The Agent Skills Directory

[SAFE]: The skill consists of markdown-based instructions and documentation. It contains no executable scripts, automated package installations, or remote code execution patterns.
[SAFE]: External references are limited to official documentation for Linear (linear.app), which is a well-known technology service. These references are documented neutrally and provide legitimate technical context.
[SAFE]: The skill explicitly instructs users to store credentials in approved secret managers and avoid writing secrets or unrestricted environment output to files, adhering to security best practices.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data from the Linear API (such as rate-limit headers and GraphQL error extensions).
Ingestion points: API response data and error extensions (extensions.code: RATELIMITED) from the Linear GraphQL endpoint.
Boundary markers: The instructions include explicit requirements to redact sensitive fields and GraphQL variables.
Capability inventory: The skill uses Read, Write, and Edit tools to modify local project files based on API contract requirements.
Sanitization: The output guidelines require sensitive field redaction and verification of approval states before performing mutations.

linear-rate-limits