Claude Code

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.

divination

9841

amenti-labs/opendivination

Skill Claude CodeCodex

Runs OpenDivination's CLI for tarot, I Ching, source inspection, and provenance-aware symbolic sessions for users or agents.

not rated 1 7mo ago A 29 tokens original MIT

security-guardrails

9842

ofershap/vibe-guard

Cursor rule Cursor

Vibe Guard - always-on security guardrails for AI-generated code.

not rated 1 9mo ago A 282 tokens original MIT

huiyu-safe-ai

9845

huiyu9144/huiyu-safe-ai

Skill Claude Code

Lightweight AI security guard that intercepts risky install/download commands (npm, npx, pip, cargo, git clone) to block known malicious packages and scan for suspicious code. Invoke ONLY when user runs install/download/clone commands.

not rated 1 5mo ago B 52 tokens

claude-hive

9847

PenguinMiaou/claude-hive

Plugin Claude Code

Bundles 2 skills, 3 commands · 145 tokens together

Cross-window multi-agent coordination for Claude Code — worktree isolation, GitHub PR workflows, and automated conflict detection.

not rated 1 7mo ago A tokens not measured original MIT

pdf-content-search

9848

juergenkoller-software/pdf-content-search-mcp

MCP server Claude CodeCodexCursor +2

MCP server "pdf-content-search" as configured in juergenkoller-software/pdf-content-search-mcp. Launched with /usr/local/bin/pdf-content-search-mcp. Needs 2 environment variables to run.

not rated 1 23d ago A tokens not measured original MIT

review

9849

aiflowlearn/awesome-claude-code

Command Claude Code

A review command that examines the current changes from four angles: risk, regressions, missing tests, and readability.

not rated 1 5mo ago A 0 tokens

inkra

9850

juergenkoller-software/inkra-mcp

MCP server Claude CodeCodexCursor +2

MCP server "inkra" as configured in juergenkoller-software/inkra-mcp. Launched with /Applications/Inkra.app/Contents/MacOS/inkra-mcp-server. Needs 2 environment variables to run.

not rated 1 changed 29d ago A tokens not measured original MIT

houan-mcp

9851

SHAYOUWORLD/houan-mcp

MCP server Claude CodeCodexCursor +2

Search Japanese Diet bills and meeting transcripts (NDL Kokkai API) with source attribution. Runs locally from the @codeagentjp/houan-mcp npm package.

not rated 1 changed 1mo ago A tokens not measured original MIT

mockhunter

9853

CodeShuX/mockhunter

Plugin Claude Code

Bundles 1 skill · 90 tokens together

Audit live web pages for fake/mock data — 5-phase Playwright + Claude Code skill that classifies every visible value as REAL, MOCK, LLM, HARDCODED, BROKEN, or UNKNOWN.

not rated 1 6mo ago A tokens not measured original MIT

context-budget

9855

tellmefrankie/news-engine

Skill Claude CodeCodex

Know how much context window you have left before Claude loses memory mid-task. Stop getting surprised by truncation on long coding sessions.

not rated 1 6mo ago A 0 tokens original MIT

vibeproof

9856

mrsametyildirim/vibeproof

Skill Claude CodeCodex

Audit an AI-generated app for fake completeness — features that look finished in the UI but are not actually wired to anything. Traces every user-visible promise from the button to the database and back. Use when asked to run /vibeproof, to check if an app is really done, to find fake or dead UI, unwired buttons…

not rated 1 2mo ago A 93 tokens original MIT

image-generate

9857

prenats/claude-imagine

Skill Claude Code

Transform descriptions into ultra-detailed prompts, then generate real images via the image generation server. Supports custom types, styles, moods, lighting, and composition with optional sub-agent delegation.

not rated 1 5mo ago A 40 tokens original MIT

code-review

9859

andr-ca/agentharness

Skill Claude Code

Use when reviewing a diff, pull request, or code change — systematic checklist for correctness, clarity, security, testability, and adherence to the project's conventions. Covers what to look for, how to give actionable feedback, and when to approve vs. request changes.

not rated 1 5d ago A 56 tokens original MIT

joedevflow

9860

JoeCardoso13/joedevflow

Skill Claude Code

Development workflow. Use when building a feature, creating an MVP, refactoring code, fixing a bug, or any task that involves writing or changing implementation code.

not rated 1 3mo ago A 36 tokens original MIT

web-typography

9861

simongonzalezdc/web-typography-skill

Skill Codex

Expert front-end web typography — apply this whenever you are styling text on the web or making type decisions in HTML/CSS/JSX/Tailwind. Use it to choose and pair fonts, build a type scale, set body copy and headings, tune fluid/responsive type with clamp(), fix line-height, rhythm, measure and heading wraps, improve…

not rated 1 2mo ago A 156 tokens original Apache-2.0

direct

9862

rhettcarillo/claude-code-direct-skill

Skill Claude Code

Work autonomously to a finished, verified result instead of narrating options or stopping for permission; spend the cheapest model that cannot get it wrong; report in a short scannable form; and get measurably better each run by recording what actually went wrong. Use when the owner says /direct, "do wonderful…

not rated 1 2mo ago A 121 tokens original MIT

extract-design-tokens

9863

humbleteam/extract-design-tokens

Skill Claude CodeCodex

Extracts a design-token set - palette, type, spacing, radii, shadows, motion - from a live URL, screenshots, or a CSS file, into CSS custom properties plus a JSON file in Design Tokens Format Module 2025.10. Trigger on "extract design tokens from this site", "pull the tokens from this screenshot", "turn this CSS into…

not rated 1 changed 10d ago A 111 tokens original MIT

liquid-org

9864

U0001F3A2/liquid-org

Plugin Claude Code

Bundles 2 skills · 424 tokens together

Run a task as an evolved multi-agent ORG. The compose-org skill makes the running Claude embody a proven team — one subagent per specialist talent — then grades and records the result so good teams get reused on similar future tasks. Backed by the liquid-org CLI (plan / compose / record).

not rated 1 4mo ago A 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: