From agentic-value-loops
Universal rules and invariants that every Agentic Value Loop must follow.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-value-loops:loop-invariantsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A loop is only "good" if every iteration satisfies **all** of these invariants.
A loop is only "good" if every iteration satisfies all of these invariants.
PLAN.md. (Phase 1).npm run version:validate MUST exit 0. No exceptions.ITERATION_LOG.md.npx claudepluginhub andersonlimahw/lemon-ai-hub --plugin agentic-value-loopsDiscovers, finds, audits, repairs, crafts, runs, debriefs, and publishes repeatable AI-agent loops. Analyzes code or coding threads for recurring work.
Conducts interactive interview to gather task details, generates PRD, and outputs optimized loop commands with phase tracking for Loop plugin.
Implements coding prompts end-to-end via a self-checking loop with separate Engineer and QA agents, generating tests, running regression suites, grading code quality, and creating stacked PRs.