A command-line tool for managing Nylas agent rules, which automatically match email events and apply actions. It can list, read, create, update, and delete those rules.

Use it to review rule details, create filtering or archiving rules, change existing rules, and remove rules you no longer need.

It lets you inspect and maintain email automation rules from the terminal instead of managing each rule manually.

agent-rule — Command by nylas

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-rule

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 1,086 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.01086
Opus 5	$0.00000	$0.00543
Sonnet 5	$0.00000	$0.00217
Haiku 4.5	$0.00000	$0.00109

Measured 2d ago against content hash e0e4dda7fff8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-rule 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.

docs/commands/agent-rule.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Rules

Detailed reference for nylas agent rule.

Rules are backed by /v3/rules and attach to workspaces via rule_ids[].

Commands

nylas agent rule list
nylas agent rule get <rule-id>
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 create --data-file rule.json
nylas agent rule update <rule-id> --name "Updated Rule"
nylas agent rule delete <rule-id> --yes

Listing Rules

nylas agent rule list
nylas agent rule list --json

Lists all rules from /v3/rules. Text output shows which workspace has each rule attached.

Reading Rules

nylas agent rule get <rule-id>
nylas agent rule read <rule-id>
nylas agent rule read <rule-id> --json

Notes:

get and read are aliases
text output expands the rule into readable sections for trigger, match logic, actions, and workspace references
--json returns the raw rule payload

Creating Rules

You can create rules either from common-case flags or from raw JSON.

Common-Case Flags

nylas agent rule create \
  --name "Block Example" \
  --condition from.domain,is,example.com \
  --action mark_as_spam

nylas agent rule create \
  --name "VIP sender" \
  --condition from.address,is,[email protected] \
  --action mark_as_read \
  --action mark_as_starred

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 create \
  --name "File receipts" \
  --condition from.domain,is,billing.example.com \
  --action assign_to_folder=Receipts

The assign_to_folder value is a folder name — a custom folder's name (use its full path for a nested folder, e.g. Clients/Acme) or a system folder name (Inbox, Sent, Drafts, Trash, Junk, Archive). The name is resolved when the rule runs, so a reference to a folder that doesn't exist is skipped.

Read the full file on GitHub · 152 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.

2d ago First seen · 152 lines · 0 tokens per session scan A e0e4dda7fff8

Subscribe to this mod's changes

agent-rule is a command published in the GitHub repository nylas/cli (68 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,086 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.

Backend and APIs Code review Writing and docs ai ai-agents api calendar cli email

agent-rule

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Agent Rules

Commands

Listing Rules

Reading Rules

Creating Rules

Common-Case Flags

What this file has done since we first saw it

Other commands, from other repositories

create-pr

/release

numbers-to-excel

briefing

symfony-api-errors

execute-plan