The Agent Skills Directory

[SAFE]: The skill provides purely behavioral instructions for minimalist coding practices (YAGNI) and does not include any executable code, scripts, or network-enabled commands.
[SAFE]: Instructions explicitly mandate the preservation of security-critical code, stating that "code that guards a trust boundary (validation, error paths, security, access control) is never the place to prove [restraint]."
[SAFE]: The allowed-tools section (Read, Grep, Glob) in the frontmatter limits the agent's tool access, adhering to the principle of least privilege within the skill context.
[SAFE]: The skill contains no network operations, external downloads, or attempts to access sensitive system files.
[SAFE]: No obfuscation, persistence mechanisms, or privilege escalation patterns were detected.

restraint