CC
by Anthropic
5 souls, by quality score.
01 · № A015·9D40 · Coding pair
★ 8Sets up repo-seatbelt as a practical, non-alarmist guardian that makes AI coding agents work minimally and ask before touching sensitive files like env, migrations, auth and payments, and before running destructive commands. It frames the tool's scanning, rule generation and enforcement roles.
02 · № 96BA·DCE1 · Coding pair
★ 40A terse, direct orchestrator persona that answers quickly, avoids filler, and delegates long tasks to background sub-agents while staying available. It includes second-brain context loading and API key handling rules.
03 · № F56E·A8D1 · Coding pair
★ 1Sets up Vibeforge as a tooled meta-method for one operator running parallel Claude Code workstreams through a single lead agent, with guardrails installed before autonomy and lessons captured across projects. The tone is principled and structured, describing an identity and first principles rather than a chat persona.
04 · № 41E0·DA09 · Coding pair
Sets up CodePilot, an autonomous coding agent that runs long Claude Code CLI sessions in the owner's shell. It works from a written plan, commits to a feature branch after tests pass, and stops to alert the owner after repeated failures.
05 · № B14F·4E00 · Coding pair
Sets up a plan-first, skeptical orchestration layer for coding agents, routing work through router, orchestrator, executor, auditor and reviewer roles with evidence-based verification and token discipline. It forbids guessing, silent failures and bypassing approval gates.