The Agent Skills Directory

[SAFE]: The analyzed file is a documentation resource providing guidance on managing the context window of language models. It does not perform any functional operations or introduce security risks.
[NO_CODE]: There are no executable scripts, shell commands, or automation tasks defined in this skill. The examples provided are static markdown snippets for prompt organization.
[CREDENTIALS_SAFE]: No hardcoded secrets, API keys, or sensitive environmental paths are present. The documentation specifically includes security best practices, such as redacting secrets before they are stored in context or summaries.
[REMOTE_CODE_EXECUTION]: No external URLs, remote script downloads, or package installation commands are present in the file.
[PROMPT_INJECTION]: The content does not contain instructions that attempt to override agent behavior, bypass safety filters, or extract system prompts. It focuses on clarifying the agent's identity and constraints via structured system prompts.

context-fundamentals