The Agent Skills Directory

[DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the !ls production/sprints/ 2>/dev/null command within its YAML frontmatter. This command is executed at skill load time to provide the agent with a list of existing files for contextual awareness. The command is benign and does not involve sensitive file access, network operations, or user-supplied argument injection.
[COMMAND_EXECUTION]: The skill performs standard file system operations using authorized platform tools (Read, Glob, Grep, Write, Edit). These operations are consistent with the stated purpose of reading project milestones and scanning design documents to generate a sprint plan.
[SAFE]: No patterns of prompt injection, data exfiltration, obfuscation, or persistence were identified. The skill's behavior aligns with its documented metadata and utility.

sprint-plan