81,896 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.
Autonomous skill improvement loop inspired by Karpathy's autoresearch pattern. Iteratively modifies skills, evaluates against fixed evals, and keeps or discards changes to converge on higher quality. Includes eval management and convergence reporting.
★not rated 1 7mo agoA
tokens not measured
originalMIT
Structured software development workflows for Claude Code, aligned with Claude 5 generation guidance (last reviewed 2026-09-29): effort follows the session, with two overrides (high for unattended implementation and fixing). Skills cover project initialization (AGENTS.md, CLAUDE.md, and the project documents), brief…
A Japanese-speaking thinking and context assistant for the Mac command line. It helps with notes, light conversation, idea development, summaries, and routing deeper discussions to Discord.
MCP server for Meshes — emit events, manage workspaces, create rules, and inspect deliveries from any MCP-compatible client. Runs locally from the @mesheshq/mcp-server npm package.
★not rated 1 6mo agoA
tokens not measured
originalMIT
A Chinese-language plugin focused on making conversations, commits, pull requests, documents, and comments sound more natural and less machine-written. It is described as leaving code logic unchanged and being enabled by default.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Fully autonomous expert forum builder and project maturity engine. User delivers an idea, auto-distills domain experts from web sources, builds knowledge base with breadth/depth/thickness/effectiveness, scores maturity (0-100), builds project code, debugs, re-scores in adversarial loop until 100/100, then submits to…
The Good, the Bad and the Ugly — tiered multi-agent orchestration for Claude Code. The Good (brain) plans and verifies, the Bad (judgment executor) handles work needing taste, the Ugly (mechanical executor) does the grunt work — in parallel herdr panes with fenced scopes.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Remove signs of AI-generated writing from any text: articles, essays, documentation, reports, fiction, blog posts, LinkedIn posts and articles, emails, landing pages, ads, and marketing copy. Determines whether the piece is neutral/narrative (strip promotional language, tighten prose) or persuasive/converting (keep…
An intelligent component management assistant that automatically determines whether to create new components, reuse existing ones, or ask users for decisions based on their instructions. Ensures component consistency and compliance based on design system specifications. |…
Switch Claude Code between Anthropic direct and custom LLM gateway profiles via slash commands. Bring-your-own-URL, bring-your-own-key, zero secret material stored in plugin files.
Skill "security-claude" from rahozosman/security-claude, covering security architecture & threat modeling intelligence, how this skill is organized (progressive disclosure), 1. pick a mode, 2. core method (applies to every mode) and 3. doing a focused review.
Plans, documents, and reviews code architecture for software projects. Produces structured architecture documents with Mermaid diagrams through a collaborative interview workflow. Triggers on architecture planning, project structuring, folder organization, system design, component design, data flow planning, codebase…
Universal loop-engineering harness: machine-verifiable stop conditions, cross-model maker/checker (Codex maker, Claude checker), disk-based loop memory, reversibility×impact decision gates that keep human approval to irreversible actions while auto-pushing reversible work-branch commits, autonomous replan on stalls, a.
★not rated 1 4mo agoA
tokens not measured
originalMIT
Verbatim recall across Claude Code sessions, plus a gate that stops oversized skills from flooding the prompt. Pure Node, no dependencies, no API calls.
★not rated 1 3mo agoA
tokens not measured
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: