The Agent Skills Directory

[DYNAMIC_CONTEXT_INJECTION]: The skill utilizes the load-time execution syntax (!command) to run a local script, yaml-helper.sh, located in the project's hooks directory. This command resolves project-specific configuration keys (performance.enforce, automation, workflow) before the session begins. The execution is limited to a local file within the skill's own environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external project data, which presents a surface for indirect prompt injection.
Ingestion points: The skill reads source code, profiler outputs, test results, and data files via Read, Glob, and Grep tools.
Boundary markers: There are no explicit instructions to use delimiters or to ignore instructions that might be embedded within the analyzed source code or data files.
Capability inventory: The skill has the ability to write to the filesystem (Write) and execute restricted bash commands (Bash).
Sanitization: The instructions do not specify any sanitization or validation steps for the content ingested from the codebase.
[COMMAND_EXECUTION]: The skill executes a local utility script (yaml-helper.sh) using the Bash tool to retrieve performance budgets and configuration from YAML files. These executions are constrained to specific helper functions and are intended for project-internal configuration resolution.

perf-profile