The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute mewt and muton CLI commands as well as project-specific test commands (e.g., cargo test, npm test, go test). This is the primary and intended function of the skill for running mutation tests.
[DATA_INGESTION_SURFACE]: The skill interprets project configuration and source code to define the scope of testing, which constitutes a surface for indirect prompt injection.
Ingestion points: The agent is instructed to read mewt.toml, package.json, Makefile, and project source files in workflows/configuration.md and references/optimization-strategies.md.
Boundary markers: Absent. No specific delimiters are recommended for wrapping untrusted project data.
Capability inventory: Includes Bash (command execution), Write (configuration modification), and Read (file inspection).
Sanitization: Absent. The skill directs the agent to execute commands discovered within project files (like test commands in mewt.toml) without explicit sanitization or validation logic.

mutation-testing