Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 415,067 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.

token-diet

3361

Kulaxyz/token-diet

Skill Claude CodeCodex

Cut token usage across the whole session without losing correctness or substance — concise user replies, lean tests/docs/plans/comments, tight code, disciplined context and tool use, and cheap sub-agent delegation. Load when the user wants less verbosity, lower cost, fewer tokens, or a "token diet" / "lean mode"; also…

not rated 472 +2 2mo ago A 81 tokens

sosumi

3362

NSHipster/sosumi.ai

Skill Claude CodeCodex

Fetches Apple documentation as Markdown via Sosumi. Use for Apple API reference, Human Interface Guidelines, WWDC transcripts, and external Swift-DocC pages.

not rated 472 4d ago A SkillSpector: pass 36 tokens original MIT

fusion-plan

3363

duolahypercho/fusion-fable

Skill Claude CodeCodex

Produce a high-confidence, CONCISE implementation / architecture / strategy PLAN that follows the OMC plan system end to end. It first runs OMC's real requirements interview (auto-chains the omc-plan skill: one question at a time, explore-first, Analyst consult) to produce an initial plan in .omc/plans/, then DEEPENS…

not rated 472 +1 1mo ago A SkillSpector: warn 266 tokens original MIT

skill-anything

3364

AgentSkillOS/SkillAnything

Skill Codex

Automatically generate production-ready Skills for any software, API, CLI tool, library, workflow, or service. Use this skill whenever the user wants to create a skill from scratch for a target application, convert an existing tool into an agent-native skill, generate skills for multiple platforms (Claude Code…

not rated 472 +1 5mo ago A 156 tokens original MIT

octocode

3366

Muvon/octocode

MCP server Claude CodeCodexCursor +2

AI-powered code indexer with semantic search and knowledge graphs. Runs locally from the @muvon/octocode npm package.

not rated 472 +2 3d ago A tokens not measured original Apache-2.0

ak-maintainer

3367

saltbo/agent-kanban

Skill Codex

Manage authorized project work through Agent Kanban and Realmroot Toolbox, typically in scheduled-task or heartbeat-triggered Sessions. Proactively inspect what needs doing, delegate execution to other Agents, and coordinate and review their Tasks as a manager.

not rated 472 +3 changed today A 50 tokens

simplify-codebase

3368

tt-a1i/simplify-codebase

Skill Claude CodeCodex

Simplification audit or authorized codebase simplification whose stated objective is to remove accidental complexity. Use for evidence-backed deletion or consolidation of dead code, duplicate state, redundant APIs or layers, ownerless abstractions, obsolete compatibility or design records, and over-engineering in any…

not rated 472 +13 changed 9d ago A 93 tokens original MIT

memtrace-skills

3369

syncable-dev/memtrace-public

Plugin Claude Code

Bundles 27 skills, 4 commands · 2,947 tokens together

Memtrace skills for codebase exploration, code search, relationship analysis, temporal evolution, blast radius impact, code quality, graph algorithms, API topology, GitHub PR code review, multi-agent fleet coordination (branch-scoped intents, conflict classification, and agent-judged Class C resolution), and…

not rated 471 +3 yesterday A tokens not measured

semantic-anchors

3370

LLM-Coding/Semantic-Anchors

Plugin Claude Code

Bundles 6 skills · 501 tokens together

Semantic anchor skills for translating established methodologies and installing persistent coding-agent context.

not rated 470 +3 yesterday A tokens not measured original Apache-2.0

jackson-video-resources/markov-hedge-fund-method

Plugin Claude Code

Bundles 1 skill · 126 tokens together

Markov regime detection for any asset. Labels each day Bull/Bear/Sideways from a rolling-return rule, builds the maximum-likelihood transition matrix, forecasts n-step ahead via Chapman-Kolmogorov, solves the stationary distribution, and runs a no-lookahead walk-forward backtest reporting Sharpe and max drawdown.…

not rated 469 3mo ago A tokens not measured

zettaranc-perspective

3373

lululu811/zettaranc-skill

Skill Claude CodeCodex

A Chinese-language framework for analysing mainland Chinese stocks, trading methods, investment portfolios, and broader career or business decisions. It is an analysis framework, not a trading system.

not rated 469 +6 12d ago A 388 tokens original MIT

hevy-mcp

3374

chrisdoc/hevy-mcp

Plugin Claude Code

Bundles 11 skills, 2 MCP servers · 724 tokens together

Read, analyze, create, and update Hevy workouts, routines, exercises, and body measurements in Claude.

not rated 469 +13 6d ago A tokens not measured original MIT

academic-rebuttal

3375

TobiasLee/Rebuttal-Skill

Skill Claude CodeCodex

Use when an author has received peer-review comments and scores for an academic paper and needs to diagnose underlying reviewer concerns, decide whether a rebuttal is worthwhile, plan rebuttal experiments, or prepare evidence-grounded response material and revision plans for the author to review and finalize. Produces…

not rated 469 +1 25d ago A 97 tokens

binggo-mcp

3376

luovicter-collab/bilibinggo

Skill Claude CodeCodex

A coding-agent interface for the local Binggo (bilibinggo) Bilibili lottery helper console. Bilibili is a Chinese video-sharing platform, and a lottery console helps manage related activities.

not rated 468 15d ago A 191 tokens

graymatter

3377

angelnicolasc/graymatter

MCP server Claude CodeCodexCursor +2

MCP server "graymatter" as configured in angelnicolasc/graymatter. Launched with graymatter mcp serve.

not rated 468 +3 6d ago A tokens not measured original MIT

triage-orchestrator

3378

tonbistudio/hermes-multi-agent-workflow

Skill Claude CodeCodex

The pipeline driver for the Hermes Multi-Agent Workflow. Triggered by new intake tasks on the triage board. Dedups, scores, fans out research, routes, proposes at the human gate, and on approval lets the engine spawn the fulfillment chain. It is DELIBERATELY THIN: it calls engine/ for every deterministic step and only…

not rated 468 +11 3mo ago A SkillSpector: warn 90 tokens original MIT

paper-fetch

3379

yogsoth-ai/de-anthropocentric-research-engine

Skill Claude CodeCodex

Retrieve one specified academic paper (by title, arXiv ID, DOI, URL, or a local .md/.txt/.pdf path the caller already has) and land it on disk as source.md plus a source.meta.json carrying a line-number section index. Checks context/papers/ for an existing copy first; local files and direct PDF URLs are read directly…

not rated 468 +24 yesterday A SkillSpector: pass 182 tokens original Apache-2.0

swarm-pr-review

3380

ZaxbyHub/opencode-swarm

Skill Claude Code

Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…

not rated 468 +2 today A SkillSpector: warn 91 tokens original MIT

repo-docs

3381

YurunChen/repo-docs-skills

Skill Claude CodeCodex

Build and maintain a Markdown guide that helps humans understand a repository through real behavior, concepts, and evidence. Use when a user asks to understand a repo, generate or update repo-docs, answer repo-architecture/onboarding questions, seed docs for a new project, sync docs after code changes, or delete…

not rated 467 +5 2mo ago A 69 tokens

ai-agent-builder

3382

claude-office-skills/skills

Skill Claude CodeCodex

Build AI agents with tools, memory, and multi-step reasoning - ChatGPT, Claude, Gemini integration patterns.

not rated 467 +14 7mo ago A Socket: passSnyk: warn 25 tokens original MIT

editing-model-diagrams

3383

goadesign/model

Skill Claude CodeCodex

Creates, edits, reviews, and regenerates C4 architecture diagrams written with goa.design/model and the mdl CLI. Use when changing Model DSL, model.go or views.go files, system landscape, context, container, component, dynamic, or deployment views, element relationships, boundaries, layout, or generated SVG diagrams.

not rated 466 +1 24d ago A SkillSpector: pass 69 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: