7 tagged agent-instructions, measured the same way as everything else here.
Skill Claude CodeCodex
Teaches AI agents to properly manage VS Code terminal lifecycle — always use background terminals and kill them after commands complete. Prevents zombie terminal accumulation in GitHub Codespaces and VS Code.
Skill Claude CodeCodex
Drive the botfile CLI to manage AI-agent skills, instructions, and commands. Use when asked to sync, plan, adopt, or check the status of agent components managed by botfile.
Skill Claude CodeCodex needs its repo
Validate AGENTS.md and related agent instruction files with the published agents-doctor CLI. Use when the user asks to check, lint, verify, explain, audit, fix, release-check, or compare AGENTS.md, CLAUDE.md, GEMINI.md, agent instruction inheritance, tool profiles, context fidelity, instruction graphs, GitHub…
Skill Codex
Reduction-first coding for every change, whether building, fixing, refactoring, or cleaning up. Delete, merge, or replace before adding, so the project ends up smaller and simpler without losing anything the app needs, in code and in the text around it. Matters most for cleanups, refactors, and larger changes.
Skill Claude Code
Audit a chair's composed Insitu protocol for contradictions, unresolved references, stale doctrine, unneeded weight, and shape. Use when asked to audit, review, or trim a protocol, when a chair's core feels heavy or wrong, or when two loaded rules seem to disagree. Produces a proposal and never edits. Not for…