 32
Change code: follow repo conventions (style, structure, naming, frameworks).
- Distinctive: line 33
Make Git changes: follow commit/pull request expectations when applicable.
- Distinctive: line 35
Are uncertain: prefer the rules over assumptions.
- Very specific: line 40
Every rule file must include YAML frontmatter with at least name and description.
- Distinctive: line 42
Prefer applying the most relevant rule(s) to the current task context.
- Distinctive: line 43
If multiple rules apply, resolve conflicts by:
- Very specific: line 56
Add more skills under .agents/skills/<name>/ for other languages, frameworks, or workflows.
- Distinctive: line 62
If skill files are added to the repository, read the relevant skill before performing specialized workflows it describes.
≈ “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
AI Agents
Guidance for AI agents working in this repository is found within the .agents directory at the root of the repository.
Documentation expectations
README.mdshould be human-focused and high-level.REQUIREMENTS.mdshould be maintained as a living Product Requirements Document with detailed project context that agents can update as understanding evolves.- Agents may maintain
.agents/FILES.mdto document important files and where they live so frequently needed files can be found quickly with fewer repeated searches.
Rules
Files which define the repo-specific instructions, conventions, and guardrails you should follow.
- Rules directory:
.agents/rules/ - Rule files:
*.mdand*.mdcfiles
If you're looking for "how to behave in this repo", start with the files in .agents/rules/.
Rule index (what to read when)
scope-of-work.md: Read at the start of any task to keep changes minimal, on-request, and reviewable.code-guidelines.md: Read before writing or reviewing code in any language.adopting-this-template.md: Read when bootstrapping a repo from this template or adding project-specific agent guidance.git-committing.md: Read before writing commit messages or creating commits.pull-requests.md: Read before preparing PR titles/descriptions or performing a PR/code review.
When to use the rules
Use the rules as constraints and process guidance whenever you:
- Change code: follow repo conventions (style, structure, naming, frameworks).
- Make Git changes: follow commit/pull request expectations when applicable.
- Review or propose changes: match the requested review tone/format and scope boundaries.
- Are uncertain: prefer the rules over assumptions; treat them as the source of truth for repo-specific preferences.
Rule format conventions
mdand.mdcfiles in.agents/rules/are authoritative instructions for agents.- Every rule file must include YAML frontmatter with at least
nameanddescription. - Set
alwaysApply: trueonly for rules that should apply to every task (for example,scope-of-work). - Prefer applying the most relevant rule(s) to the current task context.
- If multiple rules apply, resolve conflicts by:
- Prioritizing explicit user instructions first.
- Otherwise following repo scope/guardrails rules to keep changes minimal and reviewable.
Skills
AI agent skills can be found within the .agents/skills/ directory.
- Skills directory:
.agents/skills/
Skill index (what to read when)
dotnet/: Read before creating or editing C#/.NET code, solution/project layout, or .NET-specific review feedback.- Add more skills under
.agents/skills/<name>/for other languages, frameworks, or workflows.
When to use skills
- Load a skill when the task involves that stack or workflow (file types, frameworks, or user intent).
- Skills supplement rules; they do not replace universal guardrails like
scope-of-work.md. - If skill files are added to the repository, read the relevant skill before performing specialized workflows it describes.
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.

