Turn security findings into bounded agent work: one recipe, scoped context, required proof, and a human-reviewed result.
These files are stevologic/security-recipes.ai's own configuration. They tell Codex, OpenCode and GitHub Copilot how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md A 758 tok .github/prompts/ai-issue-maintenance.md A — .github/prompts/ai-maintenance.md A — .github/prompts/content-refresh.md A — .github/prompts/leftover-review.md A —