The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads and refines content from an external source.
Ingestion points: BACKLOG.md is read in Step 1 to extract and refine items.
Boundary markers: No delimiters or instructions are used to prevent the agent from obeying instructions embedded in the backlog items.
Capability inventory: The skill has access to Read, Write, Edit, and Bash tools.
Sanitization: No content validation or sanitization is performed on the ingested text.
[COMMAND_EXECUTION]: The skill uses a bash command pipeline to calculate task totals from the generated output file.
Evidence: Step 5 includes a command using grep, sed, and awk to extract and sum hours from SPRINT-PLAN.md to ensure capacity alignment.

plan-sprint