35,518 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
Build something straight from a prompt - a short requirements interview, then implement it and run an adversarial build-and-review loop until an independent reviewer is satisfied. Use when the user wants to build a feature without writing a specification first, or mentions "/freehand".
Iteratively refine beads for ralph-tui execution through 4-6 polishing rounds until convergence, ensuring each bead fits one agent context window, has quality gates appended, uses correct bd CLI syntax, and follows schema-backend-UI dependency ordering. Use when user wants to polish beads for ralph, refine ralph…
Interrogate the user about a plan or design, then iterate against user-supplied acceptance checks in a self-scoring loop until every check passes. Use when the user wants their plan stress-tested AND wants the model to keep refining until a concrete set of pass/fail criteria are satisfied. Triggers on "grill me with…
Guided architecture and infrastructure design workflow — from requirements gathering to code implementation — with interactive Mermaid diagrams, browser preview, and structured documentation.
★not rated 2 1mo agoA
tokens not measured
originalMIT
Engineering workflow in one resumable DOSSIER.md: dependency-ordered tasks, invariants, drift detection, cross-repo state, a rolling status log, and scout + reviewer subagents.
★not rated 2 2d agoA
tokens not measured
originalISC
A comprehensive software engineering plugin that transforms feature requests into structured tasks, manages development workflow, and follows best practices for code implementation.
★not rated 2 9mo agoA
tokens not measured
originalMIT
Plánování krabičkové diety s reálnými nutričními daty a cenami z Rohlik.cz. Auto-aktivovaný orchestrátor — uživatel mluví přirozeně, plugin sám pozná, jestli jde o setup maker, plánování, nebo nákup. Maso a ryby vždy 100 % spotřeba (nemrazí se). Optimalizuje odpad, hlídá makra více osob.
A disciplined AI-assisted development workflow with specification-first development, test-driven implementation, ADRs, and traceable task management. Inspired by the Rue language development process.
Generates PM documents (PRDs, specs, briefs, user stories, decision docs) from templates and knowledge base context. Supports two modes — auto-generate for immediate first drafts, or co-authoring for guided iterative writing. Invoked when asked to write, generate, or co-author product documents, or when user says…
Orchestrate 7-phase development from idea to deployment with 11 specialized AI agents. Use when starting a new project, resuming development, or managing the full product lifecycle.
Reviews every Claude Code plan before ExitPlanMode is allowed. Pick a backend per session (Opus 4.8, Sonnet 5, codex gpt-5.6-sol, or Gemini 3.1 Pro via agy) — only ones that pass a live probe are offered; autoswe runs review locally. Denies exit on P0/P1 findings and re-injects them so Claude revises the plan; loop…
★not rated 2 23d agoA
tokens not measured
originalMIT
Content Skills for Claude, by SE Ranking & Planable. Ten content-lifecycle pipelines on live SE Ranking + Planable data: campaign briefs with distribution and tracking, keyword clusters on a 12-week calendar, batch content refresh, socially validated niche plans, article-to-social packs, social-to-SEO idea mining, gap.
★not rated 2 28d agoA
tokens not measured
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: