Python runtime checks for AI agents: budgets, loops, retries, and local traces. Zero runtime dependencies. MIT.
Latest release v2.0.0 · 6 Oct 2026
11 files for Claude Code, GitHub Copilot, Codex and OpenCode: dashboard-dev, marketing, pm, sdk-dev and 7 more — 6,645 tokens loaded in every session.
.github/copilot-instructions.md A 338 tok AGENTS.md A 4,792 tok CLAUDE.md A 1,515 tok .claude/settings.json A — .claude/settings.json A — .agents/skills/next-ticket/SKILL.md A 93 tok .claude/commands/next-ticket.md A 21 tok .claude/agents/dashboard-dev.md A — .claude/agents/marketing.md A — .claude/agents/pm.md A 27 tok .claude/agents/sdk-dev.md A 30 tok These files are bmdhodl/agent47's own configuration — they tell Claude Code, GitHub Copilot, Codex and OpenCode 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.