agentmailer-plugins
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
AgentMailer is identity and communication infrastructure for AI agents. It is not a workflow engine or an agent workspace. Keep model calls, tool execution, schedules, checkpoints, and business approvals in the calling runtime. - Treat top-level skill directories as the authoring source for skills.sh. - Treat skills/ as a generated client export. Update it with the repository's generation scripts instead of editing exported skills independently. - Treat fern/openapi/openapi.json as a reviewed snapshot of https://api.agentmailer.ai/openapi.json. Run the sync check before changing…
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 repository28 other files it gives its agents.
- agent-email-patternsSkill
- agentmailer-a2aSkill
- agentmailer-check-emailSkill
- agentmailer-cliSkill
- agentmailer-emailSkill
- agentmailer-eventsSkill
- agentmailer-inboxSkill
- agentmailer-manage-inboxesSkill
- agentmailer-mcpSkill
- agentmailer-sdkSkill
- agentmailer-securitySkill
- agentmailer-send-emailSkill
- agentmailerSkill
- agentmailer-toolkitSkill
- agent-email-patternsSkill
- agentmailer-a2aSkill
- agentmailer-check-emailSkill
- agentmailer-cliSkill
- agentmailer-emailSkill
- agentmailer-eventsSkill
- agentmailer-inboxSkill
- agentmailer-manage-inboxesSkill
- agentmailer-mcpSkill
- agentmailer-sdkSkill
- agentmailer-securitySkill
- agentmailer-send-emailSkill
- agentmailerSkill
- agentmailer-toolkitSkill
The file
We split this AGENTS.md into the rules it gives an agent
9 rules. About 2 are common, 1 is distinctive, and 6 are very specific to this project.
≈2
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 9
Treat top-level skill directories as the authoring source for skills.sh.
- Very specific: line 10
Treat skills/ as a generated client export.
- Very specific: line 12
Treat fern/openapi/openapi.json as a reviewed snapshot of https://api.agentmailer.ai/openapi.json.
- Very specific: line 15
Do not hand-edit generated API methods under sdk/.
- Very specific: line 16
Keep the portable Agent Plugins manifest at plugin.json and the hosted Streamable HTTP MCP connection at mcp.json standards-conformant.
- Common: line 21
Never guess API fields, MCP tools, permissions, or credentials.
- Common: line 23
Never print or commit AgentMailer access tokens, API keys, mailbox passwords, approval codes, or webhook signing secrets.
- Distinctive: line 25
Use stable idempotency keys for retried writes.
- Very specific: line 30
Run pnpm validate after changing manifests, skills, examples, SDK metadata, or client exports.
≈ “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 instructions
AgentMailer is identity and communication infrastructure for AI agents. It is not a workflow engine or an agent workspace. Keep model calls, tool execution, schedules, checkpoints, and business approvals in the calling runtime.
Source boundaries
- Treat top-level skill directories as the authoring source for skills.sh.
- Treat
skills/as a generated client export. Update it with the repository's generation scripts instead of editing exported skills independently. - Treat
fern/openapi/openapi.jsonas a reviewed snapshot ofhttps://api.agentmailer.ai/openapi.json. Run the sync check before changing generated clients. - Do not hand-edit generated API methods under
sdk/. - Keep the portable Agent Plugins manifest at
plugin.jsonand the hosted Streamable HTTP MCP connection atmcp.jsonstandards-conformant.
Safe integration behavior
- Never guess API fields, MCP tools, permissions, or credentials. Use the published OpenAPI and MCP schemas.
- Never print or commit AgentMailer access tokens, API keys, mailbox passwords, approval codes, or webhook signing secrets.
- Use stable idempotency keys for retried writes.
- Preserve human approval for agent signup and externally consequential sends.
Validation
Run pnpm validate after changing manifests, skills, examples, SDK metadata, or
client exports. Run the relevant generated-client checks for SDK or CLI changes.
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.