agent

Command-line tools for managing Nylas agent accounts and the policies and rules that control them. Nylas agent accounts are managed email identities that do not require connecting a third-party mailbox.

In plain words
What is it for?
List, create, update, move, inspect, and delete Nylas agent accounts, policies, and rules from the command line.
Why use it?
They let developers manage agent email resources from scripts or a terminal instead of using separate API requests. They also expose account status and workspace assignment operations.

Command

Install

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.

agentmods
npx agentmods add commands/nylas/cli/agent
Clone the repo
git clone --depth 1 https://github.com/nylas/cli
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,793 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02793
Opus 5 $0.00000 $0.01396
Sonnet 5 $0.00000 $0.00559
Haiku 4.5 $0.00000 $0.00279

Measured yesterday against content hash 0aef9cce6209, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent 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 yesterday.

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.

docs/commands/agent.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent

Manage Nylas agent resources from the CLI.

New to agent accounts? Start with the getting started guide.

Agent accounts are managed email identities backed by provider nylas. Unlike OAuth grants, they do not require a third-party mailbox connection. Account operations live under nylas agent account, while nylas agent status reports connector and account readiness.

Commands

nylas agent account list
nylas agent account create <email>
nylas agent account update [agent-id|email] --app-password 'ValidAgentPass123ABC!'
nylas agent account get <agent-id|email>
nylas agent account move <agent-id|email> --workspace <workspace-id>
nylas agent account delete <agent-id|email>
nylas agent policy list
nylas agent policy create --name <name>
nylas agent policy get <policy-id>
nylas agent policy read <policy-id>
nylas agent policy update <policy-id> --name <name>
nylas agent policy delete <policy-id>
nylas agent rule list
nylas agent rule read <rule-id>
nylas agent rule create --name "Block Example" --condition from.domain,is,example.com --action mark_as_spam
nylas agent rule create --name "Archive outbound mail" --trigger outbound --condition recipient.domain,is,example.com --condition outbound.type,is,compose --action archive
nylas agent rule update <rule-id> --name "Updated Rule" --description "Block example.org"
nylas agent rule delete <rule-id>
nylas agent list list
nylas agent list get <list-id>
nylas agent list create --name "Blocked domains" --type domain --item spam.com
nylas agent list add <list-id> junk.net
nylas agent list remove <list-id> junk.net
nylas agent list delete <list-id> --yes
nylas agent overview
nylas agent status

Lists hold normalized values (domains, TLDs, or addresses) referenced by rule in_list conditions. Details: Agent list reference

List Agent Accounts

nylas agent account list
nylas agent account list --json

Example output:

$ nylas agent account list

Agent Accounts (2)

1. [email protected]            active
   ID: 11111111-1111-1111-1111-111111111111
   Workspace ID: aaaaaaaa-1111-1111-1111-111111111111

2. [email protected]                 active
   ID: 22222222-2222-2222-2222-222222222222
   Workspace ID: bbbbbbbb-2222-2222-2222-222222222222

Read the full file on GitHub · 292 lines

Changes

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.

  1. yesterday First seen · 292 lines · 0 tokens per session scan A 0aef9cce6209

Subscribe to this mod's changes

agent is a command published in the GitHub repository nylas/cli (68 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,793 tokens. 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 2026-08-30.