apoorvjain25

apoorvjain25/frontier

Plugin Claude Code

Plugin marketplace listing 1 plugin: frontier.

apoorvjain25/frontier

Plugin Claude Code

Standards written and audited by Claude Fable 5: make Opus, Sonnet, GPT, or Gemini produce work close to its bar. 21 craft rubrics, best-of-N candidates, convergence sweeps, a taste gate with permanent distillation.

apoorvjain25/frontier

Agent

Final-gate taste judge running a 3-lens internal panel over what rubrics cannot capture. Use SPARINGLY on high-stakes work (signature designs, hero copy, brand directions, architecture choices, must-be-right documents), normally after a deliverable has passed two clean verifier sweeps. Also use to rank best-of-N…

apoorvjain25/frontier

Agent

Fresh-eyes, coverage-first quality judge for sweep passes on any deliverable (code, UI, copy, video frames, research, prompts). Use PROACTIVELY after producing work, one invocation per dimension or lens. Give it the rubric (or the craft file path), the evidence (file paths, screenshot paths, run output), and the lens…

apoorvjain25/frontier

Skill Claude CodeCodex

Execute any task at frontier quality. Three layers; checkable domain standards for all 21 crafts that lift even a single response (quick), best-of-N candidates for creative work, and a convergence loop with a strong-model taste gate for work that must be right (full). Self-contained; bundles the protocol, every craft…

apoorvjain25/production-audit

Plugin Claude Code

Plugin marketplace listing 1 plugin: production-audit.

apoorvjain25/production-audit

Plugin Claude Code

Exhaustive production-readiness audit: diverse-angle discovery passes to convergence, evidence-grounded per-finding verification, claim-vs-code checks, one flat severity-tagged list with file:line evidence.

apoorvjain25/production-audit

Skill Claude CodeCodex

Exhaustive production-readiness audit of any codebase or product. Runs diverse-angle discovery passes until two consecutive passes find nothing new, adversarially verifies every finding against the real code, and reports one flat severity-tagged list with file:line evidence. No summary, no hedging.