The Agent Skills Directory

[PROMPT_INJECTION]: Indirect prompt injection surface identified where malicious instructions in analyzed source code could potentially influence agent behavior.
Ingestion points: The skill reads project source code, documentation, and configuration files using Read, Grep, and Glob tools (SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when reading external file content.
Capability inventory: The skill has access to powerful tools including Bash (shell execution), Edit (file modification), and Task (subagent and task creation).
Sanitization: No content sanitization or filtering is defined for the data ingested from the codebase.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute git diff commands to identify modified files for simplification.
[COMMAND_EXECUTION]: The skill invokes a local Python utility script (.claude/scripts/code_graph) to perform structural analysis and dependency tracing within the repository.

code-simplifier