Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 612,189 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.

react CLAUDE.md

25

react/react

Instructions file

Claude Code instructions for react/react, covering react, monorepo overview and current active work.

not rated 249k +316 today A 87 tokens original MIT

analyze-pass-impact

26

react/react

Agent Claude Code

Analyzes how a specific topic affects a group of compiler passes. Used by the /plan-update skill to parallelize research across all compiler phases. Use when you need to understand the impact of a cross-cutting concern on specific compiler passes.

not rated 249k +316 today A 53 tokens original MIT

compiler-review

27

react/react

Agent Claude Code

Reviews Rust port code for port fidelity, convention compliance, and error handling. Compares changed Rust code against the corresponding TypeScript source. Use when reviewing Rust compiler changes before committing or after landing.

not rated 249k +316 today A 42 tokens original MIT

investigate-error

28

react/react

Agent Claude Code

Investigates React compiler errors to determine the root cause and identify potential mitigation(s). Use this agent when the user asks to 'investigate a bug', 'debug why this fixture errors', 'understand why the compiler is failing', 'find the root cause of a compiler issue', or when they provide a snippet of code and…

not rated 249k +316 today A 90 tokens original MIT

react/react

Skill Claude CodeCodex

Orchestrate the Rust compiler port end-to-end. Discovers the current frontier, fixes failing passes, ports new passes, reviews, and commits in a loop.

not rated 249k +316 today A 38 tokens original MIT

plan-update

30

react/react

Skill Claude CodeCodex

Use when you need to update a plan document with deep research across all compiler passes. Launches parallel subagents to analyze how a topic affects every compiler phase, then consolidates findings into the plan doc.

not rated 249k +316 today A 44 tokens original MIT

ecc

31

affaan-m/ECC

Plugin Claude Code

Bundles 39 skills, 3 commands, 15 agents · 2,761 tokens together

Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.

not rated 247k +1.1k changed yesterday A tokens not measured original MIT

affaan-m/ECC

Instructions file GitHub Copilot

Copilot instructions for affaan-m/ECC, covering ecc for github copilot, core workflow, prompt defense baseline, coding standards and immutability.

not rated 247k +1.1k yesterday A 1,025 tokens original MIT

mattpocock-skills

33

mattpocock/skills

Plugin Claude Code

Bundles 37 skills · 1,273 tokens together

Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.

not rated 247k +2.4k today A tokens not measured original MIT

skills AGENTS.md

34

mattpocock/skills

Instructions file CodexOpenCode

AGENTS.md instructions for mattpocock/skills, a project described as: Skills for Real Engineers. Straight from my .agents directory.

not rated 247k +2.4k today A 4 tokens copy · 100% MIT

skills CLAUDE.md

35

mattpocock/skills

Instructions file

Claude Code instructions for mattpocock/skills: Skills are organized into bucket folders under skills/.

not rated 247k +2.4k today A 923 tokens original MIT

NousResearch/hermes-agent

Instructions file CodexOpenCode

AGENTS.md instructions for NousResearch/hermes-agent, covering hermes agent - development guide, what hermes is, contribution rubric — what we want / what we don't, what we want and what we don't want (rejected even when well-built).

not rated 241k +1.1k today A 23,135 tokens original MIT

comps-analysis

37

NousResearch/hermes-agent

Skill Claude CodeCodex

Build comparable-company valuation workbooks in Excel.

not rated 241k +1.1k today A 13 tokens original MIT

dcf-model

38

NousResearch/hermes-agent

Skill Claude CodeCodex

Build discounted cash flow valuation workbooks in Excel.

not rated 241k +1.1k today A 14 tokens original MIT

karpathy-guidelines

40

multica-ai/andrej-karpathy-skills

Cursor rule Cursor

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

not rated 210k +559 4mo ago A 571 tokens

multica-ai/andrej-karpathy-skills

Instructions file

Claude Code instructions for multica-ai/andrej-karpathy-skills, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

not rated 210k +559 4mo ago A 522 tokens

record-browser-gif

42

deepseek-ai/deepseek-harness

Skill Claude CodeCodex ✓ vendor

Record browser or Web UI interaction demos as optimized GIFs using the available built-in browser, state-based frame capture, and deterministic encoding, then attach the GIF to a pull request with gh --attach, falling back to a dedicated assets branch where attach cannot apply. Use when asked to make, record, or…

not rated 211k +3.7k changed today A 106 tokens original MIT

deepseek-ai/deepseek-harness

Instructions file CodexOpenCode ✓ vendor

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-release stance: foundation over blast radius, repository layout, commands and host sandbox failures.

not rated 211k +3.7k changed yesterday A 3,719 tokens original MIT

deepseek-ai/deepseek-harness

Instructions file ✓ vendor

Claude Code instructions for deepseek-ai/deepseek-harness, a project described as: DeepSeek Harness: Everything is a Plugin.

not rated 211k +3.7k today A 3 tokens original MIT

deepseek-ai/deepseek-harness

Skill Claude CodeCodex ✓ vendor

Create, modify, debug, or extend dynamic Cordis Plugins, including Host Services and Events, Client Slot and theme UI, Package-private Client-to-Host calls, dynamic Tools, version updates, approval failures, and runtime diagnostics. Use this Skill to route a user request to the correct platform and Inspect Provider…

not rated 211k +3.7k today A 80 tokens original MIT

deepseek-ai/deepseek-harness

Skill Claude CodeCodex ✓ vendor

Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted…

not rated 211k +3.7k today A 69 tokens original MIT

anomalyco/opencode

Skill Claude CodeCodex

OpenCode Desktop should be RTL-aware. Use when implementing or reviewing RTL/LTR behavior in the web app, desktop app, CSS, menus, scrolling, resizing, icons, mixed-direction text, or Electron title bars.

not rated 204k +504 today A 48 tokens original MIT

opencode AGENTS.md

48

anomalyco/opencode

Instructions file CodexOpenCode

AGENTS.md instructions for anomalyco/opencode, covering branch names, commits and pr titles, style guide, general principles and destructuring.

not rated 204k +504 today A 1,893 tokens 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: