The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses node and bash via the Bash tool to resolve feature context and perform git operations. These are standard development tasks within the scope of an architecture design tool.- [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads from untrusted sources. It relies on internal project files and well-known tools like git, node, and internal agent capabilities.- [DATA_EXFILTRATION]: No data exfiltration patterns were found. The skill includes an explicit constraint to 'Redact credentials/secrets per @rules/security.md' during the architecture design phase, demonstrating security awareness.- [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters or override system prompts. It uses standard instructional language to guide the agent through a complex workflow.- [REMOTE_CODE_EXECUTION]: There are no patterns of fetching and executing remote scripts (e.g., curl | bash). All execution is local to the project environment.- [CREDENTIALS_UNSAFE]: No hardcoded credentials were found. The skill proactively instructs the agent to avoid including sensitive data in the generated documentation.

architecture