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.
git clone --depth 1 https://github.com/OneSignal/onesignal-cursor-pluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/onesignal/onesignal-cursor-plugin/onesignal-safety)<a href="https://agentmods.dev/rules/onesignal/onesignal-cursor-plugin/onesignal-safety"><img src="https://agentmods.dev/badge/rules/onesignal/onesignal-cursor-plugin/onesignal-safety/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/onesignal/onesignal-cursor-plugin/onesignal-safety"><img src="https://agentmods.dev/badge/rules/onesignal/onesignal-cursor-plugin/onesignal-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00372 | $0.00372 |
| Opus 5.5 | $0.00149 | $0.00149 |
| Sonnet 5.5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
onesignal-safety 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 1mo 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.
What it actually says
OneSignal Safety Rules
When using OneSignal tools or generating OneSignal API code, treat sends and writes as customer-impacting operations.
Secrets
- Never ask the user to paste API keys, OAuth tokens, private keys, or other secrets into chat or source files.
- Never commit
.envfiles or real credentials. - Redact keys in logs, examples, screenshots, and support text.
Read Before Write
Prefer read-only checks before writes:
- Use health/config/reference tools before workflow-specific tools.
- Inspect existing segments, templates, messages, users, or journeys before creating duplicates.
- Surface app id, audience, channel, and object ids before any mutation.
Explicit Approval
Require clear user approval before:
- Sending or scheduling push, email, SMS, or in-app messages.
- Creating, updating, deleting, pausing, or activating segments, templates, journeys, users, subscriptions, aliases, live activities, or exports.
- Transferring subscriptions or making identity changes.
- Acting on production apps.
For message sends, the approval summary must include channel, app id, audience, estimated count when available, content, schedule/timezone, and whether this is a test send.
For large audiences or any production blast, ask for an extra confirmation after showing the estimated count.
Safer Defaults
- Default to read-only investigation when intent is ambiguous.
- Prefer test users, test segments, and test apps before broad sends.
- Do not assume "everyone" means every user record; clarify subscribed audience and channel.
- Do not bypass Cursor MCP approval prompts.
- If a OneSignal capability is unavailable through MCP, explain the limitation and provide dashboard/API guidance instead of inventing a tool.
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.
- 1mo ago First seen · 44 lines · 372 tokens per session scan A d0ce39cf860f
onesignal-safety is a cursor rule published in the GitHub repository OneSignal/onesignal-cursor-plugin (0 stars, last pushed 3mo ago), licensed MIT. It adds 372 tokens to every session, about $0.0015 per session on Opus 5.5. 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 cursor rules, from other repositories
dal-repository
Rules for working with DAL repositories in the Novu monorepo.
api-property-optionality-hygiene
Fix ApiProperty/ApiPropertyOptional optionality mismatches in DTO files; use for scheduled batch fixes or DTO edits.
safe-api-tests
NEVER run apps/api mocha tests without NODEENV=test — drops dev MongoDB.
clickhouse
Rules for working with ClickHouse analytics and trace logging.
testing
Rules for writing and running tests.
packages
Rules for working in the shared NPM packages.