The Agent Skills Directory

[SAFE]: The skill follows security best practices by explicitly instructing the agent to spawn subagents with isolated contexts (fork_context: false). This design ensures that private or irrelevant conversation history is not leaked to the subagents.
[SAFE]: The briefing process for subagents is designed to use neutral problem statements. This serves as a prompt-level boundary that reduces the risk of propagating malicious instructions or biases from the main conversation context to the fresh subagent instances.
[SAFE]: All external references (GitHub repository and license links) belong to the skill's author, Augustin BENGOLEA (bengous), and are provided in plain text without obfuscation.

council