agentic-stack

Multi-agent deep-research pipeline (orchestrator + parallel explorers + adversarial red-team). Tiered search via Exa/SearXNG/WebSearch, optional Obsidian-wiki filing and knowledge-graph. Tunable via deep-research/program.md.

Find the best product on the market in any category across major retailers. Parallel research explorers + a deterministic Python decision-matrix scoring engine + red-team verification + a ranked, segment-aware buying report.

Run a question, plan, or decision through 5 advisors that each use a distinct reasoning method (inversion, decomposition, analogy, naive questioning, dependency graphing), then anonymized peer review and a chairman synthesis.

Parallel divergent ideation: spawns N isolated idea branches under different cognitive frames, scores them, prunes traps, and deepens the survivors. For open-ended, high-stakes design/naming/strategy/schema problems.

Generate natural, tailored job-application answers from your own profile. You create a private, git-ignored references/profile.md from the included template; nothing personal ships with the plugin.

The config layer: safety hooks (block dangerous bash, block secret leaks), a session-context hook, and a verify-before-stop hook, registered via hooks/hooks.json. Ships a recommended-settings.json fragment (permission denylist + workflow flags). Contains no secrets.