81,496 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.
AI-powered development platform — 45 agents, 22 MCP servers, 39 skills for end-to-end software development across React, React Native, Flutter, .NET, and NestJS.
★not rated 4
changed 1mo agoA
tokens not measured
originalApache-2.0
Dolt/DoltHub version-control toolkit for Claude Code, via the dolthub/dolt-mcp server. A version-control-surface skill + expert agents over a Dolt backend — diagnosing DoltHub visibility, taming server sprawl, auditing the graph, and recovering incidents — with a verb-class mutation gate that keeps destructive ops…
★not rated 4
changed 20d agoA
tokens not measured
originalApache-2.0
A GitHub Projects work board as typed MCP tools: pure reads (readboardstatus, readcolumn, ...), gated epic/story lifecycle (startepic, startstory, finishepic), free column moves, and authoring verbs — plus the kyzo-plan-manage-board skill that carries the operating model.
Spec-Build-Test loop — the user defines a spec, then three agents iterate (Builder implements, Tester validates, Supervisor monitors for freezes) until the result matches. Works for any digital function — UI, APIs, CLI tools, conversational AI, data pipelines, and more.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Use when researching competitors, paid ads, Meta Ad Library creatives, TikTok ads, Instagram/TikTok organic videos, HookRadar MCP data, creative trends, AI creative analysis, reports, downloadable ad/video assets, or shareable creative tables for marketing teams.
Execute a reviewed WhyGraph plan (or a split's tasks.json) one step per fresh implementor at the step's model, with a cached-card review gate and a spec evaluation after each step, a separate acceptance run at the end, then quality and UI evaluations. The plan tool does the bookkeeping, a counted recovery ladder…
A read-only audit checklist for Hermit and Claude Code setups, covering how they are structured, used, checked, and improved, including token use and model selection.
Reviews PRDs for completeness, API accuracy, and implementation readiness. Orchestrates parallel sub-reviewers with a three-phase matrix-driven process — scaffold, fill (parallel agents including a dedicated smell pass), verify — to guarantee full coverage. Use after a PRD draft exists and before approval.
Puts the project's committed mnema record into the session's opening context without the agent asking, with the notes recorded for it on this machine beside it, the ones near the work first, and connects the mnema MCP server so it can record its own work.
★not rated 4
changed 10d agoA
tokens not measured
originalApache-2.0
A conversation guide for turning an unclear product idea or feature request into a structured product decision. It emphasizes confirming the target market, checking real user need, and looking for contrary evidence.
★not rated 4 3mo agoA145 tokens
originalMIT
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: