Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 418,074 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.

procmon-mcp

8905

0xhackerfren/ProcMon-MCP

MCP server Claude CodeCodexCursor +2

MCP server "procmon-mcp" as configured in 0xhackerfren/ProcMon-MCP. Runs locally from the procmon-mcp Python package.

not rated 80 4mo ago A tokens not measured original MIT

j5ik2o/okite-ai

Skill Claude CodeCodex

An implementation guide for building CQRS systems, which separate changing data from reading it, and event sourcing systems, which record changes as events, with Apache Pekko and Scala 3.

not rated 80 +1 5mo ago A 368 tokens original MIT

causal-memory

8908

JingxuanC/causal-memory

Plugin Claude Code

Bundles 1 skill, 2 commands · 118 tokens together

Persistent causal memory for Claude Code — decisions, outcomes, and lessons that survive compaction. Same-context counterfactuals (natural experiments), a falsifiable prediction ledger, and an activation skill that teaches when to recall and record.

not rated 80 +2 13d ago A tokens not measured original Apache-2.0

crit

8909

kevindutra/crit

Plugin Claude Code

Bundles 3 skills, 3 commands · 220 tokens together

Review markdown documents with an interactive TUI. Leave inline comments, then let Claude address the feedback automatically.

not rated 80 6mo ago A tokens not measured

mlflow

8910

mlflow/skills

Plugin Claude Code

Bundles 13 skills, 1 hook · 1,409 tokens together

Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate.

not rated 79 +2 changed 6d ago A tokens not measured original Apache-2.0

using-git-worktrees

8911

LIDR-academy/lidr-specboot

Skill Claude CodeCodex

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback.

not rated 79 +5 2mo ago A SkillSpector: warn 36 tokens original MIT

komi-learn

8914

kurikomi-labs/komi-learn

Plugin Claude Code

Bundles 4 hooks

A continuous, zero-friction learning layer: the agent learns about you and improves its own skills across every session, and can share anonymized, provenance-verified learnings to a global pool. Inspired by Hermes Agent.

not rated 79 3mo ago A tokens not measured original MIT archived

opprime-world-key

8916

garyqlin/opprime-world-key

Skill Claude CodeCodex

A key for giving an AI agent an identity and place in Opprime World, an online virtual world. Registration provides an identity ID, land, a house, an email address, and an API key for supported operations.

not rated 79 3mo ago A 44 tokens original MIT

conference-report

8917

KerberosClaw/kc_ai_skills

Skill Claude CodeCodex

Use when the user attended one or more sessions of a conference (with audio recordings + slide photos) and needs help building (1) faithful per-session reconstructions in markdown (slide visuals + speaker transcript with Whisper hallucination annotations), and (2) a downstream report deliverable whose scope and format…

not rated 79 5d ago A SkillSpector: pass 146 tokens original MIT

NatsuFox/ClaudeChrome

Skill Codex

Extract API endpoints from the active ClaudeChrome browser tab and save them as local artifacts. Use when the user asks to find, capture, reverse engineer, document, or generate Python scripts for endpoints used by the current tab, this page, a live website, or a user-specified browser interaction in ClaudeChrome.

not rated 79 +1 26d ago A 70 tokens

claude-harness

8919

panayiotism/claude-harness

Plugin Claude Code

Bundles 6 skills, 1 agent, 8 hooks · 382 tokens together

Long-running agent harness with 5-layer memory architecture, GitHub integration via gh CLI, autonomous batch processing with a dedicated implementer subagent, Agent Teams with ATDD, quality-gate hooks, and 6 Agent Skills.

not rated 79 2mo ago A tokens not measured original MIT

brainctl

8921

TSchonleber/brainctl

Skill Claude CodeCodex

Unified agent memory CLI — read, write, search, and maintain the shared memory spine (brain.db). Use for persistent cross-session memory, knowledge graph, event logging, decisions, affect tracking, and consolidation.

not rated 79 1mo ago A 45 tokens original MIT

memory-layers

8922

MelodyTung888/memory-layers-skill

Skill Claude CodeCodex

A five-layer method for turning experiences into lasting knowledge and personal principles. It is triggered by requests to summarise lessons, identify patterns, or form rules.

not rated 79 5mo ago A 121 tokens

scammer

8923

naxiaoduo/Scammer.skill

Skill Claude Code

A scam-message checker that analyzes suspicious texts, images, or conversation descriptions. It can identify the likely stage of a scam and suggest what the sender may try next.

not rated 79 +1 5mo ago A 50 tokens original MIT

browser-tester

8926

incubrain/foundry

Agent Claude Code

UI/UX visual bug detection using the agent-browser skill. Read-heavy — only modifies files when explicitly asked.

not rated 79 18d ago A 0 tokens

kali

8927

SeaC-25/Kali-Security-MCP

MCP server Claude CodeCodexCursor +2

One of 3 in .mcp.json

MCP server "kali" as configured in SeaC-25/Kali-Security-MCP. Launched with C:\Windows\py.exe -3 mcp_server.py --tool-profile harness. Needs 2 environment variables to run.

not rated 79 1mo ago A tokens not measured original MIT

fort

8928

djadmin/fort

Plugin Claude Code

Bundles 1 skill, 3 commands · 181 tokens together

Audit your Mac's security posture from Claude Code, understand what each finding means and why it matters, then fix what's safe. Drives the fort CLI over your shell and remediates only what you approve. Read-only by default. Findings map to SOC 2 / ISO 27001 / NIST / CIS when you need audit evidence.

not rated 79 +1 2mo ago A tokens not measured original MIT

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: