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/port-labs/port-skillsWrote 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/port-labs/port-skills/port-safety)<a href="https://agentmods.dev/rules/port-labs/port-skills/port-safety"><img src="https://agentmods.dev/badge/rules/port-labs/port-skills/port-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/port-labs/port-skills/port-safety"><img src="https://agentmods.dev/badge/rules/port-labs/port-skills/port-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 | $0.00196 | $0.00196 |
| Opus 5 | $0.00098 | $0.00098 |
| Sonnet 5 | $0.00039 | $0.00039 |
| Haiku 4.5 | $0.00020 | $0.00020 |
Grade A, and why
port-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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- port-safety — 100% identical, 0 lines differ
What it actually says
Port MCP rules
Knowledge lookup
Before answering any question about Port concepts (blueprints, scorecards, entities, actions, workflows, integrations, relations, properties, permissions) or before taking any action that requires Port-specific knowledge, call search_port_knowledge_sources with the relevant query.
Do not rely on training data alone for Port-specific behavior, configuration options, or API semantics. Always verify against the official documentation first.
Write confirmation
Before calling any tool that creates, updates, deletes, or triggers anything in Port, confirm the operation with the user first.
Confirmation must include:
- What will change and on which resource
- Whether the operation is reversible
- An explicit user approval before the tool call is made
Do not proceed with write operations based on implied intent.
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.
- 11d ago First seen · 25 lines · 196 tokens per session scan A 31f19b4799dd
port-safety is a cursor rule published in the GitHub repository port-labs/port-skills (3 stars, last pushed 8d ago), licensed MIT. It adds 196 tokens to every session, about $0.0010 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 cursor rules, from other repositories
ceramic-design-system
Ceramic Design System rules.
publisher
Publish HTML frontend projects to the publishing platform (publisher). Use when the user wants to publish/ship a project, get an access URL, list their published projects, or build an Android APK. No Python required — call the HTTP APIs directly.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.