This agent helps Python teams using the Anthropic or OpenAI SDK safely cut LLM spend without risking regressions. With zero code changes, it maps call sites and runs your test scenarios to rank token waste from missed prompt caching or heavy model tiers. It tests fixes in isolated git worktrees, enforcing a strict "do-no-harm" gate that reverts any patch failing to preserve behavior. It delivers a clear savings audit that converts into verified, behavior-preserving code patches upon opt-in.
Built around the parts of API integration everyone skips until 3am: token refresh, pagination to the last page, 429 rate-limit handling, retries with backoff + jitter, idempotency keys so a retry doesn't double-charge, timeouts, and typed error handling. It reads the API's own docs, matches your stack, keeps keys in env, and produces a client that survives the network blinking — not a naive fetch that falls over the first time the API throttles you.
Vibe Code Reviewer — Reviews AI-generated code for the mistakes that sink vibe-coded apps: exposed API keys, missing auth, SQL injection, client-trusted payments. Built for non-engineers — plain-language findings, severity ratings, copy-paste fixes. Catches the security holes behind the "45% of AI code is vulnerable" stat before you ship.
You shipped AI features — then the bill arrives, and every free user who never converts eats your Anthropic budget 24/7. This is the complete, production-tested Supabase + Claude backend that stops that: API key hidden from every iPhone, JWT-verified Edge Functions, 3-layer rate limiting, free-tier caps + cheap-model routing, caching (40–60% off), cost alerts — plus full Swift integration and a debug playbook. Built from a live ¥480/month app. Pairs with StoreKit 2 & Rejection Buster.
要件が曖昧なまま開発に渡していませんか？ Requirement Ready AI は、目的、機能範囲、業務ルール、入力チェック、権限、UI、API、例外、エッジケースを確認し、User Story、Acceptance Criteria、QA Test Cases、リスクまで整理します。 開発開始前に「本当に Ready か」を確認するための要件レビュー支援ツールです。
Turn vague product requirements into clear, implementation-ready specifications. When key information is missing, Agile ScopeGuard Pro identifies gaps and asks focused questions before generating relevant deliverables such as PRDs, User Stories, Functional Specifications, Acceptance Criteria, QA Test Cases, API Specifications, Workflows, Risk Analysis, and Implementation Checklists. Built to reduce ambiguity, prevent Scope Creep, and minimize costly rework.
Turn customer reviews, testimonials, comments, and survey feedback into evidence-based sales assets. ReviewFuel AI extracts customer themes, purchase triggers, objections, and recurring language, then creates ad hooks, product-page copy, three ad variants, FAQs, and a Claim Safety Check without inventing product facts.
Backend integration engineering: typed clients with the production resilience layer—retry/backoff, idempotency, rate-limiting, webhook signature verification, mock server and offline tests—that SDK generators skip.
Supabase RLS Security Auditor assesses and audits Supabase apps across RLS, Auth/IAM, data security, APIs, Edge Functions, storage, secrets, third-party integrations, governance, logging, and security operations. Built for founders, vibe-coded apps, SaaS teams, and builders preparing to launch. Returns prioritized findings, exploit paths, safe SQL/architecture fixes, regression tests, and launch-blocker guidance.