Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 438,314 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.

math-skill

10921

Wholiver/Math.Skill

Skill Claude CodeCodex

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling.

not rated 61 +3 5mo ago A 33 tokens original MIT

hyperweave-verbs

10922

InnerAura/hyperweave

Skill Claude CodeCodex

Read, verify, mutate, and round-trip HyperWeave living artifacts via the verb algebra instead of vision-parsing the SVG.

not rated 61 +2 2mo ago A SkillSpector: pass 32 tokens original Apache-2.0

norahe0304-art/30x-mckinsey-research-deck

Skill Claude Code

End-to-end playbook for producing a top-tier, McKinsey-style market-research deck (HTML page-turning presentation + print-ready PDF) for a brand or product category. Covers the research methodology (TAM/SAM/SOM bottom-up, Good/Better/Best framework, competitor profiling, customer pain points, unit economics, business…

not rated 61 +1 4mo ago A 188 tokens original MIT

uringscope

10924

rch0wdhury/uringscope

Skill Claude CodeCodex

Diagnose iouring performance and correctness problems with uringscope, an eBPF tracer and analyzer. Use when a Linux process that uses iouring shows tail latency, unexplained iou-wrk- thread explosions, suspiciously syscall-heavy behavior, silent buffer corruption, or completions that never arrive, or when strace…

not rated 61 2d ago B 110 tokens

intake

10925

shinyobjectz/montology

Skill Claude CodeCodex

The guided walkthrough for a codebase that has just installed montology (or has never written its vocabulary down) — phased questions served to the people who own the code as a clean one-question-at-a-time form in their browser (a local HTML file, no hosted service), answers returned to the agent on disk, each round…

not rated 61 +1 changed 2mo ago A SkillSpector: pass 157 tokens original Apache-2.0

digital-tech-analyst

10926

floodsung/gongzhonghao_agent_team

Agent Claude Code needs its repo

An agent for writing and editing Chinese WeChat Official Account content about digital products, such as phones, gadgets, and technology news.

not rated 61 9mo ago A 281 tokens original MIT

migration-reviewer

10928

oracle-samples/oracle-aidp-samples

Skill Claude CodeCodex

Review a migrated .ipynb for correctness — NOT just "did it run". Catches latent issues the cell-execute loop missed — wrong write-mode, lost rows, dropped columns, hardcoded paths, dead Databricks-isms, builtins shadowing, format downgrades. Outputs a structured Blockers / Important / Style / Good review report. Use…

not rated 61 +1 yesterday A 100 tokens UPL-1.0

christiandoxa/prodex

Skill Claude CodeCodex

Safely write a user prompt to and observe an already-running plain prodex s session through its default expose MCP bridge.

not rated 61 changed 2mo ago A SkillSpector: pass 31 tokens original Apache-2.0

hackathon

10931

timothy-agent/timothy

Skill Claude CodeCodex

Carries a hackathon from its published rules to a submission-ready project. Extracts every rule and constraint first, ranks ideas that all comply, and builds toward the exact deliverables the judges expect. Use when a mission is given a hackathon link or an inline hackathon brief. Do not use for general coding or…

not rated 61 changed 1mo ago A 83 tokens AGPL-3.0

Mr-remon219/search-boost

Skill Claude CodeCodex

Research independent web questions with authorized host subagents, then synthesize cited evidence and gaps. Use for requested parallel or multi-angle research, not ordinary lookups. Check child MCP access before fan-out; disclose serial fallback when delegation is unavailable.

not rated 61 changed 1mo ago A 56 tokens original MIT

validate-hypothesis

10933

JOINCLASS/ai-ceo-framework

Skill Claude CodeCodex

Business hypothesis validation skill. Validates ideas through 6 phases (origin check, market confirmation, interviews, evaluation, willingness to pay, minimum viable test, go/no-go decision). Usage: /validate-hypothesis "idea summary.

not rated 61 yesterday A 0 tokens original MIT

skill-mas

10934

linhh29/Skill_MAS

Plugin Claude Code

Bundles 2 skills, 1 hook · 92 tokens together

Automatically select the appropriate optimized Skill-MAS strategy for the current task and orchestrate work with existing skills.

not rated 61 +2 1mo ago A tokens not measured original Apache-2.0

fleet-core

10935

larcane97/clausona

Plugin Claude Code

Bundles 1 skill · 53 tokens together

Shared rules for the clausona fleet skills (superset-fleet, herdr-fleet, orca-fleet, tmux-fleet). Claude Code installs it with them; in Codex, add it yourself.

not rated 61 changed 8d ago A tokens not measured original MIT

bseoa

10936

sethblack/black-seo-analyzer

MCP server Claude CodeCodexCursor +2

MCP server "bseoa" as configured in sethblack/black-seo-analyzer. Launched with https://github.com/sethblack/black-seo-analyzer/releases/download/v26.9.16/bseoa. Needs 1 environment variable to run.

not rated 61 today A tokens not measured

multi-agent-review

10937

riekelt/multi-agent-review

Plugin Claude Code

Bundles 1 skill · 117 tokens together

Multi-model consensus review for specs and plans — panels haiku + sonnet tiers per topic, opus juror on disagreements, fail-closed verdict gate.

not rated 60 2mo ago A tokens not measured

conference-watch

10938

Zsun79/ConferenceWatch

Skill Claude CodeCodex

Watch and report on upcoming AI/ML conferences: submission deadlines (every stage), dates, location, special sessions / calls for papers, official links, and a 5-year acceptance-rate trend. Use when the user asks about future AI conference deadlines, wants to plan submissions, compare venues, or track a set of…

not rated 60 4mo ago A 96 tokens

minirag-mcp

10939

sfrangulov/minirag-mcp

MCP server Claude CodeCodexCursor +2

Local-first RAG MCP server: hybrid search over your documents, fully local. Runs locally from the minirag-mcp Python package. Needs 13 environment variables to run.

not rated 60 yesterday A Socket: warn tokens not measured original MIT

technology-mapping

10940

AlphaMao1/AlphaMao-technology-mapping

Skill Claude CodeCodex

A skill for building a broad map of a technology field, including its research origins, open-source work, and commercial companies. It is designed for technology-led areas such as quantum computing, nuclear fusion, and AI agents.

not rated 60 5mo ago A 106 tokens

video-edit

10941

hAcKlyc/cameo

Skill Claude CodeCodex

Edit, transform, trim, convert, resize, retime, or analyze video and audio files with ffmpeg/ffprobe on the command line. Use when the user wants to cut or trim a clip, change container/format or codec, scale or crop dimensions, change speed or frame rate, extract or replace or mix audio, concatenate clips, burn in or…

not rated 60 5mo ago A 130 tokens AGPL-3.0

hmr

10942

promplate/hmr

MCP server Claude CodeCodexCursor +2

Docs for hot-module-reload and reactive programming for Python (hmr on PyPI). Remote server at pyth-on-line.promplate.dev.

not rated 60 today A tokens not measured

mind-clone

10944

yzfly/Mind-Cloning-Engineering

Skill Claude CodeCodex

Activate a Cognitive Digital Twin. Can simulate a custom subject (via core/ directory) OR load pre-installed celebrity/expert personas (from personas/ directory).

not rated 60 11mo ago A 35 tokens original Apache-2.0

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: