Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/nylas/skills/agents-mdgit clone --depth 1 https://github.com/nylas/skillsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00563 | $0.00563 |
| Opus 5 | $0.00282 | $0.00282 |
| Sonnet 5 | $0.00113 | $0.00113 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
skills AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents (Claude Code, Cursor, Copilot, etc.) when working with the Nylas platform.
Repository Overview
Skills for building with the Nylas platform — email, calendar, and contacts APIs. Skills follow the Agent Skills format.
Available Skills
nylas-api
Build email, calendar, and contacts integrations with the Nylas v3 API.
Use when: code imports nylas/@nylas/nylas/nylas-python, or user asks about Nylas API, OAuth grants, webhooks, scheduler, notetaker, smart compose, transactional send.
Covers: Authentication (6 methods), Security & Prompt Safety (grant-scoped API data), Email (messages/threads/drafts/tracking/smart compose/templates), Calendar (events/availability/recurring/conferencing), Contacts, Webhooks & Pub/Sub, Scheduler (70+ UI components), Notetaker (meeting bot setup/AI notes), Admin (grants/connectors/API keys/domains), SDKs (Node.js/Python/Ruby/Kotlin), Best Practices (rate limits with numbers, error codes).
nylas-cli
Manage email, calendar, and contacts from the terminal with the Nylas CLI.
Use when: user mentions nylas init, nylas email, nylas calendar, nylas auth, nylas mcp, nylas tui, nylas air.
Covers: Setup & config, authentication, email (read/send/search/AI), calendar (events/RSVP/AI scheduling), contacts, webhooks, inbound email, dashboard management, TUI/Air/MCP/demo mode.
Key Context
- v3 only. v2 is deprecated.
- Base URLs:
api.us.nylas.com(US) /api.eu.nylas.com(EU) - A grant = authenticated user account connected through Nylas.
- Docs:
https://developer.nylas.com/llms.txt
Skill Structure
Each skill contains:
SKILL.md— Concise rules index with doc links (loaded on activation)AGENTS.md— Full compiled referenceCLAUDE.md— Claude Code auto-loaded contextrules/— Individual rule files, read on demand
Context Efficiency
SKILL.mdis the index (<100 lines) — not the content dump- Rules are individual files — agents read only what's relevant
- Doc links point to
developer.nylas.com/docs/...for always-current details
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 47 lines · 563 tokens per session scan A a26d951f123d
skills AGENTS.md is an instructions file published in the GitHub repository nylas/skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 563 tokens to every session, about $0.0028 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
olkcli CLAUDE.md
Instructions for rlrghb/olkcli, covering claude.md, what is this project?, quick reference, architecture and key patterns.
olkcli AGENTS.md
Instructions for rlrghb/olkcli, covering repository guidelines, project structure, build, test, and development commands, coding style & naming conventions and testing guidelines.
outlook-ews-mcp AGENTS.md
Instructions for viartemev/outlook-ews-mcp, covering agents.md, engineering rules, project shape, testing and conventions.
apple-pim AGENTS.md
Instructions for omarshahine/apple-pim, covering apple pim plugin, quick commands, initial setup, swift clis and mcp server.
apple-pim copilot-instructions.md
Instructions for omarshahine/apple-pim: See ../AGENTS.md for shared repository instructions.
apple-pim CLAUDE.md
Instructions for omarshahine/apple-pim, a project described as: Native macOS integration for Calendar, Reminders, and Contacts using EventKit and Contacts frameworks.