jeredblu-marketplace

Comprehensive security and safety evaluation system for agent skills (.skill files). Use when users provide GitHub URLs, website links, or .skill files for download and request security assessment, safety evaluation, or ask "is this skill safe to use." Evaluates prompt injection, malicious code, hidden instructions, data exfiltration, auto-execution (hooks/installers/MCP), remote execution (curl|sh), phone-home callbacks, credential access, forced promo/backlink output pollution, and project infection — then front-loads every trust-relevant finding in a standalone chat verdict with risk scoring.

Use when running on Claude Fable (or any premium model) and the work is token-heavy — building features, multi-file changes, research, testing, debugging, migrations, or anything spanning many files/sources. Keeps Fable on the judgment (decompose, architect, synthesize, review) and delegates bounded, verifiable heavy-lifting to cheaper models (Haiku/Sonnet/Opus) — with a quality floor so construction work is never owned by a weak agent. Triggers on requests to "be efficient with Fable", "don't burn tokens", orchestrate subagents, or delegate work. Also fires on cross-CLI delegation: "delegate to Codex", "use Codex/GPT for this", "second opinion from Codex", or offloading work to a separate Codex/ChatGPT quota.

Create comprehensive PRDs through conversational discovery. Use when users want to plan software projects, document requirements, or prepare specifications. Supports beginners to experienced PMs. Asks clarifying questions to gather requirements, researches technologies, and produces structured markdown PRDs.

Comprehensive security and privacy evaluation system for MCP (Model Context Protocol) servers. Use when users provide GitHub URLs to MCP servers and request security assessment, privacy evaluation, or ask "is this MCP safe to use." Evaluates security vulnerabilities, privacy risks, code quality, community feedback, and provides actionable recommendations with risk scoring.