Before your agent touches a file, this runs abyss CLI to show you what else depends on it. You get caller traces with confidence scores, hotspot metrics, coupled files that change together, and test coverage gaps. The hook auto-fires on edits so high-risk changes surface warnings before they ship. Works across Claude Code, Codex, Gemini, and others via shell access. The confidence tiering is smart: 1.0 for same-file calls down to 0.7 for ambiguous matches, so you know what's reliable versus a hint. If you've ever broken production because you didn't know a utility function had 500 transitive callers, this catches that.
npx -y skills add telagod/code-abyss --skill indexing-code --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot