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 commands/nylas/cli/agent-policygit clone --depth 1 https://github.com/nylas/cliWhat 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 | $0.01064 |
| Opus 5 | $0.00000 | $0.00532 |
| Sonnet 5 | $0.00000 | $0.00213 |
| Haiku 4.5 | $0.00000 | $0.00106 |
Grade A, and why
agent-policy 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 3d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Policies
Detailed reference for nylas agent policy.
Policies are application-level resources backed by /v3/policies. They attach to workspaces via policy_id.
Commands
nylas agent policy list
nylas agent policy create --name "Strict Policy"
nylas agent policy create --data-file policy.json
nylas agent policy get <policy-id>
nylas agent policy read <policy-id>
nylas agent policy update <policy-id> --name "Updated Policy"
nylas agent policy update <policy-id> --data-file update.json
nylas agent policy delete <policy-id> --yes
Listing Policies
nylas agent policy list
nylas agent policy list --json
Lists all policies from /v3/policies. Text output shows which workspace has each policy attached.
Reading Policies
nylas agent policy get <policy-id>
nylas agent policy read <policy-id>
nylas agent policy read <policy-id> --json
Notes:
getandreadare aliases- text output expands the policy into readable sections for:
- rules
- limits
- options
- spam detection
--jsonreturns the raw API payload
Use --json when you need the exact field names for automation or a follow-up update.
Creating Policies
Simple Create
nylas agent policy create --name "Strict Policy"
nylas agent policy create --name "Strict Policy" --json
This is the fastest path when you only need a named policy object and will add rules or settings later.
Full JSON Create
nylas agent policy create --data-file policy.json
nylas agent policy create --data '{"name":"Strict Policy","rules":["rule-123"]}'
Every limit is optional: omitted limits default to your billing plan's maximum, and values above the plan maximum are rejected by the API.
Example payload:
{
"name": "Strict Policy",
"rules": ["rule-123"],
"limits": {
"limit_attachment_size_limit": 50480000,
"limit_attachment_count_limit": 10,
"limit_count_daily_message_per_grant": 500,
"limit_inbox_retention_period": 30,
"limit_spam_retention_period": 7
},
"spam_detection": {
"use_list_dnsbl": false,
"use_header_anomaly_detection": false,
"spam_sensitivity": 1
}
}
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.
- 3d ago First seen · 168 lines · 0 tokens per session scan A cbe56ba42445
agent-policy is a command published in the GitHub repository nylas/cli (68 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,064 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.
Other commands, from other repositories
sonicjs-seo-blog
Generate a high-quality, SEO-optimized blog post for SonicJS on the topic: $ARGUMENTS.
calendars
Manage macOS calendar events - list, search, create, update, delete with batch operations.
jk-status
Every organization: open closes, deadlines, pending reviews.
drift
Run the drift check and report the result. If it fails, identify which file has the stale reference and fix it.
briefing
Get a daily briefing of today's calendar events, reminders, and optional inbox context.
execute-plan
Execute an implementation plan methodically with TDD and continuous validation.