81,390 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.
A Chinese academic-writing tool based on a theory of how topics and new information connect from sentence to sentence. It labels each sentence’s topic and explanation, then checks how the paragraph develops.
Research pipeline that decides depth after the evidence: source-grade weighted scoring, worker-hidden thresholds, and type-driven investigation frames.
★not rated 4
changed 2mo agoA
tokens not measured
originalMIT
Use the local sift CLI to search Claude Code, Codex, Cursor, and OpenCode chat history when prior AI coding-assistant context, session memory, implementation history, or project decisions would help.
Utility agent for pulling benchmark data, evaluating cost vs performance, and recommending which models to use for which agents. Use on-demand for model assignment reviews.
A collection of three open legal skills for Russian law, covering grammar, logic, and rhetoric. It is released under the MIT licence, which permits broad reuse with the licence notice kept.
Deep code review with 23+ specialist Opus agents. Full call-graph tracing, web-verified findings, adversarial false-positive filtering. Supports GitHub PRs, GitLab MRs, and local branch comparisons.
★not rated 4 6mo agoA
tokens not measured
originalMIT
Use at the end of a session (or midway through a long one) to deliberately capture what was learned — lessons, decisions, workflows, state changes, and facts — into the knowledge base. The nightly harvest is a safety net for lessons; unless the host opted into KBHARVESTFACTS, /debrief is the only thing that records…
Local MCP server for desktop automation: mouse, keyboard, screen, windows, and processes. Runs locally from the go-computer-use-mcp-server npm package. Needs 2 environment variables to run.
45 production-grade compliance skills for AI coding agents. Cosmetics, food, electronics, toys, textiles, supplements, medical devices, and more. Substance checks, labeling, market entry, customs, certifications. MIT licensed. Powered by the Cleo Legal API.
★not rated 4 5mo agoA
tokens not measured
originalMIT
5 free, copy-paste Claude skills for inbox and email for small businesses — triage a full inbox, draft replies in your voice, summarize long threads, turn meeting notes into action items, and answer common questions. By Ootto.
★not rated 4 5mo agoA
tokens not measured
originalMIT
Use when the user names a company they are applying or interviewing with, asks whether a startup is safe to join, wants to know if a company's AI claims are real, or needs talking points and questions before a call.
Create, follow, and continuously maintain an Open Knowledge Format (OKF) knowledge catalog in every project — a vendor-neutral, plain-markdown standard. Bundles the okf-catalog skill, the okf-auditor agent, and a SessionStart hook that flags any project missing a catalog.
★not rated 4 5mo agoA
tokens not measured
originalMIT
Enforces ASD-STE100 Simplified Technical English on every Claude Code reply. Hooks, /ste toggle, status line badge, strict lint gate. Companion to the simple-english plugin.
LLM security guardrails for Claude Code, for a self-hosted AgentGuards appliance — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization, enforced entirely by hooks. No bundled MCP server: Claude Code's .mcp.json cannot point at a…
★not rated 4 4d agoA
tokens not measured
originalMIT
AI-Native OS - the open operating system for building an AI-native company. Skills, flows, loops, and advisor agents, plus a Handbook and Dictionary, for the whole arc of making intelligence the core of a product and org. Apply when the user is building an AI-native company: framing a hypothesis, mapping terrain…
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: