The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes and executes instructions derived from external project files. * Ingestion points: The agent reads content from PLAN.final.md, PRINCIPLES.md, AGENTS.md, and CONTRIBUTING.md (SKILL.md). * Boundary markers: The skill relies on the .final.md file extension as an indicator of an approved plan (SKILL.md). * Capability inventory: The skill possesses the ability to write code, execute git commands, and run project-specific verification tools such as linters and test suites (SKILL.md). * Sanitization: There is no mention of sanitizing or filtering the natural language instructions within these plan files before implementation (SKILL.md).
[COMMAND_EXECUTION]: The skill executes shell commands to perform git operations (git fetch, git log, git commit) and to run local verification tools including linters, formatters, and test suites.

execute-plan